{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "meng-et-al-mllib-2015",
    "title": "MLlib: distributed learning algorithms and pipelines in Apache Spark",
    "summary": "Integrated distributed implementations of standard learning methods, optimized communication/linear algebra and a pipeline API with Spark's data-processing ecosystem.",
    "boundary": "This2015preprint reports a library first developed in2012 and open-sourced in2013; paper year is not first-release year. Sixteen paper authors do not exhaust140-plus community contributors. Standard learning algorithms, Spark itself and prior pipeline designs retain inherited credit; no biological application outcome is added.",
    "area": "Distributed machine-learning software",
    "topic": "Artificial intelligence",
    "year": 2015,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "meng-et-al-mllib-2015",
    "target": {
      "record_id": "urn:uuid:c6bcf9b2-d8b6-4018-a5d4-c8cbaf10a3e7",
      "version": 1,
      "content_hash": "sha256:3534ebf421ccee662cb93ad73540e338ce3cbc3aa84735b24c8b2092e53ff79b"
    },
    "humans": [
      "Xiangrui Meng",
      "Joseph Bradley",
      "Burak Yavuz",
      "Evan Sparks",
      "Shivaram Venkataraman",
      "Davies Liu",
      "Jeremy Freeman",
      "DB Tsai",
      "Manish Amde",
      "Sean Owen",
      "Doris Xin",
      "Reynold Xin",
      "Michael J. Franklin",
      "Reza Zadeh",
      "Matei Zaharia",
      "Ameet Talwalkar"
    ],
    "authors_complete": true,
    "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "cur20261015-arxiv-1505-06807v1",
        "title": "MLlib: Machine Learning in Apache Spark",
        "url": "https://arxiv.org/abs/1505.06807v1"
      }
    ],
    "points": "145000",
    "published_grade": {
      "id": "meng-et-al-mllib-2015",
      "entry_id": "meng-et-al-mllib-2015",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:c6bcf9b2-d8b6-4018-a5d4-c8cbaf10a3e7",
        "version": 1,
        "content_hash": "sha256:3534ebf421ccee662cb93ad73540e338ce3cbc3aa84735b24c8b2092e53ff79b"
      },
      "what_changed": "Integrated distributed implementations of standard learning methods, optimized communication/linear algebra and a pipeline API with Spark's data-processing ecosystem.",
      "scope": "Integrated distributed implementations of standard learning methods, optimized communication/linear algebra and a pipeline API with Spark's data-processing ecosystem. This2015preprint reports a library first developed in2012 and open-sourced in2013; paper year is not first-release year. Sixteen paper authors do not exhaust140-plus community contributors. Standard learning algorithms, Spark itself and prior pipeline designs retain inherited credit; no biological application outcome is added.",
      "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:c6bcf9b2-d8b6-4018-a5d4-c8cbaf10a3e7",
        "version": 1,
        "content_hash": "sha256:3534ebf421ccee662cb93ad73540e338ce3cbc3aa84735b24c8b2092e53ff79b"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-10-16T00:00:00Z",
    "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": "Xiangrui Meng",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Joseph Bradley",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Burak Yavuz",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Evan Sparks",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Shivaram Venkataraman",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Davies Liu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jeremy Freeman",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "DB Tsai",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Manish Amde",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Sean Owen",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Doris Xin",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Reynold Xin",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "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": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Reza Zadeh",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "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": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ameet Talwalkar",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "MLlib: Machine Learning in Apache Spark",
            "url": "https://arxiv.org/abs/1505.06807v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "This2015preprint reports a library first developed in2012 and open-sourced in2013; paper year is not first-release year. Sixteen paper authors do not exhaust140-plus community contributors. Standard learning algorithms, Spark itself and prior pipeline designs retain inherited credit; no biological application outcome is added.",
