{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "mapreduce-2004",
    "title": "Dean and Ghemawat: MapReduce",
    "summary": "Presented a map-and-reduce programming model and runtime that automatically partitions work, schedules it across clusters and handles machine failures for large data-processing jobs.",
    "boundary": "The record is the 2004 OSDI paper and its reported Google implementation. It does not claim that the paper invented all parallel functional primitives or represents every later data-processing system.",
    "area": "Distributed computing",
    "year": 2004,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "mapreduce-2004",
    "target": {
      "record_id": "urn:uuid:b909f067-8c48-4833-a46b-c36d75f8b884",
      "version": 1,
      "content_hash": "sha256:43fd9088dbff2836c73931ca2e0da0cb53dae2215f21bf03ea5f846c1d2324be"
    },
    "humans": [
      "Jeffrey Dean",
      "Sanjay Ghemawat"
    ],
    "human_identities": [
      {
        "author_position": 0,
        "source_name": "Jeffrey Dean",
        "person_id": "wrs-person-79b150dbedda3935752fb6fc",
        "display_name": "Jeff Dean",
        "status": "SOURCE_LINKED_IDENTITY",
        "sources": [
          {
            "title": "Attribution source",
            "url": "https://research.google/pubs/distilling-the-knowledge-in-a-neural-network/"
          },
          {
            "title": "Attribution source",
            "url": "https://arxiv.org/abs/1503.02531"
          },
          {
            "title": "Attribution source",
            "url": "https://research.google/pubs/mapreduce-simplified-data-processing-on-large-clusters/"
          },
          {
            "title": "Attribution source",
            "url": "https://research.google/pubs/efficient-estimation-of-word-representations-in-vector-space/"
          },
          {
            "title": "Attribution source",
            "url": "https://research.google/pubs/bigtable-a-distributed-storage-system-for-structured-data/"
          },
          {
            "title": "Attribution source",
            "url": "https://research.google/pubs/spanner-googles-globally-distributed-database-2/"
          }
        ]
      },
      {
        "author_position": 1,
        "source_name": "Sanjay Ghemawat",
        "person_id": "wrs-person-926ba55b0123d6a2e62539b2",
        "display_name": "Sanjay Ghemawat",
        "status": "SOURCE_LINKED_IDENTITY",
        "sources": [
          {
            "title": "Attribution source",
            "url": "https://research.google/pubs/the-google-file-system/"
          },
          {
            "title": "Attribution source",
            "url": "https://research.google/pubs/mapreduce-simplified-data-processing-on-large-clusters/"
          },
          {
            "title": "Attribution source",
            "url": "https://research.google/pubs/bigtable-a-distributed-storage-system-for-structured-data/"
          },
          {
            "title": "Attribution source",
            "url": "https://research.google/pubs/spanner-googles-globally-distributed-database-2/"
          }
        ]
      }
    ],
    "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": "google-dean-ghemawat-mapreduce",
        "title": "Google Research: MapReduce",
        "url": "https://research.google/pubs/mapreduce-simplified-data-processing-on-large-clusters/"
      },
      {
        "id": "dean-ghemawat-mapreduce-paper",
        "title": "Dean and Ghemawat, MapReduce: Simplified Data Processing on Large Clusters",
        "url": "https://research.google.com/archive/mapreduce-osdi04.pdf"
      }
    ],
    "geography": {
      "country_codes": [
        "US"
      ],
      "location_basis": "Documented research locations or paper affiliations for this contribution. Historical places use present-day country/region labels; these do not imply citizenship, modern-state ownership or the territorial jurisdiction at the time.",
      "source_url": "https://cse.buffalo.edu/~okennedy/courses/papers/mapreduce.pdf",
      "target": {
        "record_id": "urn:uuid:b909f067-8c48-4833-a46b-c36d75f8b884",
        "version": 1,
        "content_hash": "sha256:43fd9088dbff2836c73931ca2e0da0cb53dae2215f21bf03ea5f846c1d2324be"
      },
      "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION",
      "reviewed_on": "2026-09-27",
      "nationality_inferred": false,
      "sources": [
        {
          "title": "Attribution source",
          "url": "https://cse.buffalo.edu/~okennedy/courses/papers/mapreduce.pdf"
        },
        {
          "title": "Attribution source",
          "url": "https://storage.googleapis.com/gweb-research2023-media/pubtools/4449.pdf"
        },
        {
          "title": "Attribution source",
          "url": "https://www.jollyvip.com/wp-content/uploads/2012/Diplomarbeit_Marcel_Miersebach-v3.0.pdf"
        }
      ],
      "coverage_status": "COMPLETE",
      "country_labels": {
        "US": "United States"
      }
    },
    "points": "260000",
    "published_grade": {
      "id": "mapreduce-2004",
      "entry_id": "mapreduce-2004",
      "band": "A",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:b909f067-8c48-4833-a46b-c36d75f8b884",
        "version": 1,
        "content_hash": "sha256:43fd9088dbff2836c73931ca2e0da0cb53dae2215f21bf03ea5f846c1d2324be"
      },
      "what_changed": "Developers could express many large data jobs in a compact model while runtime handled distribution and failures.",
      "scope": "2004 two-author OSDI paper and reported Google implementation; not all parallel functional programming or later data platforms.",
