{
  "schema": "cortist.claim_graph.v2",
  "asOf": "2026-11-05",
  "claim": {
    "id": "claim:CL-0014",
    "type": "LedgerClaim",
    "claimId": "CL-0014",
    "claim": "Do agents retain the reported teamwork weaknesses when the Collaborative Intelligence benchmark is reproduced independently?",
    "status": "240-task benchmark preprint; independent reproduction pending",
    "originalState": "documented",
    "sourceDate": "2026-11-02",
    "snapshotDate": "2026-11-05",
    "originalVersion": 1,
    "canonicalUrl": "https://cortist.com/reality-ledger/cl-0014/",
    "snapshotUrl": "https://cortist.com/data/reality-ledger/records/cl-0014-v1.json",
    "snapshotSha256": "01287a0beceec6e46a49dc1e8570122769e3b01698019701e3a3f9cb681cad93",
    "attribution": "Sean Wu and collaborating researchers",
    "topic": "AI Agents",
    "evidence": "The November 2 arXiv preprint introduces a Collaborative Intelligence Benchmark with 240 tasks spanning eight dimensions of teamwork, evaluating 18 model families. The authors report the best score as 82.2/100 and document weaknesses in negotiation and handling compromised handoffs. They describe 160 public tasks and 80 held-out tasks.",
    "limitations": "The preprint is authored evaluation, not a peer-reviewed, independent replication. The selected scenarios and programmatic grader are not equivalent to actual workplace performance or a population-wide safety rate. Held-out material is not fully open to third-party reproduction without suitable access.",
    "nextEvidence": "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.",
    "statusAsOf": "2026-11-05",
    "independentlyResolved": false,
    "kind": "independent_replication",
    "deadline": null,
    "verificationCriteria": [
      "Reproduce the reported scores on the published 160-task subset.",
      "Test robustness to agent and model updates using unchanged grading rules.",
      "Assess whether controlled teamwork scores predict outcomes in external multi-agent projects."
    ]
  },
  "edges": [
    {
      "id": "edge:claim:CL-0014:ATTRIBUTED_TO:actor:2732fc5b-37",
      "from": "claim:CL-0014",
      "relation": "ATTRIBUTED_TO",
      "to": "actor:2732fc5b-37"
    },
    {
      "id": "edge:claim:CL-0014:ORIGINAL_SOURCE:source:f2225b96-32",
      "from": "claim:CL-0014",
      "relation": "ORIGINAL_SOURCE",
      "to": "source:f2225b96-32"
    },
    {
      "id": "edge:claim:CL-0014:TOPIC:topic:ai-agents",
      "from": "claim:CL-0014",
      "relation": "TOPIC",
      "to": "topic:ai-agents"
    },
    {
      "id": "edge:claim:CL-0014:EDITORIAL_ANALYSIS:news:collaborative-intelligence-benchmark-ai-agent-teamwork-822-2026",
      "from": "claim:CL-0014",
      "relation": "EDITORIAL_ANALYSIS",
      "to": "news:collaborative-intelligence-benchmark-ai-agent-teamwork-822-2026"
    },
    {
      "id": "edge:claim:CL-0014:TIMELINE_EVENT:event:CL-0014:v1:01",
      "from": "claim:CL-0014",
      "relation": "TIMELINE_EVENT",
      "to": "event:CL-0014:v1:01"
    },
    {
      "id": "edge:claim:CL-0014:TIMELINE_EVENT:event:CL-0014:v1:02",
      "from": "claim:CL-0014",
      "relation": "TIMELINE_EVENT",
      "to": "event:CL-0014:v1:02"
    }
  ],
  "originalTimeline": [
    {
      "id": "event:CL-0014:v1:01",
      "claimId": "CL-0014",
      "originalText": "2026-11-02 | Benchmark preprint | Authors release 240-task/8-dimension research and report the strongest model score of 82.2.",
      "originalSnapshotUrl": "https://cortist.com/data/reality-ledger/records/cl-0014-v1.json",
      "kind": "NEW_20261105_BASELINE_EVENT",
      "newEvidence": false
    },
    {
      "id": "event:CL-0014:v1:02",
      "claimId": "CL-0014",
      "originalText": "2026-11-05 | Cortist baseline | External generalization and independently reproduced results remain to be demonstrated.",
      "originalSnapshotUrl": "https://cortist.com/data/reality-ledger/records/cl-0014-v1.json",
      "kind": "NEW_20261105_BASELINE_EVENT",
      "newEvidence": false
    }
  ],
  "sources": [
    {
      "name": "arXiv: Measuring AI Agents as Teammates with Collaborative Intelligence",
      "url": "https://arxiv.org/abs/2611.02633",
      "published": "2026-11-02"
    }
  ],
  "originalCase": "https://cortist.com/reality-ledger/cl-0014/",
  "originalSnapshot": "https://cortist.com/data/reality-ledger/records/cl-0014-v1.json",
  "snapshotSha256": "01287a0beceec6e46a49dc1e8570122769e3b01698019701e3a3f9cb681cad93"
}