{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "dosovitskiy-et-al-vit-2020",
    "title": "Dosovitskiy and colleagues: Vision Transformer image-patch classification",
    "summary": "Applied a pure transformer to sequences of image patches for classification, reporting strong transfer after large-scale image pretraining.",
    "boundary": "This is the 2020 ViT preprint, later published at ICLR 2021; results depend on large-scale pretraining and studied recognition benchmarks.",
    "area": "Computer vision architectures",
    "topic": "Artificial intelligence",
    "year": 2020,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "dosovitskiy-et-al-vit-2020",
    "target": {
      "record_id": "urn:uuid:fd5a6930-cfa5-410b-a01e-d6569c36da0e",
      "version": 1,
      "content_hash": "sha256:23a3bef2ced68594c63e17e17b953488cdc9ce0c0acbf6f5cd7a2eea2492c0d9"
    },
    "humans": [
      "Alexey Dosovitskiy",
      "Lucas Beyer",
      "Alexander Kolesnikov",
      "Dirk Weissenborn",
      "Xiaohua Zhai",
      "Thomas Unterthiner",
      "Mostafa Dehghani",
      "Matthias Minderer",
      "Georg Heigold",
      "Sylvain Gelly",
      "Jakob Uszkoreit",
      "Neil Houlsby"
    ],
    "authors_complete": true,
    "human_role_note": "Complete named paper byline. Human research, source-reported system execution and experimental validation are distinct; individual effort shares are not measured.",
    "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-2010-11929",
        "title": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
        "url": "https://arxiv.org/abs/2010.11929v2"
      },
      {
        "id": "company-dosovitskiy-et-al-vit-2020",
        "title": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — official research page",
        "url": "https://research.google/pubs/an-image-is-worth-16x16-words-transformers-for-image-recognition-at-scale/"
      }
    ],
    "points": "70000",
    "published_grade": {
      "id": "dosovitskiy-et-al-vit-2020",
      "entry_id": "dosovitskiy-et-al-vit-2020",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:fd5a6930-cfa5-410b-a01e-d6569c36da0e",
        "version": 1,
        "content_hash": "sha256:23a3bef2ced68594c63e17e17b953488cdc9ce0c0acbf6f5cd7a2eea2492c0d9"
      },
      "what_changed": "Applied a pure transformer to sequences of image patches for classification, reporting strong transfer after large-scale image pretraining.",
      "scope": "Applied a pure transformer to sequences of image patches for classification, reporting strong transfer after large-scale image pretraining. Scope limitation: This is the 2020 ViT preprint, later published at ICLR 2021; results depend on large-scale pretraining and studied recognition benchmarks.",
      "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:fd5a6930-cfa5-410b-a01e-d6569c36da0e",
        "version": 1,
        "content_hash": "sha256:23a3bef2ced68594c63e17e17b953488cdc9ce0c0acbf6f5cd7a2eea2492c0d9"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-09-27T00:00:00Z",
    "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": "Alexey Dosovitskiy",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Lucas Beyer",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Alexander Kolesnikov",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Dirk Weissenborn",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Xiaohua Zhai",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Thomas Unterthiner",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Mostafa Dehghani",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Matthias Minderer",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Georg Heigold",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Sylvain Gelly",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jakob Uszkoreit",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Neil Houlsby",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
            "url": "https://arxiv.org/abs/2010.11929v2"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — official research page",
            "url": "https://research.google/pubs/an-image-is-worth-16x16-words-transformers-for-image-recognition-at-scale/"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "This is the 2020 ViT preprint, later published at ICLR 2021; results depend on large-scale pretraining and studied recognition benchmarks.",
        "domain": "Computer vision architectures"
      },
      "sources": [
        {
          "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
          "url": "https://arxiv.org/abs/2010.11929v2"
        },
        {
