{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "naumov-et-al-dlrm-2019", "title": "DLRM: mixed-feature recommendation and hybrid parallelism benchmark", "summary": "Combined sparse categorical embeddings, dense-feature MLP processing, explicit feature interactions and a top predictor, with model-parallel embeddings and data-parallel dense layers for systems study.", "boundary": "Integrates inherited factorization/MLP techniques rather than inventing recommendation. Public model/benchmark is not the complete confidential production recommender or every later optimized implementation. native BigBasin benchmarks do not certify user benefit, fairness or universal hardware superiority.", "area": "Large-scale recommendation systems", "topic": "Artificial intelligence", "year": 2019, "lane": "HUMAN", "result": "ALGORITHM", "package_id": "naumov-et-al-dlrm-2019", "target": { "record_id": "urn:uuid:e50023c6-dc54-4a16-a2c5-fdbb0f968b12", "version": 1, "content_hash": "sha256:4a012baa3e99596b69826abe5ec5ffae08286a71d40d6d643dd84eee24c391ec" }, "humans": [ "Maxim Naumov", "Dheevatsa Mudigere", "Hao-Jun Michael Shi", "Jianyu Huang", "Narayanan Sundaraman", "Jongsoo Park", "Xiaodong Wang", "Udit Gupta", "Carole-Jean Wu", "Alisson G. Azzolini", "Dmytro Dzhulgakov", "Andrey Mallevich", "Ilia Cherniavskii", "Yinghai Lu", "Raghuraman Krishnamoorthi", "Ansha Yu", "Volodymyr Kondratenko", "Stephanie Pereira", "Xianjie Chen", "Wenlin Chen", "Vijay Rao", "Bill Jia", "Liang Xiong", "Misha Smelyanskiy" ], "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-1906-00091v1", "title": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } ], "points": "125000", "published_grade": { "id": "naumov-et-al-dlrm-2019", "entry_id": "naumov-et-al-dlrm-2019", "band": "A", "modifier": null, "target": { "record_id": "urn:uuid:e50023c6-dc54-4a16-a2c5-fdbb0f968b12", "version": 1, "content_hash": "sha256:4a012baa3e99596b69826abe5ec5ffae08286a71d40d6d643dd84eee24c391ec" }, "what_changed": "Combined sparse categorical embeddings, dense-feature MLP processing, explicit feature interactions and a top predictor, with model-parallel embeddings and data-parallel dense layers for systems study.", "scope": "Combined sparse categorical embeddings, dense-feature MLP processing, explicit feature interactions and a top predictor, with model-parallel embeddings and data-parallel dense layers for systems study. Integrates inherited factorization/MLP techniques rather than inventing recommendation. Public model/benchmark is not the complete confidential production recommender or every later optimized implementation. native BigBasin benchmarks do not certify user benefit, fairness or universal hardware superiority.", "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:e50023c6-dc54-4a16-a2c5-fdbb0f968b12", "version": 1, "content_hash": "sha256:4a012baa3e99596b69826abe5ec5ffae08286a71d40d6d643dd84eee24c391ec" }, "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": "Maxim Naumov", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Dheevatsa Mudigere", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Hao-Jun Michael Shi", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jianyu Huang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Narayanan Sundaraman", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jongsoo Park", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xiaodong Wang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Udit Gupta", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Carole-Jean Wu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Alisson G. Azzolini", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Dmytro Dzhulgakov", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Andrey Mallevich", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ilia Cherniavskii", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yinghai Lu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Raghuraman Krishnamoorthi", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ansha Yu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Volodymyr Kondratenko", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Stephanie Pereira", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xianjie Chen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Wenlin Chen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Vijay Rao", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Bill Jia", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Liang