{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "gebru-et-al-datasheets-datasets-2021",
    "title": "Gebru and colleagues: datasheets for datasets",
    "summary": "Proposed standardized datasheets documenting a dataset's motivation, composition, collection process, recommended uses and other consequential properties.",
    "boundary": "The record is the exact seven-author work, first circulated in 2018 and published in Communications of the ACM in 2021. It does not treat documentation as proof of dataset quality or safety, or absorb model cards and later data-governance standards.",
    "area": "Evaluation, safety and interpretability",
    "topic": "Artificial intelligence",
    "year": 2021,
    "lane": "HUMAN",
    "result": "FORMALIZATION",
    "package_id": "gebru-et-al-datasheets-datasets-2021",
    "target": {
      "record_id": "urn:uuid:a7387406-e853-4e39-a814-6677cfd2199c",
      "version": 1,
      "content_hash": "sha256:fa3aa77333b2ebca4cabdcecb8e4a3f808f99c32a997c1b0c5bbacf26e02fd2c"
    },
    "humans": [
      "Timnit Gebru",
      "Jamie Morgenstern",
      "Briana Vecchione",
      "Jennifer Wortman Vaughan",
      "Hanna Wallach",
      "Hal Daumé III",
      "Kate Crawford"
    ],
    "authors_complete": true,
    "human_role_note": "The named authors contributed to this scoped work; individual effort shares and later applications are not assigned by the byline.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "arxiv-datasheets-datasets-2018",
        "title": "arXiv manuscript for Datasheets for Datasets",
        "url": "https://arxiv.org/abs/1803.09010"
      },
      {
        "id": "acm-datasheets-datasets-2021",
        "title": "ACM publication of Datasheets for Datasets",
        "url": "https://doi.org/10.1145/3458723"
      }
    ],
    "points": "95000",
    "published_grade": {
      "id": "gebru-et-al-datasheets-datasets-2021",
      "entry_id": "gebru-et-al-datasheets-datasets-2021",
      "band": "A",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:a7387406-e853-4e39-a814-6677cfd2199c",
        "version": 1,
        "content_hash": "sha256:fa3aa77333b2ebca4cabdcecb8e4a3f808f99c32a997c1b0c5bbacf26e02fd2c"
      },
      "what_changed": "Proposed a structured dataset datasheet covering motivation, composition, collection and recommended use.",
      "scope": "The record is the exact seven-author work, first circulated in 2018 and published in Communications of the ACM in 2021. It does not treat documentation as proof of dataset quality or safety, or absorb model cards and later data-governance standards.",
      "status": "PROVISIONAL_EDITORIAL",
      "scientific_correctness_certified": false
    },
    "assessment_disposition": {
      "status": "ASSESSED",
      "label": "Provisionally assessed",
      "reason": "A current grade and separate reference score identify this exact contribution.",
      "target": {
        "record_id": "urn:uuid:a7387406-e853-4e39-a814-6677cfd2199c",
        "version": 1,
        "content_hash": "sha256:fa3aa77333b2ebca4cabdcecb8e4a3f808f99c32a997c1b0c5bbacf26e02fd2c"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-09-25T00:00:00Z",
    "publisher": {
      "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33",
      "role": "WRS_EDITORIAL_PUBLICATION"
    },
    "record": {
      "contributors": [
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Timnit Gebru",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formalizer"
          ],
          "source": {
            "citation": "arXiv manuscript for Datasheets for Datasets",
            "url": "https://arxiv.org/abs/1803.09010"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jamie Morgenstern",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formalizer"
          ],
          "source": {
            "citation": "arXiv manuscript for Datasheets for Datasets",
            "url": "https://arxiv.org/abs/1803.09010"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Briana Vecchione",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formalizer"
          ],
          "source": {
            "citation": "arXiv manuscript for Datasheets for Datasets",
            "url": "https://arxiv.org/abs/1803.09010"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jennifer Wortman Vaughan",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formalizer"
          ],
          "source": {
            "citation": "arXiv manuscript for Datasheets for Datasets",
            "url": "https://arxiv.org/abs/1803.09010"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Hanna Wallach",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formalizer"
          ],
          "source": {
            "citation": "arXiv manuscript for Datasheets for Datasets",
            "url": "https://arxiv.org/abs/1803.09010"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Hal Daumé III",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formalizer"
          ],
          "source": {
            "citation": "arXiv manuscript for Datasheets for Datasets",
            "url": "https://arxiv.org/abs/1803.09010"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Kate Crawford",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formalizer"
