{
    "identifier": "ark:\/88434\/mds2-2895",
    "accessLevel": "public",
    "contactPoint": {
        "hasEmail": "mailto:[email protected]",
        "fn": "Gary Howarth II"
    },
    "programCode": [
        "006:045"
    ],
    "landingPage": "https:\/\/data.nist.gov\/od\/id\/mds2-2895",
    "title": "NIST Excerpts Benchmark Data",
    "description": "The NIST Excerpts Benchmark Data are a set of target data for deidentification algorithms. The data are configured to work with \"SDNist: Synthetic Data Report Tool\", a package for evaluating synthetic data generators: https:\/\/github.com\/usnistgov\/SDNist. An installation of SDNist will download the data resources automatically. \n\nJan 2025 -- Benhcmark Excerpts: \n- NIST American Community Survey (ACS) Data Excerpts, 24 demographic features over 40k records,\n- NIST Survey of Business Owners (SBO) Data Excerpts, 130 demographic and financial features over 161k records\n\nThe data are curated subsets of U.S. Census Bureau products.",
    "language": [
        "en"
    ],
    "distribution": [
        {
            "accessURL": "https:\/\/github.com\/usnistgov\/SDNist\/tree\/main\/BenchmarkData",
            "format": "A data respository",
            "description": "The NIST Data Excerpts are curated subsets of publicly released tabular data sets, drawn from real households and businesses in the U.S. The Excerpts serve as benchmark data for the [SDNist v2: Deidentified Data Report Tool](https:\/\/github.com\/usnistgov\/SDNist\/) .",
            "title": "NIST Excerpt Benchmark Data"
        }
    ],
    "bureauCode": [
        "006:55"
    ],
    "modified": "2025-01-31 00:00:00",
    "publisher": {
        "@type": "org:Organization",
        "name": "National Institute of Standards and Technology"
    },
    "theme": [
        "Information Technology:Privacy",
        "Information Technology:Data and informatics",
        "Information Technology:Software research"
    ],
    "keyword": [
        "privacy",
        "synthetic data",
        "demographic data",
        "American Community Survey",
        "SDNist"
    ]
}