{"schemaVersion":"nuwa-reading-1","snapshotId":"2026-10-29.1","generatedOn":"2026-10-28","qualityRule":"Availability and section disposition do not establish evidence verification, editorial approval or experimental replication.","works":[{"id":"published-note","sourceId":"agentcyberrange","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"asimov","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"cybench","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-08-15","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"cybergym","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-06-03","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"in-context-scheming","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-12-06","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"aisi-cyber-range","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-03-16","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"time-horizons","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-08","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"re-bench","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-11-22","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"replibench","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-04-21","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"self-replication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-12-09","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"truthful-sad","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-07-15","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"stealth-evals","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-05-02","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"wmdp","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-03-05","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"opendeception","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-04-18","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"aisi-propensity","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-04-24","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"palisade-shutdown","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-07-05","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"agentdojo","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-11-24","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"agentharm","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-10-11","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"harmbench","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-02-06","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"anthropic-unintended","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-09","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"palisade-robot-shutdown","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-02-12","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"strongreject","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-02-15","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"secbench-pro","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-26","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"sandboxescapebench","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-03-23","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"paperbench","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-04-02","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"alignment-faking","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-12-18","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"agentic-misalignment","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-06-20","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"shade-arena","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-06-16","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"vct","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-04-21","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"vct-v2","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-11","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"biotier","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-07-16","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"mask","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-03-05","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"ape","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-06-03","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"conspiracy-persuasion","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-01-08","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"sec-bench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-06-13","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"exploitbench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-13","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"exploitgym-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-13","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"cve-bench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-03-21","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"sre-bench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-08-11","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"irregular-opus-cyber-assessment-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-22","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"irregular-astra-cyber-assessment-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-03","sourceLocations":["Original Irregular article (3 September 2026), Testing Configuration; Key Outcomes; FrontierCyber Case Studies; CyScenarioBench and Atomic Challenges; Overall Assessment"]},{"id":"published-note","sourceId":"solve-plus-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-03","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"cyberseceval-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"cybersoceval-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"caisi-glm-cyber-assessment-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-17","sourceLocations":["Original NIST/CAISI article (17 September 2026), Methodological Notes; Tables 1–2; Figure 1 index