          ],
          "source": {
            "citation": "arXiv manuscript for Datasheets for Datasets",
            "url": "https://arxiv.org/abs/1803.09010"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "arXiv manuscript for Datasheets for Datasets",
            "url": "https://arxiv.org/abs/1803.09010"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "ACM publication of Datasheets for Datasets",
            "url": "https://doi.org/10.1145/3458723"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "The record is the exact seven-author work, first circulated in 2018 and published in Communications of the ACM in 2021. It does not treat documentation as proof of dataset quality or safety, or absorb model cards and later data-governance standards.",
        "domain": "Evaluation, safety and interpretability"
      },
      "sources": [
        {
          "citation": "arXiv manuscript for Datasheets for Datasets",
          "url": "https://arxiv.org/abs/1803.09010"
        },
        {
          "citation": "ACM publication of Datasheets for Datasets",
          "url": "https://doi.org/10.1145/3458723"
        }
      ],
      "statement": "# Gebru and colleagues: datasheets for datasets\n\nProposed standardized datasheets documenting a dataset's motivation, composition, collection process, recommended uses and other consequential properties.\n\n## Scientific scope\n\nThe record is the exact seven-author work, first circulated in 2018 and published in Communications of the ACM in 2021. It does not treat documentation as proof of dataset quality or safety, or absorb model cards and later data-governance standards.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nTimnit Gebru; Jamie Morgenstern; Briana Vecchione; Jennifer Wortman Vaughan; Hanna Wallach; Hal Daumé III; Kate Crawford\n\nThe named authors contributed to this scoped work; individual effort shares and later applications are not assigned by the byline.\n\n\n\n## Original sources\n\n- [arXiv manuscript for Datasheets for Datasets](https://arxiv.org/abs/1803.09010)\n- [ACM publication of Datasheets for Datasets](https://doi.org/10.1145/3458723)\n",
      "summary": "Proposed standardized datasheets documenting a dataset's motivation, composition, collection process, recommended uses and other consequential properties.",
      "title": "Gebru and colleagues: datasheets for datasets"
    },
    "record_id": "urn:uuid:a7387406-e853-4e39-a814-6677cfd2199c",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:a7387406-e853-4e39-a814-6677cfd2199c",
      "version": 1,
      "content_hash": "sha256:fa3aa77333b2ebca4cabdcecb8e4a3f808f99c32a997c1b0c5bbacf26e02fd2c"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:6c8aec010e0e6fc1ff8cc2b9139af0579df6e20ebee138cd213c94c2973c2f88"
  },
  "target": {
    "record_id": "urn:uuid:a7387406-e853-4e39-a814-6677cfd2199c",
    "version": 1,
    "content_hash": "sha256:fa3aa77333b2ebca4cabdcecb8e4a3f808f99c32a997c1b0c5bbacf26e02fd2c"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "gebru-et-al-datasheets-datasets-2021",
    "entry_id": "gebru-et-al-datasheets-datasets-2021",
    "revision": 1,
    "title": "Gebru and colleagues: datasheets for datasets",
    "context": "Evaluation, safety and interpretability",
    "track": "FORMALIZATION",
    "band": "A",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-25",
    "evidence_cutoff": "2026-09-25",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Proposed a structured dataset datasheet covering motivation, composition, collection and recommended use.",
    "scope": "The record is the exact seven-author work, first circulated in 2018 and published in Communications of the ACM in 2021. It does not treat documentation as proof of dataset quality or safety, or absorb model cards and later data-governance standards.",
    "evidence_summary": "The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact seven-author work, first circulated in 2018 and published in Communications of the ACM in 2021. It does not treat documentation as proof of dataset quality or safety, or absorb model cards and later data-governance standards.",
    "references": [
      {
        "title": "arXiv manuscript for Datasheets for Datasets",
        "url": "https://arxiv.org/abs/1803.09010",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      }
    ],
    "roles": [
      {
        "who": "Timnit Gebru",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Jamie Morgenstern",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Briana Vecchione",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Jennifer Wortman Vaughan",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Hanna Wallach",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Hal Daumé III",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Kate Crawford",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      }
    ],
    "target": {
      "record_id": "urn:uuid:a7387406-e853-4e39-a814-6677cfd2199c",
      "version": 1,
      "content_hash": "sha256:fa3aa77333b2ebca4cabdcecb8e4a3f808f99c32a997c1b0c5bbacf26e02fd2c"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "95000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}