        "domain": "Distributed machine-learning software"
      },
      "sources": [
        {
          "citation": "MLlib: Machine Learning in Apache Spark",
          "url": "https://arxiv.org/abs/1505.06807v1"
        }
      ],
      "statement": "# MLlib: distributed learning algorithms and pipelines in Apache Spark\n\nIntegrated distributed implementations of standard learning methods, optimized communication/linear algebra and a pipeline API with Spark's data-processing ecosystem.\n\n## Scientific scope\n\nThis2015preprint reports a library first developed in2012 and open-sourced in2013; paper year is not first-release year. Sixteen paper authors do not exhaust140-plus community contributors. Standard learning algorithms, Spark itself and prior pipeline designs retain inherited credit; no biological application outcome is added.\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\nXiangrui Meng; Joseph Bradley; Burak Yavuz; Evan Sparks; Shivaram Venkataraman; Davies Liu; Jeremy Freeman; DB Tsai; Manish Amde; Sean Owen; Doris Xin; Reynold Xin; Michael J. Franklin; Reza Zadeh; Matei Zaharia; Ameet Talwalkar\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [MLlib: Machine Learning in Apache Spark](https://arxiv.org/abs/1505.06807v1)\n",
      "summary": "Integrated distributed implementations of standard learning methods, optimized communication/linear algebra and a pipeline API with Spark's data-processing ecosystem.",
      "title": "MLlib: distributed learning algorithms and pipelines in Apache Spark"
    },
    "record_id": "urn:uuid:c6bcf9b2-d8b6-4018-a5d4-c8cbaf10a3e7",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:c6bcf9b2-d8b6-4018-a5d4-c8cbaf10a3e7",
      "version": 1,
      "content_hash": "sha256:3534ebf421ccee662cb93ad73540e338ce3cbc3aa84735b24c8b2092e53ff79b"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:cfa7ef5af65470ecc58951d7d5b50a00a9955331a9d775edc84049e841042c52"
  },
  "target": {
    "record_id": "urn:uuid:c6bcf9b2-d8b6-4018-a5d4-c8cbaf10a3e7",
    "version": 1,
    "content_hash": "sha256:3534ebf421ccee662cb93ad73540e338ce3cbc3aa84735b24c8b2092e53ff79b"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "meng-et-al-mllib-2015",
    "entry_id": "meng-et-al-mllib-2015",
    "revision": 1,
    "title": "MLlib: distributed learning algorithms and pipelines in Apache Spark",
    "context": "Distributed machine-learning software",
    "track": "Human-designed research method or resource",
    "band": "A",
    "modifier": null,
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-16",
    "evidence_cutoff": "2026-10-16",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Integrated distributed implementations of standard learning methods, optimized communication/linear algebra and a pipeline API with Spark's data-processing ecosystem.",
    "scope": "Integrated distributed implementations of standard learning methods, optimized communication/linear algebra and a pipeline API with Spark's data-processing ecosystem. This2015preprint reports a library first developed in2012 and open-sourced in2013; paper year is not first-release year. Sixteen paper authors do not exhaust140-plus community contributors. Standard learning algorithms, Spark itself and prior pipeline designs retain inherited credit; no biological application outcome is added.",
    "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. This2015preprint reports a library first developed in2012 and open-sourced in2013; paper year is not first-release year. Sixteen paper authors do not exhaust140-plus community contributors. Standard learning algorithms, Spark itself and prior pipeline designs retain inherited credit; no biological application outcome is added.",
    "references": [
      {
        "title": "MLlib: Machine Learning in Apache Spark",
        "url": "https://arxiv.org/abs/1505.06807v1",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      }
    ],
    "roles": [
      {
        "who": "Source-listed authors and technical contributors",
        "credit": "SCIENCE",
        "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities."
      }
    ],
    "target": {
      "record_id": "urn:uuid:c6bcf9b2-d8b6-4018-a5d4-c8cbaf10a3e7",
      "version": 1,
      "content_hash": "sha256:3534ebf421ccee662cb93ad73540e338ce3cbc3aa84735b24c8b2092e53ff79b"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "145000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}