definition"]},{"id":"published-note","sourceId":"hcast-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-03-21","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"mirrorcode-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-04-10","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"expenditure-horizon-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-07-21","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"mle-bench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-10-09","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"posttrainbench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-03-09","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"deepmind-dangerous-capabilities-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-03-20","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"self-replication-extended-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-03-14","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"palisade-network-replication-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-07","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"agentic-self-modification-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-16","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"machiavelli-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2023-04-06","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"emergent-misalignment-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":true,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-02-25","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"school-of-reward-hacks-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-08-25","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"conditional-misalignment-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-04-28","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"reward-hacking-emergent-misalignment-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-11-21","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"contrastive-reward-seeking-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-07-21","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"sabotage-safety-research-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-04-27","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"ai-sandbagging-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-06-11","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"sleeper-agents-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-01-14","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"subliminal-learning-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-07-20","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"ai-control-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":true,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2023-12-12","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"ctrl-z-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":true,"review":"verified"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-04-14","sourceLocations":["arXiv:2504.10374v1, §§2, 3.2–3.4, 4–6; Appendix C"]},{"id":"published-note","sourceId":"basharena-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":true,"review":"verified"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-17","sourceLocations":["arXiv:2512.15688v1, §§2, 3.2, 4.1–4.4, 5–6"]},{"id":"published-note","sourceId":"multi-agent-control-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-07-08","sourceLocations":["arXiv:2607.07368v2 (12 October 2026), §§2.1–2.6, 3.1–3.4, 4; Appendix C.4.2–C.4.3"]},{"id":"published-note","sourceId":"anti-scheming-training-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-09-17","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"malt-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-10-14","sourceLocations":["Original METR article (14 October 2025), Dataset details; Dataset collection; Monitoring Setup and Results; Limitations"]},{"id":"published-note","sourceId":"metr-monitorability-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-01-22","sourceLocations":["Original METR article (page date 22 January 2026), Methodology; Results; Transcript analysis; Limitations and Future Work; Errata"]},{"id":"published-note","sourceId":"auditing-games-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-08","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"belief-verified-lie-detectors-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-06-17","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"obfuscation-atlas-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-02-16","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"tamperbench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-02-06","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"automated-alignment-mitigation-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-08-28","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"training-run-evaluations-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-07-05","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"cot-faithfulness-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-04-03","sourceLocations":["Original Anthropic article, Testing for faithfulness; Can we improve faithfulness?; Faithfulness and reward hacking; Conclusions"]},{"id":"published-note","sourceId":"cot-misbehavior-monitoring-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-03-14","sourceLocations":["arXiv:2503.11926v1, §§2.1–2.2, 3.1–3.3, 5.1–5.2, 6"]},{"id":"published-note","sourceId":"injecagent-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-03-05","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"agent-safetybench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-12-19","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"petri-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-10-06","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"bloom-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-19","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"truthfulqa-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2021-09-08","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"value-leakage-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-07-15","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"agent-security-red-teaming-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-03-23","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"labbench-two-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-02-04","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"fortress-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-06-17","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"rand-biological-benchmarking-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-11-25","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"rand-biological-risk-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-31","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"conventional-weapons-evaluations-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-10","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"fortress-audit-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"cheating-agent-evaluations-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-02","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"item-response-safety-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-08-05","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"optstop-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-08-14","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"metr-frontier-risk-report-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-19","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"hugging-face-incident-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":true,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-08-26","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"anthropic-cyber-incidents-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-09","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"anthropic-threat-report-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"saferai-glm-risk-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-08-02","sourceLocations":["Original