{
  "slug": "decision-ledger",
  "title": "Decision Ledger",
  "description": "The fully new skill passed one pair, then missed a weakly phrased proposal twice.",
  "status": "inconclusive",
  "status_label": "Inconclusive",
  "status_explanation": "Only one of three attempted pairs remained valid, so the acceptance gate rejected an efficacy claim.",
  "claim": "Proved the release pipeline can publish an honest miss from a brand-new skill.",
  "method": "Three attempted paired Harbor runs with a frozen verifier and invalid pairs excluded.",
  "model": "openai/gpt-5.6-sol",
  "package_hash": "2ba9d3b76b8ac66b57ff7bed01827c25d4298c1cdf21a65988590c967dbe301a",
  "stats": [
    {
      "value": "3",
      "label": "Attempted pairs"
    },
    {
      "value": "1",
      "label": "Valid pair"
    },
    {
      "value": "1/3",
      "label": "Treatment verifier passes"
    },
    {
      "value": "0/3",
      "label": "Baseline verifier passes"
    }
  ],
  "limitations": [
    "One representative task",
    "One model",
    "Only one valid pair after objective-gate failures"
  ]
}