Claim · 2023-11-21 · revision · Stated in source · Supported

Claude 2 model card states what the model-card question “Red-teaming” 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

Claude 2 model card → states provision → Red-teaming

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

Claude 2 model cardstates provision ↓Red-teaming

Machine-checkedStated in sourceSupported

Supporting evidence: primary · 1 source

Provision: Model-card question · provision ID model-card-q12
Date: 2023-11-21 · revision Records dated 2023 →

Scope and limitsThe card states pre-deployment red-teaming by external red teamers including crowdworker platforms on Trust and Safety topics, and red-teaming for unnamed national security risks. Section 3.1 adds a crowdworker red-teaming task and Section 3.4 automated red-teaming on 328 held-out prompts. No number of testers or period is given. 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

Model Card and Evaluations for Claude Models, with 'Claude 2.1 Model Card Appendix' (update of November 21, 2023)

Anthropic · Publication date unknown

Cite the original source

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

Source excerpt

“Before deployment, we also worked with external red teamers, including crowdworker platforms, to test Claude 2 on a range of Trust and Safety related topics”

Location in source Section 2 'Evaluations and Red Teaming', PDF p. 2

How it was read Retrieved directly from the publisher

Machine-checked · 2026-11-03

Source details and check notes

Authors: Anthropic
Version: Retrieved for the candidate pack on 2026-11-02 (SHA-256 e735ad89f95c7aa295459e0ef9153d2c54a7503f16ff39c8e20b9b4f22fd4d56) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256. The Claude 2 model card as re-issued with a 'Claude 2.1 Model Card Appendix' (16 pages), linked from Anthropic's Claude 2.1 announcement. Its update line is dated November 21, 2023; the card prints no issue date. A later expression of the card than the 14-page expression the dataset already holds.
Version date: 2023-11-21
Canonical address: Open the canonical source ↗
Accessed: 2026-11-02
Language: English (en)
Attribution: Anthropic, “Model Card and Evaluations for Claude Models, with 'Claude 2.1 Model Card Appendix' (update of November 21, 2023)”.
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). The quotation (25 words) matched the card’s text retrieved for the candidate pack on 2026-11-02 (SHA-256 e735ad89f95c7aa295459e0ef9153d2c54a7503f16ff39c8e20b9b4f22fd4d56) and again on 2026-11-03 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. No human editorial review.

primary sourceSupports the claim

Model Card and Evaluations for Claude Models, with 'Claude 2.1 Model Card Appendix' (update of November 21, 2023)

Anthropic · Publication date unknown

Cite the original source

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

Source excerpt

“We evaluated and red-teamed Claude 2 and previous Claude models for several national security and safety related risks.”

Location in source Section 2 'Evaluations and Red Teaming', PDF p. 2

How it was read Retrieved directly from the publisher

Machine-checked · 2026-11-03

Source details and check notes

Authors: Anthropic
Version: Retrieved for the candidate pack on 2026-11-02 (SHA-256 e735ad89f95c7aa295459e0ef9153d2c54a7503f16ff39c8e20b9b4f22fd4d56) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256. The Claude 2 model card as re-issued with a 'Claude 2.1 Model Card Appendix' (16 pages), linked from Anthropic's Claude 2.1 announcement. Its update line is dated November 21, 2023; the card prints no issue date. A later expression of the card than the 14-page expression the dataset already holds.
Version date: 2023-11-21
Canonical address: Open the canonical source ↗
Accessed: 2026-11-02
Language: English (en)
Attribution: Anthropic, “Model Card and Evaluations for Claude Models, with 'Claude 2.1 Model Card Appendix' (update of November 21, 2023)”.
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). The quotation (18 words) matched the card’s text retrieved for the candidate pack on 2026-11-02 (SHA-256 e735ad89f95c7aa295459e0ef9153d2c54a7503f16ff39c8e20b9b4f22fd4d56) and again on 2026-11-03 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. 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-anthropic-claude-2-1-q12