SaferAI report page (2 August 2026), Executive Summary; Cyber Offense (Figures 1–3); Loss of Control (Figures 6–7); Harmful Manipulation (Figures 8–9); Conclusion; Limitations and Future Work"]},{"id":"published-note","sourceId":"bountybench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-05-21","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"deep-ignorance-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":true,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-08-08","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"monitoring-monitorability-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"limited"},{"id":"method","available":true,"review":"limited"},{"id":"finding","available":true,"review":"limited"},{"id":"supports","available":true,"review":"limited"},{"id":"limits","available":true,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-20","sourceLocations":["Retained existing source-specific note sections; this pass audits duplicate/boilerplate structure and source availability, not complete section-level verification."]},{"id":"published-note","sourceId":"monitorability-opportunity-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-07-15","sourceLocations":["arXiv:2507.11473v2, §§1.1–1.2, 2–5"]},{"id":"published-note","sourceId":"monitorbench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-03-30","sourceLocations":["arXiv:2603.28590v2, §§3.1–3.3, 4.1–4.3; Appendix A.3–A.4"]},{"id":"published-note","sourceId":"catastrophic-cyber-benchmark-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-10-10","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"instrumentaleval-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-02-16","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"mcptox-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-08-19","sourceLocations":["arXiv:2508.14925v2, §§3.2–3.4, 4, 5"]},{"id":"published-note","sourceId":"judgebench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-10-16","sourceLocations":["arXiv:2410.12784v2, §§3, 4.1–4.4; Appendix A.3–A.5"]},{"id":"published-note","sourceId":"narcbench-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-04-01","sourceLocations":["arXiv:2604.01151v2, §§3.1–3.4, 4.1–4.6; Appendices F.7, G.9, H.8"]},{"id":"published-note","sourceId":"transect-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-07","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"extreme-risk-evaluations-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2023-05-24","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"monitorability-metrics-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-20","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"prefill-awareness-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-06-10","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"consistency-misalignment-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-06-02","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"loss-of-oversight-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-21","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"steganography-monitoring-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-04-29","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"log-analysis-pipeline-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-02-25","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"control-monitoring-deployment-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-15","sourceLocations":["arXiv:2512.22154v1, §§2–3, 4–5, 6.1–6.2; Appendix E"]},{"id":"published-note","sourceId":"async-control-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"verified"},{"id":"method","available":true,"review":"verified"},{"id":"finding","available":true,"review":"verified"},{"id":"supports","available":true,"review":"verified"},{"id":"limits","available":true,"review":"verified"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-15","sourceLocations":["arXiv:2512.13526v1, §§1–3, red-team/blue-team rounds and deployment simulations; limitations in Introduction"]},{"id":"published-note","sourceId":"self-evaluation-wireheading-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-01","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"open-weight-risk-management-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-10-26","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"pretraining-poisoning-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-10-08","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"inoculation-prompting-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-10-05","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"misuse-safety-case-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-06-05","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"unlearning-evaluation-validity-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-05-31","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"safety-cases-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-02-10","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"misuse-safeguard-principles-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-02-04","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"control-safety-case-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-01-28","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"embedded-evaluators-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-29","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"specification-gaming-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-02-19","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"llm-honeypot-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-10-17","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"beyond-owls-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-07","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"activation-oracles-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-19","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"rogue-replication-threat-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-11-12","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"capability-elicitation-publication","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"limited"},{"id":"method","available":false,"review":"limited"},{"id":"finding","available":false,"review":"limited"},{"id":"supports","available":false,"review":"limited"},{"id":"limits","available":false,"review":"limited"},{"id":"connections","available":false,"review":"limited"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-03-15","sourceLocations":["No complete section-level method/results/limitations review completed for this note; cached original page and any chart audit retained as discovery evidence."]