{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "zaharia-et-al-rdd-2012",
    "title": "Zaharia and colleagues: resilient distributed datasets for in-memory cluster computing",
    "summary": "Introduced resilient distributed datasets, using immutable partitions and lineage-based recomputation for fault-tolerant in-memory cluster computations, and evaluated the abstraction in Spark.",
    "boundary": "The record is the exact nine-author NSDI 2012 paper and its reported Spark implementation. Later Spark releases, APIs, contributors and deployments remain separate; benchmark gains are limited to the tested workloads and systems.",
    "area": "Distributed systems",
    "year": 2012,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "zaharia-et-al-rdd-2012",
    "target": {
      "record_id": "urn:uuid:a042c3ec-be31-48eb-ab2c-59a9d3eaae1c",
      "version": 1,
      "content_hash": "sha256:1d8c4d8220edcdba28e225cb88300ca1a2d7eb3bcba4502b9d1eed5745207177"
    },
    "humans": [
      "Matei Zaharia",
      "Mosharaf Chowdhury",
      "Tathagata Das",
      "Ankur Dave",
      "Justin Ma",
      "Murphy McCauley",
      "Michael J. Franklin",
      "Scott Shenker",
      "Ion Stoica"
    ],
    "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": "usenix-rdd-2012",
        "title": "USENIX proceedings record for Resilient Distributed Datasets",
        "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
      },
      {
        "id": "usenix-rdd-2012-pdf",
        "title": "USENIX full paper for Resilient Distributed Datasets",
        "url": "https://www.usenix.org/system/files/conference/nsdi12/nsdi12-final138.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://www.usenix.org/system/files/conference/nsdi12/nsdi12-final138.pdf",
      "target": {
        "record_id": "urn:uuid:a042c3ec-be31-48eb-ab2c-59a9d3eaae1c",
        "version": 1,
        "content_hash": "sha256:1d8c4d8220edcdba28e225cb88300ca1a2d7eb3bcba4502b9d1eed5745207177"
      },
      "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION",
      "reviewed_on": "2026-09-26",
      "nationality_inferred": false,
      "sources": [
        {
          "title": "Attribution source",
          "url": "https://www.usenix.org/system/files/conference/nsdi12/nsdi12-final138.pdf"
        }
      ],
      "coverage_status": "COMPLETE",
      "country_labels": {
        "US": "United States"
      }
    },
    "points": "170000",
    "published_grade": {
      "id": "zaharia-et-al-rdd-2012",
      "entry_id": "zaharia-et-al-rdd-2012",
      "band": "A",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:a042c3ec-be31-48eb-ab2c-59a9d3eaae1c",
        "version": 1,
        "content_hash": "sha256:1d8c4d8220edcdba28e225cb88300ca1a2d7eb3bcba4502b9d1eed5745207177"
      },
      "what_changed": "Introduced immutable partitioned datasets with lineage recomputation and evaluated Spark implementation.",
      "scope": "The record is the exact nine-author NSDI 2012 paper and its reported Spark implementation. Later Spark releases, APIs, contributors and deployments remain separate; benchmark gains are limited to the tested workloads and systems.",
      "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:a042c3ec-be31-48eb-ab2c-59a9d3eaae1c",
        "version": 1,
        "content_hash": "sha256:1d8c4d8220edcdba28e225cb88300ca1a2d7eb3bcba4502b9d1eed5745207177"
      },
      "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": "Matei Zaharia",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "USENIX proceedings record for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Mosharaf Chowdhury",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "USENIX proceedings record for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Tathagata Das",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "USENIX proceedings record for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ankur Dave",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "USENIX proceedings record for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Justin Ma",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "USENIX proceedings record for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Murphy McCauley",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "USENIX proceedings record for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Michael J. Franklin",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "USENIX proceedings record for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Scott Shenker",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "USENIX proceedings record for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ion Stoica",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "USENIX proceedings record for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "USENIX proceedings record for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "USENIX full paper for Resilient Distributed Datasets",
            "url": "https://www.usenix.org/system/files/conference/nsdi12/nsdi12-final138.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 exact nine-author NSDI 2012 paper and its reported Spark implementation. Later Spark releases, APIs, contributors and deployments remain separate; benchmark gains are limited to the tested workloads and systems.",
