{
  "_schema": "https://data.nist.gov/od/dm/nerdm-schema/v0.7#",
  "@context": [
    "https://data.nist.gov/od/dm/nerdm-pub-context.jsonld",
    {
      "@base": "ark:/88434/mds2-2895"
    }
  ],
  "@type": [
    "nrdp:DataPublication",
    "nrdp:PublicDataResource",
    "dcat:Dataset"
  ],
  "_extensionSchemas": [
    "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/PublicDataResource"
  ],
  "@id": "ark:/88434/mds2-2895",
  "ediid": "ark:/88434/mds2-2895",
  "version": "1.0.3",
  "doi": "doi:10.18434/mds2-2895",
  "title": "NIST Excerpts Benchmark Data",
  "contactPoint": {
    "fn": "Gary Howarth",
    "hasEmail": "mailto:gary.howarth@nist.gov"
  },
  "modified": "2025-01-31 00:00:00",
  "status": "available",
  "landingPage": "https://data.nist.gov/od/id/mds2-2895",
  "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.",
    "Jan 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",
    "The data are curated subsets of U.S. Census Bureau products."
  ],
  "keyword": [
    "privacy",
    "synthetic data",
    "demographic data",
    "American Community Survey",
    "SDNist"
  ],
  "theme": [
    "Information Technology: Privacy",
    "Information Technology: Data and informatics",
    "Information Technology: Software research"
  ],
  "topic": [
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Information Technology: Privacy"
    },
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Information Technology: Data and informatics"
    },
    {
      "@type": "Concept",
      "scheme": "https://data.nist.gov/od/dm/nist-themes/v1.1",
      "tag": "Information Technology: Software research"
    }
  ],
  "accessLevel": "public",
  "license": "https://www.nist.gov/open/license",
  "publisher": {
    "name": "National Institute of Standards and Technology",
    "@type": "org:Organization"
  },
  "language": [
    "en"
  ],
  "bureauCode": [
    "006:55"
  ],
  "programCode": [
    "006:052"
  ],
  "_editStatus": "done",
  "components": [
    {
      "accessURL": "https://github.com/usnistgov/SDNist/tree/main/BenchmarkData",
      "format": {
        "description": "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",
      "@type": [
        "nrdp:AccessPage",
        "dcat:Distribution"
      ],
      "@id": "#usnistgov/SDNist/tree/main/BenchmarkData",
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/AccessPage"
      ]
    }
  ],
  "authors": [
    {
      "familyName": "Task",
      "fn": "Christine  Task",
      "givenName": "Christine",
      "middleName": "",
      "affiliation": [
        {
          "title": "Knexu",
          "@type": "org:Organization"
        }
      ],
      "orcid": "",
      "@type": "foaf:Person"
    },
    {
      "familyName": "Bhagat",
      "fn": "Karan    Bhagat",
      "givenName": "Karan  ",
      "middleName": "",
      "affiliation": [
        {
          "title": "Kn",
          "@type": "org:Organization"
        }
      ],
      "orcid": "",
      "@type": "foaf:Person"
    },
    {
      "familyName": "Damon",
      "fn": "Streat  Damon",
      "givenName": "Streat",
      "middleName": "",
      "affiliation": [
        {
          "title": "Kne",
          "@type": "org:Organization"
        }
      ],
      "orcid": "",
      "@type": "foaf:Person"
    },
    {
      "familyName": "Howarth",
      "fn": "Gary  Howarth",
      "givenName": "Gary",
      "middleName": "",
      "affiliation": [
        {
          "title": "National Institute of Standards and Technology",
          "subunits": [
            "Privacy Engineering Program"
          ],
          "@type": "org:Organization",
          "@id": "ror:05xpvk416"
        }
      ],
      "orcid": "0000-0002-3587-0546",
      "@type": "foaf:Person"
    }
  ],
  "annotated": "2025-01-31T20:22:43.472088",
  "revised": "2023-06-02T18:09:58.429080",
  "issued": null,
  "firstIssued": "2023-06-02T18:09:58.429080",
  "releaseHistory": {
    "@id": "ark:/88434/mds2-2895.rel",
    "@type": [
      "nrdr:ReleaseHistory"
    ],
    "hasRelease": [
      {
        "version": "1.0.0",
        "issued": "2022-12-05",
        "@id": "ark:/88434/mds2-2895/pdr:v/1.0.0",
        "location": "https://data.nist.gov/od/id/ark:/88434/mds2-2895/pdr:v/1.0.0",
        "description": "initial release"
      },
      {
        "version": "1.0.1",
        "issued": "2022-12-05 00:00:00",
        "@id": "ark:/88434/mds2-2895/pdr:v/1.0.1",
        "location": "https://data.nist.gov/od/id/ark:/88434/mds2-2895/pdr:v/1.0.1",
        "description": "metadata update"
      },
      {
        "version": "1.0.2",
        "issued": "2022-12-05 00:00:00",
        "@id": "ark:/88434/mds2-2895/pdr:v/1.0.2",
        "location": "https://data.nist.gov/od/id/ark:/88434/mds2-2895/pdr:v/1.0.2",
        "description": "metadata update"
      },
      {
        "version": "1.0.3",
        "issued": "2025-01-31 00:00:00",
        "@id": "ark:/88434/mds2-2895/pdr:v/1.0.3",
        "location": "https://data.nist.gov/od/id/ark:/88434/mds2-2895/pdr:v/1.0.3",
        "description": "metadata update"
      }
    ]
  }
}