},{"id":"published-note","sourceId":"abstentionbench-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-06-10","sourceLocations":[]},{"id":"published-note","sourceId":"deceptionbench-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-10-17","sourceLocations":[]},{"id":"published-note","sourceId":"persusafety-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-04-14","sourceLocations":[]},{"id":"published-note","sourceId":"impossiblebench-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-10-23","sourceLocations":[]},{"id":"published-note","sourceId":"evalawarebench-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"theagentcompany-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-12-18","sourceLocations":[]},{"id":"published-note","sourceId":"lab-bench-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-07-14","sourceLocations":[]},{"id":"published-note","sourceId":"charxiv-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"biomysterybench-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"evmbench-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"swe-bench-pro-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"ctf-archive-diamond-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-01","sourceLocations":[]},{"id":"published-note","sourceId":"portbench-primary","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-01","sourceLocations":[]},{"id":"published-note","sourceId":"neo-kimi-k3-source","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-11","sourceLocations":[]},{"id":"published-note","sourceId":"neo-deepseek-v4-source","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-29","sourceLocations":[]},{"id":"published-note","sourceId":"neo-glm52-source","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-07-03","sourceLocations":[]},{"id":"published-note","sourceId":"caisi-deepseek-2025-source","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-09-30","sourceLocations":[]},{"id":"published-note","sourceId":"caisi-deepseek-v4-source","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-01","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-monitor-redteam","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-22","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-aisi-cyber-incident","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-self-assessment","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-16","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-traceprobe","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-safety-benchmark-review","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-expert-persuasion","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-06-15","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-warmth-sycophancy","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-04-29","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-roboharm","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-03","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-oopsieverse","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-06-30","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-foresight-vla","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-aisi-trends","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-long-form-tasks","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-horizon-assumptions","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-03-20","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-horizon-limits","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-01-22","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-hibayes","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-reprobait","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-14","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-protein-filtering","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-19","sourceLocations":[]},{"id":"published-note","sourceId":"dr-20261028-risk-open-problems","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":false,"review":"not-recorded"},{"id":"method","available":false,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":false,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":[]},{"id":"published-note","sourceId":"anthropic-sabotage-evaluations","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-10-18","sourceLocations":["Human decision sabotage; Code sabotage; Sandbagging; Undermining oversight"]},{"id":"published-note","sourceId":"openai-internal-monitoring","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-03-19","sourceLocations":["Our approach & how it works; Category overview; Limitations"]},{"id":"published-note","sourceId":"openai-anthropic-cross-evaluation","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-08-27","sourceLocations":["What we did (renderedL107–113); Summary of our findings (renderedL116–122;grader caveatL119)"]},{"id":"published-note","sourceId":"anthropic-pilot-risk-report","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-10-28","sourceLocations":["Primary takeaways; Internal and independent review links"]},{"id":"published-note","sourceId":"anthropic-taste","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-08-28","sourceLocations":["Building a Research Judgment Benchmark (TASTE); Evaluating Models’ Research Judgment"]},{"id":"published-note","sourceId":"anthropic-modular-pretraining","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-07-08","sourceLocations":["Introduction; Modularization Works Across Scales"]},{"id":"published-note","sourceId":"deepmind-gram","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-28","sourceLocations":["Abstract; Authors"]},{"id":"published-note","sourceId":"deepmind-fsf","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-09-22","sourceLocations":["Key updates to the Framework; FSF 3.1: Introducing tracked capability levels"]},{"id":"published-note","sourceId":"openai-confessions","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-03","sourceLocations":["How confessions work; What we learned; Limitations"]},{"id":"published-note","sourceId":"openai-cot-control","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-03-05","sourceLocations":["What is CoT controllability; Limitations; Going forward"]},{"id":"published-note","sourceId":"openai-external-testing","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-11-19","sourceLocations":["Independent evaluations by external labs; Methodology review; What makes a third party assessment collaboration successful?"]