{
  "schema": "cortist.evidence_graph.verification_matrix.v1",
  "version": "2026-11-05",
  "asOf": "2026-11-05",
  "dataType": "DATED_SOURCE_REVIEW_SNAPSHOT_NOT_LIVE_STATUS",
  "summary": {
    "totalOriginalClaims": 10,
    "reviewedInThisScheduledRun": 2,
    "notReviewedInThisScheduledRun": 8,
    "distinctOriginalSources": 12,
    "claimSourceCitations": 12,
    "materialPostBaselineChanges": 0,
    "officialForecastsScored": 0,
    "huggingFace": {
      "status": "BLOCKED",
      "recordsVerifiedInThisRun": 0,
      "lastSuccessfulVerification": "2026-11-02",
      "note": "Public access blocked; no mismatch established"
    }
  },
  "provenance": {
    "watchQAKey": "qa:cortist-evidence-watch:2026-11-05",
    "watchCheckedAtUTC": "2026-11-05T07:10Z",
    "HFQAKey": "qa:cortist-hf-sync:2026-11-05",
    "ledger": "https://cortist.com/data/reality-ledger/index.json",
    "changes": "https://cortist.com/data/reality-ledger/changes.json",
    "graph": "https://cortist.com/data/evidence-graph/v1/index.json",
    "nextRotation": [
      "CL-0003",
      "CL-0004"
    ],
    "rotationCursor": 2
  },
  "definitions": {
    "reviewed": "Actual source re-read recorded in this one scheduled run; not independent confirmation or case resolution",
    "notReviewed": "Not rechecked in this specific run; does not imply never reviewed",
    "originalStatus": "Historical snapshot dated 2026-10-25, never automatically overwritten",
    "outcome": "No new post-baseline material revision or claim verification established by this dataset"
  },
  "cases": [
    {
      "claimId": "CL-0001",
      "claim": "Were OpenAI's monitoring flaws independently re-tested after the reported fixes?",
      "organization": "OpenAI / METR / Redwood Research",
      "originalStatus": "Independent re-test pending",
      "originalStatusAsOf": "2026-10-25",
      "originalSnapshotSHA256": "4573be5683900c69eb2e5d157d45e38e3cdfbf2c5927675fe669a63b48113e01",
      "originalSnapshotURL": "https://cortist.com/data/reality-ledger/records/cl-0001-v1.json",
      "canonicalCaseURL": "https://cortist.com/reality-ledger/cl-0001/",
      "evidenceGraphURL": "https://cortist.com/evidence-graph/cl-0001/",
      "newsURL": "https://cortist.com/news/openai-metr-redwood-monitoring-flaws/",
      "originalSources": [
        {
          "name": "METR's October 22 primary assessment",
          "url": "https://metr.org/blog/2026-10-22-red-teaming-openai-agent-monitoring/"
        }
      ],
      "reviewedIn20261105ScheduledRun": true,
      "lastScheduledSourceReview": "2026-11-05",
      "sourceFinding": "NO_NEW_INDEPENDENT_RETEST",
      "sourceFindingDetail": "METR states subsequent company remediation claims were not evaluated",
      "nextEvidence": "A new independent test of the patched safeguards with a disclosed scope and methodology.",
      "postBaselineMaterialRevision": false,
      "verifiedOutcome": null
    },
    {
      "claimId": "CL-0002",
      "claim": "Do MAI-DxO's retrospective results establish benefits for real patients?",
      "organization": "Microsoft AI",
      "originalStatus": "Prospective evidence pending",
      "originalStatusAsOf": "2026-10-25",
      "originalSnapshotSHA256": "0ed706bd00a62620d3d8e74ba93a08d2a756081de9604794eaa340e2f1f82868",
      "originalSnapshotURL": "https://cortist.com/data/reality-ledger/records/cl-0002-v1.json",
      "canonicalCaseURL": "https://cortist.com/reality-ledger/cl-0002/",
      "evidenceGraphURL": "https://cortist.com/evidence-graph/cl-0002/",
      "newsURL": "https://cortist.com/news/microsoft-mai-dxo-sequential-diagnosis-science-2026/",
      "originalSources": [
        {
          "name": "Microsoft: Building Medical Superintelligence",