      "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:b909f067-8c48-4833-a46b-c36d75f8b884",
        "version": 1,
        "content_hash": "sha256:43fd9088dbff2836c73931ca2e0da0cb53dae2215f21bf03ea5f846c1d2324be"
      },
      "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": "Jeffrey Dean",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Google Research: MapReduce",
            "url": "https://research.google/pubs/mapreduce-simplified-data-processing-on-large-clusters/"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Sanjay Ghemawat",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Google Research: MapReduce",
            "url": "https://research.google/pubs/mapreduce-simplified-data-processing-on-large-clusters/"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Google Research: MapReduce",
            "url": "https://research.google/pubs/mapreduce-simplified-data-processing-on-large-clusters/"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Dean and Ghemawat, MapReduce: Simplified Data Processing on Large Clusters",
            "url": "https://research.google.com/archive/mapreduce-osdi04.pdf"
          }
        }
      ],
      "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 2004 OSDI paper and its reported Google implementation. It does not claim that the paper invented all parallel functional primitives or represents every later data-processing system.",
        "domain": "Distributed computing"
      },
      "sources": [
        {
          "citation": "Google Research: MapReduce",
          "url": "https://research.google/pubs/mapreduce-simplified-data-processing-on-large-clusters/"
        },
        {
          "citation": "Dean and Ghemawat, MapReduce: Simplified Data Processing on Large Clusters",
          "url": "https://research.google.com/archive/mapreduce-osdi04.pdf"
        }
      ],
      "statement": "# Dean and Ghemawat: MapReduce\n\nPresented a map-and-reduce programming model and runtime that automatically partitions work, schedules it across clusters and handles machine failures for large data-processing jobs.\n\n## Scientific scope\n\nThe record is the 2004 OSDI paper and its reported Google implementation. It does not claim that the paper invented all parallel functional primitives or represents every later data-processing system.\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\nJeffrey Dean; Sanjay Ghemawat\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- [Google Research: MapReduce](https://research.google/pubs/mapreduce-simplified-data-processing-on-large-clusters/)\n- [Dean and Ghemawat, MapReduce: Simplified Data Processing on Large Clusters](https://research.google.com/archive/mapreduce-osdi04.pdf)\n",
      "summary": "Presented a map-and-reduce programming model and runtime that automatically partitions work, schedules it across clusters and handles machine failures for large data-processing jobs.",
      "title": "Dean and Ghemawat: MapReduce"
    },
    "record_id": "urn:uuid:b909f067-8c48-4833-a46b-c36d75f8b884",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:b909f067-8c48-4833-a46b-c36d75f8b884",
      "version": 1,
      "content_hash": "sha256:43fd9088dbff2836c73931ca2e0da0cb53dae2215f21bf03ea5f846c1d2324be"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:6c03c03204510ee028fc4c7e54f973e6bdd16d3d26fb45e79f90cc2b208dc3b0"
  },
  "target": {
    "record_id": "urn:uuid:b909f067-8c48-4833-a46b-c36d75f8b884",
    "version": 1,
    "content_hash": "sha256:43fd9088dbff2836c73931ca2e0da0cb53dae2215f21bf03ea5f846c1d2324be"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "mapreduce-2004",
    "entry_id": "mapreduce-2004",
    "revision": 1,
    "title": "Dean and Ghemawat: MapReduce",
    "context": "Distributed computing",
    "track": "Data-processing programming model and runtime",
    "band": "A",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-25",
    "evidence_cutoff": "2026-09-25",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Developers could express many large data jobs in a compact model while runtime handled distribution and failures.",
    "scope": "2004 two-author OSDI paper and reported Google implementation; not all parallel functional programming or later data platforms.",
    "evidence_summary": "The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the 2004 OSDI paper and its reported Google implementation. It does not claim that the paper invented all parallel functional primitives or represents every later data-processing system.",
    "references": [
      {
        "title": "Google Research: MapReduce",
        "url": "https://research.google/pubs/mapreduce-simplified-data-processing-on-large-clusters/",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      },
      {
        "title": "Dean and Ghemawat, MapReduce: Simplified Data Processing on Large Clusters",
        "url": "https://research.google.com/archive/mapreduce-osdi04.pdf",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      }
    ],
    "roles": [
      {
        "who": "Jeffrey Dean",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Sanjay Ghemawat",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      }
    ],
    "target": {
      "record_id": "urn:uuid:b909f067-8c48-4833-a46b-c36d75f8b884",
      "version": 1,
      "content_hash": "sha256:43fd9088dbff2836c73931ca2e0da0cb53dae2215f21bf03ea5f846c1d2324be"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "260000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}