},{"id":"published-note","sourceId":"apollo-precursor-validity","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-07-03","sourceLocations":["L14-L38; L98-L125"]},{"id":"published-note","sourceId":"redwood-linuxarena","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-04-20","sourceLocations":["L1-L36; L37-L57"]},{"id":"published-note","sourceId":"arc-whitebox","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-06-02","sourceLocations":["L9-L39"]},{"id":"published-note","sourceId":"metr-opus55","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-22","sourceLocations":["L68-L107"]},{"id":"published-note","sourceId":"metr-anthropic-review","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-20","sourceLocations":["L68-L79; L119-L146"]},{"id":"published-note","sourceId":"metr-coverup","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-06","sourceLocations":["L58-L95; L116-L119"]},{"id":"published-note","sourceId":"redwood-screwtape","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-16","sourceLocations":["L1-L16; L47-L51"]},{"id":"published-note","sourceId":"redwood-resampling","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":["L27-L42; L54-L81"]},{"id":"published-note","sourceId":"redwood-simulated","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-24","sourceLocations":["L1-L27; L80-L103; L119-L135"]},{"id":"published-note","sourceId":"redwood-monitorability","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-09-23","sourceLocations":["article byline; L53-L65; L245-L260"]},{"id":"published-note","sourceId":"apollo-reward-seeking","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-07-21","sourceLocations":["L19"]},{"id":"published-note","sourceId":"apollo-embedded","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-01","sourceLocations":["L17-L29; L45-L55; L119-L137"]},{"id":"published-note","sourceId":"redwood-logit-rocs","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":null,"sourceLocations":["L1-L63; L232-L244"]},{"id":"published-note","sourceId":"palisade-elicitation","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-05-26","sourceLocations":["L1-L3"]},{"id":"published-note","sourceId":"redwood-basharena","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-12-18","sourceLocations":["L1-L48; L71-L129"]},{"id":"published-note","sourceId":"asb","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-10-03","sourceLocations":["#S3; #S5; #S6"]},{"id":"published-note","sourceId":"safeagentbench","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-12-17","sourceLocations":["#S3; #S4; #S5"]},{"id":"published-note","sourceId":"tool-emu","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2023-09-25","sourceLocations":["#S3; #S4; #S6"]},{"id":"published-note","sourceId":"agents-that-matter","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-07-01","sourceLocations":["#S2; #S3; #S4; #S5; #S6; #S7"]},{"id":"published-note","sourceId":"construct-validity","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-11-03","sourceLocations":["#S1; #S2; #S3; #S4"]},{"id":"published-note","sourceId":"item-level-data","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-02-27","sourceLocations":["#S3; #S4; #S5; #S7"]},{"id":"published-note","sourceId":"tensor-trust","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2023-11-02","sourceLocations":["#S3; #S5; #S6; #S8"]},{"id":"published-note","sourceId":"agentvigil","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-05-09","sourceLocations":["#S3; #S5; #S6"]},{"id":"published-note","sourceId":"redcode","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-11-12","sourceLocations":["#S3; #S4; #S5"]},{"id":"published-note","sourceId":"agentpoison","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-07-17","sourceLocations":["#S3; #S4; #S5"]},{"id":"published-note","sourceId":"measurement-to-meaning","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2025-05-13","sourceLocations":["#S2; #S3; #S4"]},{"id":"published-note","sourceId":"attack-reuse","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-10-27","sourceLocations":["#S3; #S4; #S5; #S6"]},{"id":"published-note","sourceId":"evalci","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-07-05","sourceLocations":["#S3; #S4; #S5; #S6"]},{"id":"published-note","sourceId":"resolution-diagnostics","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2026-05-28","sourceLocations":["#S3; #S6; #S7"]},{"id":"published-note","sourceId":"toolsword","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-02-16","sourceLocations":["#S2; #S3; #S4; #Sx1"]},{"id":"published-note","sourceId":"r-judge","label":{"en":"NUWA research note · independent review pending","zh":"NUWA 研究解读 · 独立复核待完成"},"hasSubstantiveContent":true,"sections":[{"id":"question","available":true,"review":"not-recorded"},{"id":"method","available":true,"review":"not-recorded"},{"id":"finding","available":false,"review":"not-recorded"},{"id":"supports","available":false,"review":"not-recorded"},{"id":"limits","available":true,"review":"not-recorded"},{"id":"connections","available":false,"review":"not-recorded"}],"baselineComplete":false,"reviewPending":false,"sourceReview":"existing-catalogue-scope","publicationState":"published","editorialApproval":"pending-human-review","publication":"2024-01-18","sourceLocations":["#S3; #S4; #Sx1"]}],"protocols":[{"id":"agentcyberrange","sourceId":"agentcyberrange","version":"Website bundle routes-B-0Mubrq.js / 2026-10-24 capture","review":"measurement-profile","structuredResults":33,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"asimov","sourceId":"asimov","version":"ASIMOV v2 / arXiv:2509.21651","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"cybench","sourceId":"cybench","version":"arXiv:2408.08926v4","review":"measurement-profile","structuredResults":41,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"cybergym","sourceId":"cybergym","version":"arXiv:2506.02548v3","review":"measurement-profile","structuredResults":108,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"in-context-scheming","sourceId":"in-context-scheming","version":"arXiv:2412.04984v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"aisi-cyber-scenarios","sourceId":"aisi-cyber-range","version":"Research