          "url": "https://microsoft.ai/news/building-medical-superintelligence/"
        },
        {
          "name": "Science research paper DOI",
          "url": "https://doi.org/10.1126/science.aeh7930"
        }
      ],
      "reviewedIn20261105ScheduledRun": true,
      "lastScheduledSourceReview": "2026-11-05",
      "sourceFinding": "PROSPECTIVE_OUTCOMES_NOT_ESTABLISHED",
      "sourceFindingDetail": "Microsoft describes prospective study as future work; retrospective benchmark not clinical outcomes",
      "nextEvidence": "Prospective clinical evaluations with independent review, diagnostic safety and patient outcomes.",
      "postBaselineMaterialRevision": false,
      "verifiedOutcome": null
    },
    {
      "claimId": "CL-0003",
      "claim": "When can customers independently test Google Agent Compute Engine?",
      "organization": "Google Cloud",
      "originalStatus": "Customer preview pending",
      "originalStatusAsOf": "2026-10-25",
      "originalSnapshotSHA256": "ac96e66881b37c650ce3b02815d22e6359c7e0d061e41863bd033a290765d9d0",
      "originalSnapshotURL": "https://cortist.com/data/reality-ledger/records/cl-0003-v1.json",
      "canonicalCaseURL": "https://cortist.com/reality-ledger/cl-0003/",
      "evidenceGraphURL": "https://cortist.com/evidence-graph/cl-0003/",
      "newsURL": "https://cortist.com/news/google-agent-compute-engine-ai-agent-sandboxes-2026/",
      "originalSources": [
        {
          "name": "Google Cloud: Agent Compute Engine announcement",
          "url": "https://cloud.google.com/blog/topics/ai-infrastructure/introducing-agent-compute-engine-and-expanded-agent-governance"
        }
      ],
      "reviewedIn20261105ScheduledRun": false,
      "lastScheduledSourceReview": null,
      "sourceFinding": "NOT_REVIEWED_IN_THIS_SCHEDULED_RUN",
      "sourceFindingDetail": null,
      "nextEvidence": "Public customer-preview documentation, supported regions and independently reproducible operational evaluations.",
      "postBaselineMaterialRevision": false,
      "verifiedOutcome": null
    },
    {
      "claimId": "CL-0004",
      "claim": "What did AISI's Mythos 5 incident investigation establish?",
      "organization": "UK AI Security Institute / Anthropic",
      "originalStatus": "Evaluation evidence published",
      "originalStatusAsOf": "2026-10-25",
      "originalSnapshotSHA256": "2f44cd6f0e2fe1456e0dd0536eee77be6ecd66605492524b748382fdfb408c11",
      "originalSnapshotURL": "https://cortist.com/data/reality-ledger/records/cl-0004-v1.json",
      "canonicalCaseURL": "https://cortist.com/reality-ledger/cl-0004/",
      "evidenceGraphURL": "https://cortist.com/evidence-graph/cl-0004/",
      "newsURL": "https://cortist.com/news/anthropic-mythos-5-aisi-alignment-failures-2026/",
      "originalSources": [
        {
          "name": "UK AISI investigation",
          "url": "https://www.aisi.gov.uk/blog/investigating-alignment-failures-in-aisis-incident"
        },
        {
          "name": "Anthropic follow-up",
          "url": "https://www.anthropic.com/research/alignment-assessment-ukaisi"
        }
      ],
      "reviewedIn20261105ScheduledRun": false,
      "lastScheduledSourceReview": null,
      "sourceFinding": "NOT_REVIEWED_IN_THIS_SCHEDULED_RUN",
      "sourceFindingDetail": null,
      "nextEvidence": "Replications, mitigation tests and broader external evaluations beyond the initial scenarios.",
      "postBaselineMaterialRevision": false,
      "verifiedOutcome": null
    },
    {
      "claimId": "CL-0005",
      "claim": "What does the 3.7% decline in AI-exposed young-worker jobs prove?",
      "organization": "ADP Research / Stanford",
      "originalStatus": "Payroll pattern documented",
      "originalStatusAsOf": "2026-10-25",
