{"schemaVersion":"nuwa-current-record-1","version":"2026-10-29.1","publication":"published","work":{"id":"auditing-games","title":"Auditing Games for Sandbagging","aliases":[],"authors":["Jordan Taylor","Sid Black","Dillon Bowen","Thomas Read","Satvik Golechha","Alex Zelenka-Martin","Oliver Makins","Connor Kissane","Kola Ayonrinde","Jacob Merizian","Samuel Marks","Chris Cundy","Joseph Bloom"],"primaryFunction":"evaluation","secondaryFunctions":[],"kind":"study","sourceId":"auditing-games-publication","attributionSourceId":"auditing-games-publication-author-source","originalUrl":"https://arxiv.org/abs/2512.07810","publicationDate":"2025-12-08","updatedOn":"2026-10-25","areas":["deception"],"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":[],"contributions":[{"organizationId":"aisi","role":"research","sourceId":"auditing-games-publication-author-source","locator":"Author affiliations on the original paper title page"},{"organizationId":"far","role":"research","sourceId":"auditing-games-publication-author-source","locator":"Author affiliations on the original paper title page"},{"organizationId":"anthropic","role":"research","sourceId":"auditing-games-publication-author-source","locator":"Author affiliations on the original paper title page"}],"summary":{"en":"Uses adversarial auditing games to test detection of deliberately trained capability concealment.","zh":"通过对抗审计博弈，测试对有意训练的能力隐藏行为的检测。"},"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":["risk-monitoring"]},"reading":{"id":"auditing-games","title":"Auditing Games for Sandbagging","en":{"question":"Can auditors distinguish trained sandbaggers from genuinely weaker models?","design":"A red team fine-tunes five model organisms; a blue team applies black-box, activation-probe and training-based detection under explicit game constraints.","findings":["Black-box approaches did not reliably discriminate sandbaggers.","One correct training demonstration could elicit full performance, but benign models also improved, creating false positives."],"interpretation":"NUWA interpretation: elicitation uplift alone is not diagnostic of intentional capability hiding.","limits":"Trained organisms are proxies, and detector robustness depends on the red-team construction and access regime.","decisionRelevance":"Model recommendation: include benign weak-model controls and adversarially constructed organisms when validating sandbagging detection.","takeaway":"NUWA interpretation: elicitation uplift alone is not diagnostic of intentional capability hiding.","connections":[],"scoring":null,"conditions":null,"statistics":null,"usage":"Model recommendation: include benign weak-model controls and adversarially constructed organisms when validating sandbagging detection."},"zh":{"question":"审计者能否区分训练出的能力隐藏模型与真实弱模型？","design":"红队微调五个模型样本，蓝队在明确游戏约束下使用黑盒、激活探针及训练检测。","findings":["黑盒方法不能可靠区分。","一条正确训练示例可激发完整能力，但良性模型也提高，造成误报。"],"interpretation":"NUWA 解读：激发后提升本身不能诊断故意隐藏能力。","limits":"训练样本仅为代理，稳健性依赖红队构造和访问权限。","decisionRelevance":"模型建议：验证检测器时加入真实弱模型对照与对抗构造样本。","takeaway":"NUWA 解读：激发后提升本身不能诊断故意隐藏能力。","connections":[],"scoring":null,"conditions":null,"statistics":null,"usage":"模型建议：验证检测器时加入真实弱模型对照与对抗构造样本。"},"assertionPolicy":{"question":"source-research-question","design":"source-finding","findings":"source-finding","interpretation":"nuwa-interpretation","limits":"source-limit-or-explicit-editorial-scope-limit","connections":"source-supported-relationship-only","decisionRelevance":"model-recommendation-not-source-conclusion"},"sourceRefs":[{"sourceId":"auditing-games-publication-author-source","url":"https://arxiv.org/html/2512.07810","locator":"Abstract","version":"Selected original resource https://arxiv.org/html/2512.07810; sha256:0c00d4cce9c41437666e2e086b86648e87bcb735c9624e4bc87c85eb9fc63470; archived source capture; exact capture time not independently established","artifactSha256":"0c00d4cce9c41437666e2e086b86648e87bcb735c9624e4bc87c85eb9fc63470"},{"sourceId":"auditing-games-publication-author-source","url":"https://arxiv.org/html/2512.07810","locator":"§3 Game Setup","version":"Selected original resource https://arxiv.org/html/2512.07810; sha256:0c00d4cce9c41437666e2e086b86648e87bcb735c9624e4bc87c85eb9fc63470; archived source capture; exact capture time not independently established","artifactSha256":"0c00d4cce9c41437666e2e086b86648e87bcb735c9624e4bc87c85eb9fc63470"},{"sourceId":"auditing-games-publication-author-source","url":"https://arxiv.org/html/2512.07810","locator":"§6 Blue Team – Detection Results","version":"Selected original resource https://arxiv.org/html/2512.07810; sha256:0c00d4cce9c41437666e2e086b86648e87bcb735c9624e4bc87c85eb9fc63470; archived source capture; exact capture time not independently established","artifactSha256":"0c00d4cce9c41437666e2e086b86648e87bcb735c9624e4bc87c85eb9fc63470"},{"sourceId":"auditing-games-publication-author-source","url":"https://arxiv.org/html/2512.07810","locator":"§7 Discussion","version":"Selected original resource https://arxiv.org/html/2512.07810; sha256:0c00d4cce9c41437666e2e086b86648e87bcb735c9624e4bc87c85eb9fc63470; archived source capture; exact capture time not independently established","artifactSha256":"0c00d4cce9c41437666e2e086b86648e87bcb735c9624e4bc87c85eb9fc63470"}],"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-source-sections; not a complete section-by-section paper audit","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"77c9d57ac6354896346eff2517b55eb551422974a7538b99e768f6e4688bbcf0"}},"sources":[{"id":"auditing-games-publication","title":"Auditing Games for Sandbagging","url":"https://arxiv.org/abs/2512.07810","version":"arXiv:2512.07810v1","publicationDate":"2025-12-08","datePrecision":"day","type":"paper","verifiedOn":"2026-10-25","documentId":"arxiv:2512.07810","authors":["Jordan Taylor","Sid Black Dillon Bowen Thomas Read Satvik Golechha","Alex Zelenka-Martin Oliver Makins Connor Kissane Kola Ayonrinde Jacob Merizian","Samuel Marks Chris Cundy Joseph Bloom"],"aliases":["https://doi.org/10.48550/arXiv.2512.07810","https://arxiv.org/abs/2512.07810","https://arxiv.org/pdf/2512.07810"]}]}