page checked 2026-10-25","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"time-horizons","sourceId":"time-horizons","version":"Time Horizon 1.1; page updated 2026-09-08","review":"measurement-profile","structuredResults":26,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"re-bench","sourceId":"re-bench","version":"arXiv:2411.15114v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"replibench","sourceId":"replibench","version":"arXiv:2504.18565v2","review":"measurement-profile","structuredResults":5,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"self-replication","sourceId":"self-replication","version":"arXiv:2412.12140v1","review":"measurement-profile","structuredResults":2,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"truthful-sad","sourceId":"truthful-sad","version":"2024-07-15 article; original paper linked","review":"measurement-profile","structuredResults":30,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"stealth-evals","sourceId":"stealth-evals","version":"arXiv:2505.01420v4","review":"measurement-profile","structuredResults":37,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"wmdp","sourceId":"wmdp","version":"arXiv:2403.03218v7","review":"measurement-profile","structuredResults":14,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"opendeception","sourceId":"opendeception","version":"arXiv:2504.13707v3","review":"measurement-profile","structuredResults":11,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"aisi-propensity-study","sourceId":"aisi-propensity","version":"Research page checked 2026-10-25","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"palisade-shutdown","sourceId":"palisade-shutdown","version":"2025-07-05 article; later TMLR version separate","review":"measurement-profile","structuredResults":29,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"agentdojo","sourceId":"agentdojo","version":"arXiv:2406.13352v3","review":"measurement-profile","structuredResults":19,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"agentharm","sourceId":"agentharm","version":"arXiv:2410.09024v3","review":"measurement-profile","structuredResults":3,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"harmbench","sourceId":"harmbench","version":"arXiv:2402.04249v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"anthropic-unintended-actions","sourceId":"anthropic-unintended","version":"2026-10-09 article","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"palisade-robot-shutdown","sourceId":"palisade-robot-shutdown","version":"2026-02-12 technical report","review":"measurement-profile","structuredResults":2,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"strongreject","sourceId":"strongreject","version":"arXiv:2402.10260v2","review":"measurement-profile","structuredResults":16,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"secbench-pro","sourceId":"secbench-pro","version":"arXiv:2605.26548v2","review":"measurement-profile","structuredResults":48,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"sandboxescapebench","sourceId":"sandboxescapebench","version":"AISI research page checked 2026-10-25","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"paperbench","sourceId":"paperbench","version":"arXiv:2504.01848v3","review":"measurement-profile","structuredResults":6,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"alignment-faking","sourceId":"alignment-faking","version":"Anthropic research article 2024-12-18","review":"measurement-profile","structuredResults":27,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"agentic-misalignment","sourceId":"agentic-misalignment","version":"Anthropic research article 2025-06-20","review":"measurement-profile","structuredResults":176,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"shade-arena","sourceId":"shade-arena","version":"Anthropic research article 2025-06-16","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"vct","sourceId":"vct","version":"arXiv:2504.16137v2","review":"measurement-profile","structuredResults":12,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"vct-v2","sourceId":"vct-v2","version":"SecureBio release 2026-09-11","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"biotier","sourceId":"biotier","version":"arXiv:2607.14479v1","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"mask","sourceId":"mask","version":"arXiv:2503.03750v3","review":"measurement-profile","structuredResults":106,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"ape","sourceId":"ape","version":"arXiv:2506.02873v4","review":"measurement-profile","structuredResults":63,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"conspiracy-persuasion","sourceId":"conspiracy-persuasion","version":"FAR.AI report 2026-01-08","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"sec-bench","sourceId":"sec-bench-publication","version":"arXiv:2506.11791v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"exploitbench","sourceId":"exploitbench-publication","version":"arXiv:2605.14153v1","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"exploitgym","sourceId":"exploitgym-publication","version":"Source capture 2026-10-25","review":"measurement-profile","structuredResults":21,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"cve-bench","sourceId":"cve-bench-publication","version":"arXiv:2503.17332v4","review":"measurement-profile","structuredResults":6,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"sre-bench","sourceId":"sre-bench-publication","version":"arXiv:2608.11469v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"cyberseceval","sourceId":"cyberseceval-publication","version":"Source capture 2026-10-25","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"cybersoceval","sourceId":"cybersoceval-publication","version":"arXiv:2509.20166v1","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"hcast","sourceId":"hcast-publication","version":"arXiv:2503.17354v1","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"mirrorcode","sourceId":"mirrorcode-publication","version":"Source capture 