      "originalSnapshotSHA256": "0c744620eca44c1beaa58cfa8ae681c135bfa784c88f689f56e0d556ca1f32d5",
      "originalSnapshotURL": "https://cortist.com/data/reality-ledger/records/cl-0005-v1.json",
      "canonicalCaseURL": "https://cortist.com/reality-ledger/cl-0005/",
      "evidenceGraphURL": "https://cortist.com/evidence-graph/cl-0005/",
      "newsURL": "https://cortist.com/news/adp-ai-exposed-young-workers-september-2026/",
      "originalSources": [
        {
          "name": "ADP Research September 2026 payroll update",
          "url": "https://www.adpresearch.com/research/canaries-dashboard-employment-in-ai-exposed-occupations-shrank-in-september"
        }
      ],
      "reviewedIn20261105ScheduledRun": false,
      "lastScheduledSourceReview": null,
      "sourceFinding": "NOT_REVIEWED_IN_THIS_SCHEDULED_RUN",
      "sourceFindingDetail": null,
      "nextEvidence": "Later payroll releases and research separating AI adoption from other labor-market drivers.",
      "postBaselineMaterialRevision": false,
      "verifiedOutcome": null
    },
    {
      "claimId": "CL-0006",
      "claim": "Do Anthropic's junior hiring changes prove AI agents displaced workers?",
      "organization": "Anthropic",
      "originalStatus": "Company workforce research",
      "originalStatusAsOf": "2026-10-25",
      "originalSnapshotSHA256": "081fde83fb120db0fcc9505f791baf792648cfbb22ed90effea89b0f23c8e18b",
      "originalSnapshotURL": "https://cortist.com/data/reality-ledger/records/cl-0006-v1.json",
      "canonicalCaseURL": "https://cortist.com/reality-ledger/cl-0006/",
      "evidenceGraphURL": "https://cortist.com/evidence-graph/cl-0006/",
      "newsURL": "https://cortist.com/news/anthropic-junior-hiring-ai-agents-2026/",
      "originalSources": [
        {
          "name": "Anthropic workforce research",
          "url": "https://www.anthropic.com/research/employment-at-anthropic"
        }
      ],
      "reviewedIn20261105ScheduledRun": false,
      "lastScheduledSourceReview": null,
      "sourceFinding": "NOT_REVIEWED_IN_THIS_SCHEDULED_RUN",
      "sourceFindingDetail": null,
      "nextEvidence": "Independent cross-company data on absolute junior hiring, agent adoption and causality.",
      "postBaselineMaterialRevision": false,
      "verifiedOutcome": null
    },
    {
      "claimId": "CL-0007",
      "claim": "Will NVIDIA Vera's agent-sandbox throughput advantage hold for customers?",
      "organization": "Modal / NVIDIA",
      "originalStatus": "Rollout and replication pending",
      "originalStatusAsOf": "2026-10-25",
      "originalSnapshotSHA256": "bcaf8f4a45d2a3eff4b0f9bf0ad34c89820c17c5c4e10fa1c49e3b7229110b54",
      "originalSnapshotURL": "https://cortist.com/data/reality-ledger/records/cl-0007-v1.json",
      "canonicalCaseURL": "https://cortist.com/reality-ledger/cl-0007/",
      "evidenceGraphURL": "https://cortist.com/evidence-graph/cl-0007/",
      "newsURL": "https://cortist.com/news/nvidia-vera-modal-ai-agent-sandbox-benchmarks/",
      "originalSources": [
        {
          "name": "Modal NVIDIA Vera benchmarking",
          "url": "https://modal.com/blog/nvidia-vera-sandboxes"
        }
      ],
      "reviewedIn20261105ScheduledRun": false,
      "lastScheduledSourceReview": null,
      "sourceFinding": "NOT_REVIEWED_IN_THIS_SCHEDULED_RUN",
      "sourceFindingDetail": null,
      "nextEvidence": "General customer availability, third-party reproduction and realistic performance-per-cost data.",
      "postBaselineMaterialRevision": false,
      "verifiedOutcome": null
    },
    {
      "claimId": "CL-0008",
      "claim": "Have OpenAI's updated frontier-training containment controls passed independent review?",
      "organization": "OpenAI",
      "originalStatus": "External validation pending",
      "originalStatusAsOf": "2026-10-25",
      "originalSnapshotSHA256": "d8d97f82f596ea8915bd713348dd1c38896e75f61c107cb855eb340185e7d322",
      "originalSnapshotURL": "https://cortist.com/data/reality-ledger/records/cl-0008-v1.json",
      "canonicalCaseURL": "https://cortist.com/reality-ledger/cl-0008/",
      "evidenceGraphURL": "https://cortist.com/evidence-graph/cl-0008/",
      "newsURL": "https://cortist.com/news/openai-frontier-training-containment-security-2026/",
      "originalSources": [
        {
          "name": "OpenAI frontier training containment disclosure",
          "url": "https://openai.com/index/securing-our-frontier-model-training-environment/"
        }
      ],
      "reviewedIn20261105ScheduledRun": false,
      "lastScheduledSourceReview": null,
      "sourceFinding": "NOT_REVIEWED_IN_THIS_SCHEDULED_RUN",
      "sourceFindingDetail": null,
      "nextEvidence": "A new externally scoped containment re-test with methodology and evidence of actual controls.",
      "postBaselineMaterialRevision": false,
      "verifiedOutcome": null
    },
    {
      "claimId": "CL-0009",
      "claim": "Do 134 IEA data-centre grid policies show that the measures work?",
      "organization": "International Energy Agency",
      "originalStatus": "Policy inventory documented",
      "originalStatusAsOf": "2026-10-25",
      "originalSnapshotSHA256": "0ee568f900556714c2458e98b6255bc31514694e4f9d47c9b3a0523d5aea317a",
      "originalSnapshotURL": "https://cortist.com/data/reality-ledger/records/cl-0009-v1.json",
      "canonicalCaseURL": "https://cortist.com/reality-ledger/cl-0009/",
      "evidenceGraphURL": "https://cortist.com/evidence-graph/cl-0009/",
      "newsURL": "https://cortist.com/news/iea-data-centre-grid-policies-2026/",
      "originalSources": [
        {
          "name": "IEA Powering Artificial Intelligence executive summary",
          "url": "https://www.iea.org/reports/powering-artificial-intelligence/executive-summary"
        }
      ],
      "reviewedIn20261105ScheduledRun": false,
      "lastScheduledSourceReview": null,
      "sourceFinding": "NOT_REVIEWED_IN_THIS_SCHEDULED_RUN",
      "sourceFindingDetail": null,
      "nextEvidence": "Evidence on implementation, connection delays, grid capacity and cost allocation.",
      "postBaselineMaterialRevision": false,
      "verifiedOutcome": null
    },
    {
      "claimId": "CL-0010",
      "claim": "Will METR publish independent safety evaluations after gaining access to Anthropic?",
      "organization": "Anthropic / METR",
      "originalStatus": "Independent METR report pending",
      "originalStatusAsOf": "2026-10-25",
      "originalSnapshotSHA256": "52df29a18d2a52aa97542d28ce2a96edfedc42e201705eedd1431dd4bf420656",
      "originalSnapshotURL": "https://cortist.com/data/reality-ledger/records/cl-0010-v1.json",
      "canonicalCaseURL": "https://cortist.com/reality-ledger/cl-0010/",
      "evidenceGraphURL": "https://cortist.com/evidence-graph/cl-0010/",
      "newsURL": "https://cortist.com/news/anthropic-metr-independent-ai-evaluators/",
      "originalSources": [
        {
          "name": "Anthropic independent evaluators disclosure",
          "url": "https://www.anthropic.com/news/an-update-on-independent-evaluators"
        }
      ],
      "reviewedIn20261105ScheduledRun": false,
      "lastScheduledSourceReview": null,
      "sourceFinding": "NOT_REVIEWED_IN_THIS_SCHEDULED_RUN",
      "sourceFindingDetail": null,
      "nextEvidence": "Public METR analysis with disclosed test scope, evidence, access limits and independent conclusions.",
      "postBaselineMaterialRevision": false,
      "verifiedOutcome": null
    }
  ]
}