{
  "schemaVersion": "2.0",
  "asOf": "2026-11-05",
  "schedule": "Existing Cortist daily automation at 09:00 America/Los_Angeles; prioritized rotating source reviews; no new scheduler",
  "rules": {
    "sourceVerification": "Every status-changing update needs actual primary-source evidence and specific material delta",
    "appendOnly": true,
    "neverOverwriteV1": true,
    "neverFakeIndependentReplication": true,
    "keepEvidencePendingIfUncertain": true,
    "deduplicateSources": true,
    "saveDailyQA": true,
    "deepSourcesPerDay": 2,
    "maxDaysForRoutineRotation": 10,
    "priority": "Check due-soon public commitments first, then oldest actual source review; record blockers and defer safely",
    "neverTreatInitialReadingAsIndependentReplication": true
  },
  "records": [
    {
      "id": "CL-0001",
      "claim": "Were OpenAI's monitoring flaws independently re-tested after the reported fixes?",
      "sourceUrls": [
        "https://metr.org/blog/2026-10-22-red-teaming-openai-agent-monitoring/"
      ],
      "followUp": "Find direct independent claim-specific follow-up and verify publication date"
    },
    {
      "id": "CL-0002",
      "claim": "Do MAI-DxO's retrospective results establish benefits for real patients?",
      "sourceUrls": [
        "https://microsoft.ai/news/building-medical-superintelligence/",
        "https://doi.org/10.1126/science.aeh7930"
      ],
      "followUp": "Find direct independent claim-specific follow-up and verify publication date"
    },
    {
      "id": "CL-0003",
      "claim": "When can customers independently test Google Agent Compute Engine?",
      "sourceUrls": [
        "https://cloud.google.com/blog/topics/ai-infrastructure/introducing-agent-compute-engine-and-expanded-agent-governance"
      ],
      "followUp": "Find direct independent claim-specific follow-up and verify publication date"
    },
    {
      "id": "CL-0004",
      "claim": "What did AISI's Mythos 5 incident investigation establish?",
      "sourceUrls": [
        "https://www.aisi.gov.uk/blog/investigating-alignment-failures-in-aisis-incident",
        "https://www.anthropic.com/research/alignment-assessment-ukaisi"
      ],
      "followUp": "Find direct independent claim-specific follow-up and verify publication date"
    },
    {
      "id": "CL-0005",
      "claim": "What does the 3.7% decline in AI-exposed young-worker jobs prove?",
      "sourceUrls": [
        "https://www.adpresearch.com/research/canaries-dashboard-employment-in-ai-exposed-occupations-shrank-in-september"
      ],
      "followUp": "Find direct independent claim-specific follow-up and verify publication date"
    },
    {
      "id": "CL-0006",
      "claim": "Do Anthropic's junior hiring changes prove AI agents displaced workers?",
      "sourceUrls": [
        "https://www.anthropic.com/research/employment-at-anthropic"
      ],
      "followUp": "Find direct independent claim-specific follow-up and verify publication date"
    },
    {
      "id": "CL-0007",
      "claim": "Will NVIDIA Vera's agent-sandbox throughput advantage hold for customers?",
      "sourceUrls": [
        "https://modal.com/blog/nvidia-vera-sandboxes"
      ],
      "followUp": "Find direct independent claim-specific follow-up and verify publication date"
    },
    {
      "id": "CL-0008",
      "claim": "Have OpenAI's updated frontier-training containment controls passed independent review?",
      "sourceUrls": [
        "https://openai.com/index/securing-our-frontier-model-training-environment/"
      ],
      "followUp": "Find direct independent claim-specific follow-up and verify publication date"
    },
    {
      "id": "CL-0009",
      "claim": "Do 134 IEA data-centre grid policies show that the measures work?",
      "sourceUrls": [
        "https://www.iea.org/reports/powering-artificial-intelligence/executive-summary"
      ],
      "followUp": "Find direct independent claim-specific follow-up and verify publication date"
    },
    {
      "id": "CL-0010",
      "claim": "Will METR publish independent safety evaluations after gaining access to Anthropic?",
      "sourceUrls": [
        "https://www.anthropic.com/news/an-update-on-independent-evaluators"
      ],
      "followUp": "Find direct independent claim-specific follow-up and verify publication date"
    },
    {
      "id": "CL-0011",
      "claim": "How many of OpenAI's 948 reported Linux root-exploit findings lead to independently verified and deployed fixes?",
      "sourceUrls": [
        "https://openai.com/index/a-thousand-fewer-paths-to-root/"
      ],
      "followUp": "Dated, deduplicated references to upstream Linux commits, advisories, maintainer acknowledgments, downstream distribution releases and independent reproduction of a disclosed sample; track accepted versus still pending fixes.",
      "kind": "research_replication",
      "deadline": null,
      "priority": "due-date-driven-or-oldest-source-first",
      "initialSourceReviewedOn": "2026-11-05",
      "doNotCountAsScheduledDeepReview": true
    },
    {
      "id": "CL-0012",
      "claim": "Will the open structRFM RNA model's reported structure-prediction gains replicate on independent RNA targets?",
      "sourceUrls": [
        "https://www.nature.com/articles/s41586-026-11210-2",
        "https://github.com/heqin-zhu/structRFM"
      ],
      "followUp": "Independent reproduction with pinned model checkpoints, archived evaluation scripts, new RNA families and leakage controls; separately measure lab-validated structure/function discoveries.",
      "kind": "independent_replication",
      "deadline": null,
      "priority": "due-date-driven-or-oldest-source-first",
      "initialSourceReviewedOn": "2026-11-05",
      "doNotCountAsScheduledDeepReview": true
    },
    {
      "id": "CL-0013",
      "claim": "Will Lambda's proposed $33.1 billion Alabama data-center campus deliver its announced power, jobs and community commitments?",