          "citation": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — official research page",
          "url": "https://research.google/pubs/an-image-is-worth-16x16-words-transformers-for-image-recognition-at-scale/"
        }
      ],
      "statement": "# Dosovitskiy and colleagues: Vision Transformer image-patch classification\n\nApplied a pure transformer to sequences of image patches for classification, reporting strong transfer after large-scale image pretraining.\n\n## Scientific scope\n\nThis is the 2020 ViT preprint, later published at ICLR 2021; results depend on large-scale pretraining and studied recognition benchmarks.\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\nAlexey Dosovitskiy; Lucas Beyer; Alexander Kolesnikov; Dirk Weissenborn; Xiaohua Zhai; Thomas Unterthiner; Mostafa Dehghani; Matthias Minderer; Georg Heigold; Sylvain Gelly; Jakob Uszkoreit; Neil Houlsby\n\nComplete named paper byline. Human research, source-reported system execution and experimental validation are distinct; individual effort shares are not measured.\n\n\n\n## Original sources\n\n- [Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper](https://arxiv.org/abs/2010.11929v2)\n- [Dosovitskiy and colleagues: Vision Transformer image-patch classification — official research page](https://research.google/pubs/an-image-is-worth-16x16-words-transformers-for-image-recognition-at-scale/)\n",
      "summary": "Applied a pure transformer to sequences of image patches for classification, reporting strong transfer after large-scale image pretraining.",
      "title": "Dosovitskiy and colleagues: Vision Transformer image-patch classification"
    },
    "record_id": "urn:uuid:fd5a6930-cfa5-410b-a01e-d6569c36da0e",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:fd5a6930-cfa5-410b-a01e-d6569c36da0e",
      "version": 1,
      "content_hash": "sha256:23a3bef2ced68594c63e17e17b953488cdc9ce0c0acbf6f5cd7a2eea2492c0d9"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:07cab2fcd6c3f091ac83507fc6e5c2595b06cd5418e792d8ffc88eba1855a511"
  },
  "target": {
    "record_id": "urn:uuid:fd5a6930-cfa5-410b-a01e-d6569c36da0e",
    "version": 1,
    "content_hash": "sha256:23a3bef2ced68594c63e17e17b953488cdc9ce0c0acbf6f5cd7a2eea2492c0d9"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "dosovitskiy-et-al-vit-2020",
    "entry_id": "dosovitskiy-et-al-vit-2020",
    "revision": 1,
    "title": "Dosovitskiy and colleagues: Vision Transformer image-patch classification",
    "context": "Computer vision architectures",
    "track": "Human-designed AI research method or resource",
    "band": "A",
    "modifier": null,
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-27",
    "evidence_cutoff": "2026-09-27",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Applied a pure transformer to sequences of image patches for classification, reporting strong transfer after large-scale image pretraining.",
    "scope": "Applied a pure transformer to sequences of image patches for classification, reporting strong transfer after large-scale image pretraining. Scope limitation: This is the 2020 ViT preprint, later published at ICLR 2021; results depend on large-scale pretraining and studied recognition benchmarks.",
    "evidence_summary": "The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. This is the 2020 ViT preprint, later published at ICLR 2021; results depend on large-scale pretraining and studied recognition benchmarks.",
    "references": [
      {
        "title": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper",
        "url": "https://arxiv.org/abs/2010.11929v2",
        "locator": "Abstract and complete bibliographic byline for 2010.11929v2; not an independent proof or experimental replication."
      },
      {
        "title": "Dosovitskiy and colleagues: Vision Transformer image-patch classification — official research page",
        "url": "https://research.google/pubs/an-image-is-worth-16x16-words-transformers-for-image-recognition-at-scale/",
        "locator": "Source-linked contribution and stated scientific limits; not an independent replication."
      }
    ],
    "roles": [
      {
        "who": "The named authors listed in the linked research record",
        "credit": "SCIENCE",
        "did": "Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured."
      }
    ],
    "target": {
      "record_id": "urn:uuid:fd5a6930-cfa5-410b-a01e-d6569c36da0e",
      "version": 1,
      "content_hash": "sha256:23a3bef2ced68594c63e17e17b953488cdc9ce0c0acbf6f5cd7a2eea2492c0d9"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "70000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}