{
  "schemaVersion": "2.0",
  "id": "CL-0014",
  "version": 1,
  "recordUrl": "https://cortist.com/reality-ledger/cl-0014/",
  "snapshotUrl": "https://cortist.com/data/reality-ledger/records/cl-0014-v1.json",
  "sourceDate": "2026-11-02",
  "snapshotDate": "2026-11-05",
  "topic": "AI Agents",
  "state": "documented",
  "status": "240-task benchmark preprint; independent reproduction pending",
  "organization": "Sean Wu and collaborating researchers",
  "claim": "Do agents retain the reported teamwork weaknesses when the Collaborative Intelligence benchmark is reproduced independently?",
  "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.",
  "sources": [
    {
      "name": "arXiv: Measuring AI Agents as Teammates with Collaborative Intelligence",
      "url": "https://arxiv.org/abs/2611.02633",
      "published": "2026-11-02"
    }
  ],
  "timeline": [
    "2026-11-02 | Benchmark preprint | Authors release 240-task/8-dimension research and report the strongest model score of 82.2.",
    "2026-11-05 | Cortist baseline | External generalization and independently reproduced results remain to be demonstrated."
  ],
  "newsUrl": "https://cortist.com/news/collaborative-intelligence-benchmark-ai-agent-teamwork-822-2026/",
  "topicUrl": "https://cortist.com/ai-agents/",
  "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."
  ],
  "sourceReviewNote": "Cortist read the cited original publication before opening the case; this is not independent replication or resolved-outcome verification",
  "independentlyResolved": false,
  "baselineStatusAsOf": "2026-11-05"
}