      "sourceUrls": [
        "https://lambda.ai/blog/lambda-to-invest-33-billion-in-alabama-with-new-data-center"
      ],
      "followUp": "Regulatory rate/order approval, dated start-of-construction documentation, verified capital expenditure and grid connection, realized employment/payroll, water-meter data and distributions under the community-benefits agreement.",
      "kind": "delivery_commitment",
      "deadline": "2027-Q1 planned construction start; longer commitments through 2049",
      "priority": "due-date-driven-or-oldest-source-first",
      "initialSourceReviewedOn": "2026-11-05",
      "doNotCountAsScheduledDeepReview": true
    },
    {
      "id": "CL-0014",
      "claim": "Do agents retain the reported teamwork weaknesses when the Collaborative Intelligence benchmark is reproduced independently?",
      "sourceUrls": [
        "https://arxiv.org/abs/2611.02633"
      ],
      "followUp": "Independent model reruns with version-pinned tasks, public subset reproduction, held-out evaluation by an independent steward and evidence that task-level weaknesses predict real team behavior.",
      "kind": "independent_replication",
      "deadline": null,
      "priority": "due-date-driven-or-oldest-source-first",
      "initialSourceReviewedOn": "2026-11-05",
      "doNotCountAsScheduledDeepReview": true
    },
    {
      "id": "CL-0015",
      "claim": "Can short-context compaction match long-context agent accuracy with lower real-world serving costs?",
      "sourceUrls": [
        "https://arxiv.org/abs/2611.05306"
      ],
      "followUp": "Independent reruns reporting matched accuracy, latency, GPU utilization and actual cost per completed task across providers and context policies.",
      "kind": "independent_replication",
      "deadline": null,
      "priority": "due-date-driven-or-oldest-source-first",
      "initialSourceReviewedOn": "2026-11-05",
      "doNotCountAsScheduledDeepReview": true
    },
    {
      "id": "CL-0016",
      "claim": "Will Anthropic's Claude Frontier Academy actually train 10,000 deployed engineers by the end of 2027?",
      "sourceUrls": [
        "https://www.anthropic.com/news/claude-frontier-academy"
      ],
      "followUp": "A dated, independently auditable count of engineers who complete the program and qualify for the stated credentials by 31 December 2027, with separate financial accounting and retention/outcome measures.",
      "kind": "delivery_commitment",
      "deadline": "2027-12-31",
      "priority": "due-date-driven-or-oldest-source-first",
      "initialSourceReviewedOn": "2026-11-05",
      "doNotCountAsScheduledDeepReview": true
    },
    {
      "id": "CL-0017",
      "claim": "Will Anthropic publish its promised policy proposal for embedded independent AI evaluators by 15 December 2026?",
      "sourceUrls": [
        "https://www.anthropic.com/responsible-scaling-policy/roadmap"
      ],
      "followUp": "An archived, time-stamped Anthropic proposal published on or before 15 December 2026 covering evaluator access, funding and independence, with subsequent changes tracked rather than retroactively altering the original target.",
      "kind": "delivery_commitment",
      "deadline": "2026-12-15",
      "priority": "due-date-driven-or-oldest-source-first",
      "initialSourceReviewedOn": "2026-11-05",
      "doNotCountAsScheduledDeepReview": true
    },
    {
      "id": "CL-0018",
      "claim": "When will Google's Genie 4 move beyond trusted research testers to documented consumer and developer access?",
      "sourceUrls": [
        "https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/"
      ],
      "followUp": "Dated official availability notices, verifiable user access for the specified consumer/developer cohorts, public usage terms and independent evaluations of consistency and physical fidelity over extended sessions.",
      "kind": "delivery_commitment",
      "deadline": "No fixed public date announced",
      "priority": "due-date-driven-or-oldest-source-first",
      "initialSourceReviewedOn": "2026-11-05",
      "doNotCountAsScheduledDeepReview": true
    },
    {
      "id": "CL-0019",
      "claim": "Does OpenAI's reported 10.2–37.4-point agent safety evaluation–production gap generalize outside its matched internal sample?",
      "sourceUrls": [
        "https://alignment.openai.com/eval-production-behavior-gap"
      ],
      "followUp": "Independent matched evaluations with documented case selection, grading, baseline model versions and intervals; replication with third-party agent deployment data and explicit accounting for confounders.",
      "kind": "independent_replication",
      "deadline": null,
      "priority": "due-date-driven-or-oldest-source-first",
      "initialSourceReviewedOn": "2026-11-05",
      "doNotCountAsScheduledDeepReview": true
    },
    {
      "id": "CL-0020",
      "claim": "Will global data-center electricity demand approach the IEA's projected 950 TWh in 2030?",
      "sourceUrls": [
        "https://www.iea.org/reports/key-questions-on-energy-and-ai",
        "https://www.iea.org/reports/key-questions-on-energy-and-ai/executive-summary"
      ],
      "followUp": "IEA or other audited 2030 global electricity statistics under comparable data-center boundaries, plus documented corrections for changed definitions and independent data series.",
      "kind": "projection_tracking",
      "deadline": "2030",
      "priority": "due-date-driven-or-oldest-source-first",
      "initialSourceReviewedOn": "2026-11-05",
      "doNotCountAsScheduledDeepReview": true
    }
  ],
  "oldV1Archive": "/data/reality-ledger/archive/watchlist-v1-20261025.json",
  "newCaseBaselineIds": [
    "CL-0011",
    "CL-0012",
    "CL-0013",
    "CL-0014",
    "CL-0015",
    "CL-0016",
    "CL-0017",
    "CL-0018",
    "CL-0019",
    "CL-0020"
  ]
}