Xiong", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Misha Smelyanskiy", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Integrates inherited factorization/MLP techniques rather than inventing recommendation. Public model/benchmark is not the complete confidential production recommender or every later optimized implementation. native BigBasin benchmarks do not certify user benefit, fairness or universal hardware superiority.", "domain": "Large-scale recommendation systems" }, "sources": [ { "citation": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1" } ], "statement": "# DLRM: mixed-feature recommendation and hybrid parallelism benchmark\n\nCombined sparse categorical embeddings, dense-feature MLP processing, explicit feature interactions and a top predictor, with model-parallel embeddings and data-parallel dense layers for systems study.\n\n## Scientific scope\n\nIntegrates inherited factorization/MLP techniques rather than inventing recommendation. Public model/benchmark is not the complete confidential production recommender or every later optimized implementation. native BigBasin benchmarks do not certify user benefit, fairness or universal hardware superiority.\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\nMaxim Naumov; Dheevatsa Mudigere; Hao-Jun Michael Shi; Jianyu Huang; Narayanan Sundaraman; Jongsoo Park; Xiaodong Wang; Udit Gupta; Carole-Jean Wu; Alisson G. Azzolini; Dmytro Dzhulgakov; Andrey Mallevich; Ilia Cherniavskii; Yinghai Lu; Raghuraman Krishnamoorthi; Ansha Yu; Volodymyr Kondratenko; Stephanie Pereira; Xianjie Chen; Wenlin Chen; Vijay Rao; Bill Jia; Liang Xiong; Misha Smelyanskiy\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- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://arxiv.org/abs/1906.00091v1)\n", "summary": "Combined sparse categorical embeddings, dense-feature MLP processing, explicit feature interactions and a top predictor, with model-parallel embeddings and data-parallel dense layers for systems study.", "title": "DLRM: mixed-feature recommendation and hybrid parallelism benchmark" }, "record_id": "urn:uuid:e50023c6-dc54-4a16-a2c5-fdbb0f968b12", "version": 1, "source_ref": { "record_id": "urn:uuid:e50023c6-dc54-4a16-a2c5-fdbb0f968b12", "version": 1, "content_hash": "sha256:4a012baa3e99596b69826abe5ec5ffae08286a71d40d6d643dd84eee24c391ec" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:06b47dba1b6be3fc75ff32c0171189079763c342ae039e48a59eaab715524a9c" }, "target": { "record_id": "urn:uuid:e50023c6-dc54-4a16-a2c5-fdbb0f968b12", "version": 1, "content_hash": "sha256:4a012baa3e99596b69826abe5ec5ffae08286a71d40d6d643dd84eee24c391ec" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "naumov-et-al-dlrm-2019", "entry_id": "naumov-et-al-dlrm-2019", "revision": 1, "title": "DLRM: mixed-feature recommendation and hybrid parallelism benchmark", "context": "Large-scale recommendation systems", "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": "Combined sparse categorical embeddings, dense-feature MLP processing, explicit feature interactions and a top predictor, with model-parallel embeddings and data-parallel dense layers for systems study.", "scope": "Combined sparse categorical embeddings, dense-feature MLP processing, explicit feature interactions and a top predictor, with model-parallel embeddings and data-parallel dense layers for systems study. Integrates inherited factorization/MLP techniques rather than inventing recommendation. Public model/benchmark is not the complete confidential production recommender or every later optimized implementation. native BigBasin benchmarks do not certify user benefit, fairness or universal hardware superiority.", "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. Integrates inherited factorization/MLP techniques rather than inventing recommendation. Public model/benchmark is not the complete confidential production recommender or every later optimized implementation. native BigBasin benchmarks do not certify user benefit, fairness or universal hardware superiority.", "references": [ { "title": "Deep Learning Recommendation Model for Personalization and Recommendation Systems", "url": "https://arxiv.org/abs/1906.00091v1", "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:e50023c6-dc54-4a16-a2c5-fdbb0f968b12", "version": 1, "content_hash": "sha256:4a012baa3e99596b69826abe5ec5ffae08286a71d40d6d643dd84eee24c391ec" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "125000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }