{
    "identifier": "ark:\/88434\/mds2-4158",
    "accessLevel": "public",
    "contactPoint": {
        "hasEmail": "mailto:[email protected]",
        "fn": "Michael Majurski"
    },
    "programCode": [
        "006:045"
    ],
    "landingPage": "https:\/\/data.nist.gov\/od\/id\/mds2-4158",
    "title": "Demo Codebase for agentic-research-measurement-probes",
    "description": "An agentic AI measurement tool for deep research over local corpora of PDF and Markdown documents. Given a research question, it orchestrates a programmatic AI pipeline to exhaustively evaluate, synthesize, and verify information from your documents, producing a Markdown report with inline footnote citations -- then automatically measures the quality of every citation using LM-judge measurement probes.\n\nThe probes are a first-class feature, not an afterthought. After each report section is written, three mutually exclusive probe evaluators run automatically, scoring every citation along distinct quality dimensions: faithfulness (does the source support the claim?), completeness (is the source's full message represented without cherry-picking?), and sufficiency (does the source carry the evidentiary burden the claim requires, or does the author overreach?). Probe results are stored alongside the report as a structured audit trail, enabling quantitative measurement of AI-generated research quality.",
    "language": [
        "en"
    ],
    "distribution": [
        {
            "accessURL": "https:\/\/github.com\/usnistgov\/agentic-research-measurement-probes",
            "description": "Github repository of the agentic-research-measurement-probes demo",
            "title": "agentic-research-measurement-probes Github Repository"
        }
    ],
    "bureauCode": [
        "006:55"
    ],
    "modified": "2026-03-26 00:00:00",
    "publisher": {
        "@type": "org:Organization",
        "name": "National Institute of Standards and Technology"
    },
    "theme": [
        "Information Technology:Software research"
    ],
    "keyword": [
        "Agentic-AI Measurement",
        "LLM",
        "Deep Research"
    ]
}