Claim · 2025-07-24 · publication · Stated in source · Supported

The SafeWork-R1 report states that the model was developed with the laboratory's SafeLadder framework of large-scale, progressive, safety-oriented reinforcement-learning post-training supported by multi-principled verifiers.

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

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law → states provision → SafeLadder: large-scale, progressive, safety-oriented reinforcement-learning post-training with multi-principled verifiers

Where it appears

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

Claim and evidence

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Lawstates provision ↓SafeLadder: large-scale, progressive, safety-oriented reinforcement-learning post-training with multi-principled verifiers

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Provision: Statement · provision ID shlab-safework-r1-safeladder
Date: 2025-07-24 · publication Records dated 2025 →

Scope and limitsA description of the developer's method in its own report, not an independent evaluation of its effect.

The evidence 01

primary sourceSupports the claim

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law

arXiv · 2025-07-24

Cite the original source

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

Source excerpt

“SafeLadder framework, which incorporates large-scale, progressive, safety-oriented reinforcement learning post-training, supported by a suite of multi-principled verifiers”

Location in source Abstract

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Shanghai Artificial Intelligence Laboratory
Version: Dated document, retrieved on 2026-10-29 (SHA-256 109bdd4579feaaf689d89176b184f4036d487af0308f6305cecc1d5dd06eafee) directly from the publisher. Version: 2507.18576v1. PDF of version 1 (24 July 2025); the abstract page notes a later v3 of 7 August 2025, not inspected.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Shanghai Artificial Intelligence Laboratory, “SafeWork-R1: Coevolving Safety and Intelligence under the AI-45° Law”, 2025-07-24.
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, Chinese frontier-AI institutions, third collection (research/china-labs-3). The quotation (17 words) matched the text retrieved for the candidate pack on 2026-10-29 and again in a fresh retrieval the same day, read directly from the publisher. 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. Submission date of the cited arXiv version; not the model's release date and not the date of later versions.

Record ID c3-shlab-safework-r1-safeladder