{"schemaVersion":"nuwa-record-evidence-1","batchId":"research-2026-10-28","baseSnapshotId":"2026-10-27.3","publication":"published","dossier":null,"update":{"id":"monitorbench","review":{"state":"published-note","sourceScope":"full-text","availableScope":null,"readingCoverage":"selected-original-sections","completePaperAudit":false,"independentEvidenceReview":"pending-human-review","bilingualEditorialReview":"pending-human-review","authorship":"model-assisted-research-note","preparedFingerprint":"6fc5f16bd1dc14b86813f87b1979bcf4fa6be7e803fd5ad90b274c8de46b39be"},"text":{"en":"Separate recognition on fixed traces from safety diagnosis during execution. Self-assessment recall depends on its teacher labels; TraceProbe replay localises recorded actions rather than rerunning the model in a counterfactual.","zh":"将固定轨迹上的监测识别与真实执行中的安全诊断分开。Self-assessment 的教师相对召回受标签参考限制；TraceProbe 的工具回放定位已有轨迹，并不是模型重新决策的反事实实验。"},"sourceRefs":[{"sourceId":"dr-20261028-self-assessment","url":"https://safeguards.anthropic.com/2026/self-assessment/","title":"Scaling Misuse Detection with Self-Assessment","locator":"Results; limitations; text lines 00008,00014,00060","version":"Original resource captured 2026-10-28T07:24:41.534870+00:00; sha256:03b9ece6dae1c006622bb47373fb914bec20cee054a452748f30573c63ff6110","artifactSha256":"03b9ece6dae1c006622bb47373fb914bec20cee054a452748f30573c63ff6110","textSha256":"dae7a057951783e9c5d28fa96611c0ffda40e4f16aaeecc69620656d4255c6d2","capturedAt":"2026-10-28T07:24:41.534870+00:00","resourceEdition":"Cunningham et al. Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks. arXiv:2601.04603, January 2026. https://arxiv.org/abs/2601.04603"},{"sourceId":"dr-20261028-traceprobe","url":"https://aclanthology.org/2026.emnlp-main.1233.pdf","title":"TraceProbe: An Execution-Based Benchmark for Diagnosing Safety Failures in LLM Agents","locator":"§3.6; §5–6; Tables 2,15,17; limitations; text lines 00483","version":"Original resource captured 2026-10-28T07:24:41.534922+00:00; sha256:b0b85491f4be9fb842c2f97891b033a75b44a85c756b0f3b92cf8da775d8f828","artifactSha256":"b0b85491f4be9fb842c2f97891b033a75b44a85c756b0f3b92cf8da775d8f828","textSha256":"e384b1448665f91ea0204f7c519dcc36f5932f05db24104a7346136b208df6a6","capturedAt":"2026-10-28T07:24:41.534922+00:00","resourceEdition":"trajectories.Preprint, arXiv:2602.02475."}],"relatedWorkIds":["self-assessment","traceprobe"],"publication":{"state":"published","publishedOn":"2026-10-29","authorizationReference":"user-authorized-global-index-publication-2026-10-29","reviewedCandidateId":"local-6efe31bc4a0c0f37"}}}