{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"petri","title":"Petri : An open-source auditing tool to accelerate AI safety research","aliases":[],"authors":[],"primaryFunction":"governance","secondaryFunctions":[],"kind":"method","sourceId":"petri-publication","attributionSourceId":"petri-publication","originalUrl":"https://www.anthropic.com/research/petri-open-source-auditing","publicationDate":"2025-10-06","updatedOn":"2026-10-25","areas":[],"scopeNote":{"en":"Relevance is assigned to the research question and stated conditions of the work. A topic tag is not a risk rating.","zh":"风险关联依据研究问题及明确条件建立，主题标签不代表风险评级。"},"protocolIds":["petri"],"contributions":[{"organizationId":"anthropic","role":"publisher","sourceId":"petri-publication","locator":"Official publication masthead and article byline"}],"summary":{"en":"Provides an automated auditing tool for constructing and exploring behavioral safety tests with auditor and target models.","zh":"通过审计模型与目标模型，提供自动构造和探索行为安全测试的工具。"},"note":{"question":null,"method":null,"finding":null,"supports":null,"limits":null,"connections":null},"resources":[],"noteStatus":{"question":"limited","method":"limited","finding":"limited","supports":"limited","limits":"limited","connections":"limited"},"noteAvailability":{"en":"A substantive NUWA research note is not yet available. The repeated draft sections were removed pending review of the original methods, findings and limitations; use the original publication for the research account.","zh":"实质性的 NUWA 研究笔记尚未完成。重复草稿章节已移除，待核查原始方法、发现与限制；研究内容请以原始出版物为准。"},"noteSourceLocator":"No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence.","tags":[]},"reading":{"id":"petri","title":"Petri : An open-source auditing tool to accelerate AI safety research","en":{"takeaway":"Automated multi-turn auditing surfaces hypotheses and transcripts, but pilot scores remain provisional.","question":"Can seed-driven simulated interactions efficiently expose behaviors that deserve deeper alignment investigation?","design":"An auditor plans and interacts with a target through simulated users/tools; a judge scores transcripts. The pilot covers diverse seeds and a whistleblowing ablation study.","findings":["Whistleblowing changes with granted agency, leadership complicity and the perceived wrongdoing.","Some harmless wrongdoing narratives also elicit disclosure, challenging a simple harm-minimization explanation."],"interpretation":"NUWA interpretation: positive transcripts and controlled ablations are more informative than treating an aggregate pilot score as universal alignment quality.","limits":"The article explicitly describes a small provisional scenario set, imperfect AI auditors and evaluation-awareness complications. The separate full technical report was not read here.","connections":["NUWA connection: automated-alignment-mitigation uses Petri for an additional audit after benchmark optimization; this does not make that audit an exhaustive safety test."],"decisionRelevance":"NUWA recommendation: inspect transcripts and vary hypothesized causes; label seed coverage and judge limitations alongside any score."},"zh":{"takeaway":"自动多轮审计可产生假设与轨迹，但试点分数仍属暂定。","question":"种子指令驱动的模拟互动能否高效发现值得深入调查的对齐行为？","design":"审计智能体通过模拟用户与工具规划和交互，裁判对轨迹评分；试点覆盖多种种子，并对举报行为做消融。","findings":["举报随授权自主性、领导共谋及所感知问题性质改变。","一些无害问题叙事也引发披露，使单纯最小化伤害解释受到质疑。"],"interpretation":"NUWA 解读：阳性轨迹与受控消融比把聚合试点分数视为通用对齐质量更有信息。","limits":"文章明确说明场景集合有限、AI 审计者不完美且存在评估意识问题；本次未阅读单独技术报告。","connections":["NUWA 关联：自动对齐缓解在基准优化后使用 Petri 补充审计，但并不构成穷尽安全测试。"],"decisionRelevance":"NUWA 建议：检查轨迹并改变假定原因，分数旁保留种子覆盖与裁判局限。"},"sourceRefs":[{"sourceId":"petri-publication","url":"https://www.anthropic.com/research/petri-open-source-auditing","locator":"Broad-coverage pilot-alignment evaluations","version":"Selected original resource https://www.anthropic.com/research/petri-open-source-auditing; sha256:7e988b2e577de252b4b8404d10266c39adfc5af9a52b8c8555d6022c1e7d2650; archived source capture; exact capture time not independently established","artifactSha256":"7e988b2e577de252b4b8404d10266c39adfc5af9a52b8c8555d6022c1e7d2650"},{"sourceId":"petri-publication","url":"https://www.anthropic.com/research/petri-open-source-auditing","locator":"Case study: Whistleblowing behavior","version":"Selected original resource https://www.anthropic.com/research/petri-open-source-auditing; sha256:7e988b2e577de252b4b8404d10266c39adfc5af9a52b8c8555d6022c1e7d2650; archived source capture; exact capture time not independently established","artifactSha256":"7e988b2e577de252b4b8404d10266c39adfc5af9a52b8c8555d6022c1e7d2650"},{"sourceId":"petri-publication","url":"https://www.anthropic.com/research/petri-open-source-auditing","locator":"Get started","version":"Selected original resource https://www.anthropic.com/research/petri-open-source-auditing; sha256:7e988b2e577de252b4b8404d10266c39adfc5af9a52b8c8555d6022c1e7d2650; archived source capture; exact capture time not independently established","artifactSha256":"7e988b2e577de252b4b8404d10266c39adfc5af9a52b8c8555d6022c1e7d2650"}],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"},"review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected substantive sections of the full source body","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"00d6e0c04cec980113bcceb683e0bf57a8914b2177c2db51049c774f6314d087"}},"sources":[{"id":"petri-publication","title":"Petri : An open-source auditing tool to accelerate AI safety research","url":"https://www.anthropic.com/research/petri-open-source-auditing","version":"Source capture 2026-10-25","publicationDate":"2025-10-06","datePrecision":"day","type":"research-publication","verifiedOn":"2026-10-25","documentId":"https://www.anthropic.com/research/petri-open-source-auditing"}]}