2026-10-25","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"mle-bench","sourceId":"mle-bench-publication","version":"arXiv:2410.07095v6","review":"measurement-profile","structuredResults":6,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"posttrainbench","sourceId":"posttrainbench-publication","version":"arXiv:2603.08640v2","review":"measurement-profile","structuredResults":25,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"machiavelli","sourceId":"machiavelli-publication","version":"arXiv:2304.03279v4","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"tamperbench","sourceId":"tamperbench-publication","version":"arXiv:2602.06911v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"injecagent","sourceId":"injecagent-publication","version":"arXiv:2403.02691v3","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"agent-safetybench","sourceId":"agent-safetybench-publication","version":"arXiv:2412.14470v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"truthfulqa","sourceId":"truthfulqa-publication","version":"Source capture 2026-10-25","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"labbench-two","sourceId":"labbench-two-publication","version":"arXiv:2604.09554v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"fortress","sourceId":"fortress-publication","version":"arXiv:2506.14922v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"bountybench","sourceId":"bountybench-publication","version":"arXiv:2505.15216v3","review":"measurement-profile","structuredResults":10,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"basharena","sourceId":"basharena-publication","version":"arXiv:2512.15688v1","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"monitorbench","sourceId":"monitorbench-publication","version":"arXiv:2603.28590v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"catastrophic-cyber-benchmark","sourceId":"catastrophic-cyber-benchmark-publication","version":"arXiv:2410.09114v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"instrumentaleval","sourceId":"instrumentaleval-publication","version":"arXiv:2502.12206v1","review":"measurement-profile","structuredResults":8,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"mcptox","sourceId":"mcptox-publication","version":"arXiv:2508.14925v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"judgebench","sourceId":"judgebench-publication","version":"arXiv:2410.12784v2","review":"measurement-profile","structuredResults":15,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"narcbench","sourceId":"narcbench-publication","version":"arXiv:2604.01151v2","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"abstentionbench","sourceId":"abstentionbench-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"deceptionbench","sourceId":"deceptionbench-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":44,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"persusafety","sourceId":"persusafety-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":38,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"impossiblebench","sourceId":"impossiblebench-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":4,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"evalawarebench","sourceId":"evalawarebench-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":13,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"theagentcompany","sourceId":"theagentcompany-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"lab-bench","sourceId":"lab-bench-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":4,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"charxiv","sourceId":"charxiv-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":12,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"petri","sourceId":"petri-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":36,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"biomysterybench","sourceId":"biomysterybench-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"evmbench","sourceId":"evmbench-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":4,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"swe-bench-pro","sourceId":"swe-bench-pro-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"ctf-archive-diamond","sourceId":"ctf-archive-diamond-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":11,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"portbench","sourceId":"portbench-primary","version":"2026-10-25 source capture","review":"measurement-profile","structuredResults":4,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"traceprobe","sourceId":"dr-20261028-traceprobe","version":"Original resource captured 2026-10-28T07:24:41.534922+00:00; sha256:b0b85491f4be9fb842c2f97891b033a75b44a85c756b0f3b92cf8da775d8f828","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"roboharm","sourceId":"dr-20261028-roboharm","version":"Original resource captured 2026-10-28T07:24:43.704880+00:00; sha256:c5b843fd1a59541e7c7713423f4c765813de1b6dc8cb85bc7aa5913c0c945572","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"oopsieverse","sourceId":"dr-20261028-oopsieverse","version":"Original resource captured 2026-10-28T07:24:43.858466+00:00; sha256:e5c0c24c6eb494b5bef1612f1f6d5381aa9972a4aaa8937de7dcdb3e046a48d0","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"foresight-vla","sourceId":"dr-20261028-foresight-vla","version":"Original resource captured 2026-10-28T07:24:44.372873+00:00; sha256:303708eaa7bcf2e1d96cd551279703949de0dff652b1b5b86e0cd2dd5905329a","review":"measurement-profile","structuredResults":0,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"redwood-linuxarena","sourceId":"redwood-linuxarena","version":"0222314816805662a18563e24991608fb94644e3cd2919616b6c84d5f683b076","review":"measurement-profile","structuredResults":28,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"redwood-basharena","sourceId":"redwood-basharena","version":"4e1567de205bd18388f70b944799ff2fe3acbadc80321e73bf1b50200083f034","review":"measurement-profile","structuredResults":7,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"asb","sourceId":"asb","version":"85bab447cf5c3c692c7d3dae2785f0bcc6a9e4f8d8e15da9aac5cb6ec976054b","review":"measurement-profile","structuredResults":611,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"safeagentbench","sourceId":"safeagentbench","version":"fc3f276d7f8003ffcc110c585a40c0ef6f2b88207d4da50f060d4d4ee32b4031","review":"measurement-profile","structuredResults":540,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"tool-emu","sourceId":"tool-emu","version":"b939e7682699392e9c5a1328a3f23982af58b734e2f499ac00f0d315e757223b","review":"measurement-profile","structuredResults":21,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"tensor-trust","sourceId":"tensor-trust","version":"fb1e829e9a35db2f01567c1b0e3bfcdbb34ff68c7e005bab5c99097c99991c35","review":"measurement-profile","structuredResults":42,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]},{"id":"redcode","sourceId":"redcode","version":"7e4796140ad966c180057ec7fcc9440e099ad8d2b7e27ea54a7825cdc2fbc961","review":"measurement-profile","structuredResults":84,"missingReview":["construct-validity","scoring-audit","representative-case","independent-method-review"]}]}