{
  "title": "National security public AI evaluation and approval evidence",
  "source_page": "https://fiund.com/industries/national-security-public-evaluation-evidence-data",
  "authorship": "Original fictional Fiund editorial exercise. No actual operating records or third-party source assets are included.",
  "example": {
    "title": "A public test report does not establish acceptance or deployment",
    "context": "A benign fictional office benchmark retrieves original form titles from a paper catalog. It uses no operational, security-sensitive or restricted material.",
    "records": [
      [
        "NE1",
        "Practice evaluation scope",
        "Test E1 covers title retrieval from ten original dummy documents in a detached fixture."
      ],
      [
        "NE2",
        "Public-style test report",
        "Records one E1 run with eight of ten exact title matches. Report says acceptance review pending."
      ],
      [
        "NE3",
        "Announcement draft",
        "Says the office is exploring evaluation. No acceptance decision, deployment authorization or operational-outcome record supplied."
      ]
    ],
    "question": "Which evaluation work and score are documented, and what evidence would be missing from a claim of accepted or deployed capability?",
    "answer": "NE1 and NE2 document one narrowly scoped E1 run with eight exact matches out of ten dummy-document questions. NE2 explicitly leaves acceptance pending, and NE3 adds no deployment or operational evidence. The supported statement is the reported test and its limited score, not accepted capability, authorized deployment or real-world effectiveness. Keep scope, measured result and approval stage separate with their sources cited.",
    "failureModes": [
      "Treating an exploratory announcement or test completion as acceptance.",
      "Generalizing a small fixture score to operational performance or deployment authority."
    ],
    "fields": [
      [
        "Benchmark scope and fixture",
        "Defines what was tested."
      ],
      [
        "Run result and scoring rule",
        "Makes the limited metric inspectable."
      ],
      [
        "Acceptance and deployment authority",
        "Preserves stages absent from the report."
      ]
    ],
    "holdout": "Add an acceptance decision limited to continued lab evaluation. Require the model to distinguish that authorization from operational deployment.",
    "boundary": "Use original benign examples only. Exclude classified, export-controlled, controlled unclassified and operational records; actual access and testing decisions stay with the agency."
  }
}