Claim · 2026-06-12 · revision · Stated in source · Supported

Muse Spark Safety & Preparedness Report states what the model-card question “Persuasion” asks.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Muse Spark Safety & Preparedness Report → states provision → Persuasion

Where it appears

Model cards compared →

Claim and evidence

Muse Spark Safety & Preparedness Reportstates provision ↓Persuasion

Machine-checkedStated in sourceSupported

Supporting evidence: primary · 1 source

Provision: Model-card question · provision ID model-card-q10
Subject version: Earliest located expression printing April 14, 2026; the expression read prints June 12, 2026 · Published 2026-04-14 · Effective date not established · Revised 2026-06-12
Date: 2026-06-12 · revision Records dated 2026 →

Scope and limitsThe report states a multi-turn social-engineering capability evaluation (an attacker model trying to convince a simulated victim), with composite scores against open models (Figure 20), as part of the cyber domain, and concludes that the capability is not high enough to trigger a high-risk determination under its framework. The victims are simulated: no result with human subjects is reported. Methods are not recorded (hazard rule). What the card states, quoted from the expression read. A card is the developer’s own account: not evidence that an evaluation was run as described, that a safeguard works, or that a finding is independent.

The evidence 02

primary sourceSupports the claim

Muse Spark Safety & Preparedness Report (arXiv 2606.12429v1)

Meta · Publication date unknown

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“we have included results from an evaluation developed by Charlemagne Labs that specifically measures social engineering capabilities in multi-turn settings.”

Location in source Section 2.2.2.3 'Social Engineering Capabilities', PDF p. 47

How it was read Retrieved directly from the publisher

Machine-checked · 2026-11-04

Source details and check notes

Authors: Meta
Version: Retrieved for the candidate pack on 2026-11-04 (SHA-256 977d071052e3f5dc267e1022671babf6a7967111f9bf2ad84e88b6419b405e61) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256. Meta's own address for the report answered HTTP 400 to the candidate pack, so the report was read on arXiv. The copy read prints 'Date: June 12, 2026'; arXiv's margin stamp on its first page reads 14 May 2026, the submission date.
Version date: 2026-06-12
Canonical address: Open the canonical source ↗
Accessed: 2026-11-04
Language: English (en)
Attribution: Meta, “Muse Spark Safety & Preparedness Report (arXiv 2606.12429v1)”.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, model cards compared (research/model-cards-2). The quotation (20 words) matched the card’s text retrieved for the candidate pack on 2026-11-04 (SHA-256 977d071052e3f5dc267e1022671babf6a7967111f9bf2ad84e88b6419b405e61) and again on 2026-11-04, after the adjudication, in a fresh retrieval with the same SHA-256. Matching ignored differences of whitespace, case, quotation marks, dashes, PDF line-break hyphens and Unicode compatibility forms, so the source’s typography can differ. A cross-family machine check (2026-11-04, item 28) checked this passage’s cell; its finding was applied at the adjudication of 2026-11-04. No human editorial review.

primary sourceSupports the claim

Muse Spark Safety & Preparedness Report (arXiv 2606.12429v1)

Meta · Publication date unknown

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“we do not find the capabilities of the model (without system level guardrails) to be sufficiently high to trigger a determination of high risk according to our Advanced AI Scaling Framework”

Location in source Section 2.2.2.3 'Social Engineering Capabilities', PDF p. 48

How it was read Retrieved directly from the publisher

Machine-checked · 2026-11-04

Source details and check notes

Authors: Meta
Version: Retrieved for the candidate pack on 2026-11-04 (SHA-256 977d071052e3f5dc267e1022671babf6a7967111f9bf2ad84e88b6419b405e61) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256. Meta's own address for the report answered HTTP 400 to the candidate pack, so the report was read on arXiv. The copy read prints 'Date: June 12, 2026'; arXiv's margin stamp on its first page reads 14 May 2026, the submission date.
Version date: 2026-06-12
Canonical address: Open the canonical source ↗
Accessed: 2026-11-04
Language: English (en)
Attribution: Meta, “Muse Spark Safety & Preparedness Report (arXiv 2606.12429v1)”.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, model cards compared (research/model-cards-2). The quotation (31 words) matched the card’s text retrieved for the candidate pack on 2026-11-04 (SHA-256 977d071052e3f5dc267e1022671babf6a7967111f9bf2ad84e88b6419b405e61) and again on 2026-11-04, after the adjudication, in a fresh retrieval with the same SHA-256. Matching ignored differences of whitespace, case, quotation marks, dashes, PDF line-break hyphens and Unicode compatibility forms, so the source’s typography can differ. A cross-family machine check (2026-11-04, item 28) checked this passage’s cell; its finding was applied at the adjudication of 2026-11-04. No human editorial review.

Status and meaning

Editorial status. Machine-checked. Machines found this record and checked it against its sources; no person accepted it individually. 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. Dated as the card read is dated: the date of its revision, as the source records it.

Record ID mc-cell-meta-muse-spark-q10