        "domain": "Distributed systems"
      },
      "sources": [
        {
          "citation": "USENIX proceedings record for Resilient Distributed Datasets",
          "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia"
        },
        {
          "citation": "USENIX full paper for Resilient Distributed Datasets",
          "url": "https://www.usenix.org/system/files/conference/nsdi12/nsdi12-final138.pdf"
        }
      ],
      "statement": "# Zaharia and colleagues: resilient distributed datasets for in-memory cluster computing\n\nIntroduced resilient distributed datasets, using immutable partitions and lineage-based recomputation for fault-tolerant in-memory cluster computations, and evaluated the abstraction in Spark.\n\n## Scientific scope\n\nThe record is the exact nine-author NSDI 2012 paper and its reported Spark implementation. Later Spark releases, APIs, contributors and deployments remain separate; benchmark gains are limited to the tested workloads and systems.\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\nMatei Zaharia; Mosharaf Chowdhury; Tathagata Das; Ankur Dave; Justin Ma; Murphy McCauley; Michael J. Franklin; Scott Shenker; Ion Stoica\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- [USENIX proceedings record for Resilient Distributed Datasets](https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia)\n- [USENIX full paper for Resilient Distributed Datasets](https://www.usenix.org/system/files/conference/nsdi12/nsdi12-final138.pdf)\n",
      "summary": "Introduced resilient distributed datasets, using immutable partitions and lineage-based recomputation for fault-tolerant in-memory cluster computations, and evaluated the abstraction in Spark.",
      "title": "Zaharia and colleagues: resilient distributed datasets for in-memory cluster computing"
    },
    "record_id": "urn:uuid:a042c3ec-be31-48eb-ab2c-59a9d3eaae1c",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:a042c3ec-be31-48eb-ab2c-59a9d3eaae1c",
      "version": 1,
      "content_hash": "sha256:1d8c4d8220edcdba28e225cb88300ca1a2d7eb3bcba4502b9d1eed5745207177"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:0cc99927252ca6b920b09b1220132b497513d46905b56a33749d29c448b0a523"
  },
  "target": {
    "record_id": "urn:uuid:a042c3ec-be31-48eb-ab2c-59a9d3eaae1c",
    "version": 1,
    "content_hash": "sha256:1d8c4d8220edcdba28e225cb88300ca1a2d7eb3bcba4502b9d1eed5745207177"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "zaharia-et-al-rdd-2012",
    "entry_id": "zaharia-et-al-rdd-2012",
    "revision": 1,
    "title": "Zaharia and colleagues: resilient distributed datasets for in-memory cluster computing",
    "context": "Distributed systems",
    "track": "SYSTEM",
    "band": "A",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-25",
    "evidence_cutoff": "2026-09-25",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Introduced immutable partitioned datasets with lineage recomputation and evaluated Spark implementation.",
    "scope": "The record is the exact nine-author NSDI 2012 paper and its reported Spark implementation. Later Spark releases, APIs, contributors and deployments remain separate; benchmark gains are limited to the tested workloads and systems.",
    "evidence_summary": "The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact nine-author NSDI 2012 paper and its reported Spark implementation. Later Spark releases, APIs, contributors and deployments remain separate; benchmark gains are limited to the tested workloads and systems.",
    "references": [
      {
        "title": "USENIX proceedings record for Resilient Distributed Datasets",
        "url": "https://www.usenix.org/conference/nsdi12/technical-sessions/presentation/zaharia",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      },
      {
        "title": "USENIX full paper for Resilient Distributed Datasets",
        "url": "https://www.usenix.org/system/files/conference/nsdi12/nsdi12-final138.pdf",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      }
    ],
    "roles": [
      {
        "who": "Matei Zaharia",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Mosharaf Chowdhury",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Tathagata Das",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Ankur Dave",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Justin Ma",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Murphy McCauley",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Michael J. Franklin",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Scott Shenker",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Ion Stoica",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      }
    ],
    "target": {
      "record_id": "urn:uuid:a042c3ec-be31-48eb-ab2c-59a9d3eaae1c",
      "version": 1,
      "content_hash": "sha256:1d8c4d8220edcdba28e225cb88300ca1a2d7eb3bcba4502b9d1eed5745207177"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "170000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}