{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "zhang-et-al-wukong-2024",
    "title": "Wukong: scalable stacked factorization-machine recommendation",
    "summary": "Combined factorization-machine interaction blocks, learned low-rank projections and linear compression blocks in a residual stack, with coordinated depth/width scaling for large recommendation datasets.",
    "boundary": "Empirical scaling over the tested compute/model/data ranges is not an all-scale law. Low-rank interaction compression depends on dimensions and learned projections; the interaction-order explanation does not certify learning every interaction. Distinct from DHEN's heterogeneous-module ensemble; inherited factorization machines and residual normalization are not new here.",
    "area": "Recommendation architectures",
    "topic": "Artificial intelligence",
    "year": 2024,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "zhang-et-al-wukong-2024",
    "target": {
      "record_id": "urn:uuid:f3750f65-1fb3-41bf-a832-1ca82dfbe6a5",
      "version": 1,
      "content_hash": "sha256:22cc88cd471c9646ee65d404aa055c412b0235d7bb29317b898a209a503639ff"
    },
    "humans": [
      "Buyun Zhang",
      "Liang Luo",
      "Yuxin Chen",
      "Jade Nie",
      "Xi Liu",
      "Daifeng Guo",
      "Yanli Zhao",
      "Shen Li",
      "Yuchen Hao",
      "Yantao Yao",
      "Guna Lakshminarayanan",
      "Ellie Dingqiao Wen",
      "Jongsoo Park",
      "Maxim Naumov",
      "Wenlin Chen"
    ],
    "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-2403-02545v1",
        "title": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
        "url": "https://arxiv.org/abs/2403.02545v1"
      }
    ],
    "points": "70000",
    "published_grade": {
      "id": "zhang-et-al-wukong-2024",
      "entry_id": "zhang-et-al-wukong-2024",
      "band": "B",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:f3750f65-1fb3-41bf-a832-1ca82dfbe6a5",
        "version": 1,
        "content_hash": "sha256:22cc88cd471c9646ee65d404aa055c412b0235d7bb29317b898a209a503639ff"
      },
      "what_changed": "Combined factorization-machine interaction blocks, learned low-rank projections and linear compression blocks in a residual stack, with coordinated depth/width scaling for large recommendation datasets.",
      "scope": "Combined factorization-machine interaction blocks, learned low-rank projections and linear compression blocks in a residual stack, with coordinated depth/width scaling for large recommendation datasets. Empirical scaling over the tested compute/model/data ranges is not an all-scale law. Low-rank interaction compression depends on dimensions and learned projections; the interaction-order explanation does not certify learning every interaction. Distinct from DHEN's heterogeneous-module ensemble; inherited factorization machines and residual normalization are not new here.",
      "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:f3750f65-1fb3-41bf-a832-1ca82dfbe6a5",
        "version": 1,
        "content_hash": "sha256:22cc88cd471c9646ee65d404aa055c412b0235d7bb29317b898a209a503639ff"
      },
      "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": "Buyun Zhang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Liang Luo",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yuxin Chen",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jade Nie",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Xi Liu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Daifeng Guo",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yanli Zhao",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Shen Li",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yuchen Hao",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yantao Yao",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Guna Lakshminarayanan",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ellie Dingqiao Wen",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "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": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "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": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        },
        {
          "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": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
            "url": "https://arxiv.org/abs/2403.02545v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Empirical scaling over the tested compute/model/data ranges is not an all-scale law. Low-rank interaction compression depends on dimensions and learned projections; the interaction-order explanation does not certify learning every interaction. Distinct from DHEN's heterogeneous-module ensemble; inherited factorization machines and residual normalization are not new here.",
        "domain": "Recommendation architectures"
      },
      "sources": [
        {
          "citation": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
          "url": "https://arxiv.org/abs/2403.02545v1"
        }
      ],
      "statement": "# Wukong: scalable stacked factorization-machine recommendation\n\nCombined factorization-machine interaction blocks, learned low-rank projections and linear compression blocks in a residual stack, with coordinated depth/width scaling for large recommendation datasets.\n\n## Scientific scope\n\nEmpirical scaling over the tested compute/model/data ranges is not an all-scale law. Low-rank interaction compression depends on dimensions and learned projections; the interaction-order explanation does not certify learning every interaction. Distinct from DHEN's heterogeneous-module ensemble; inherited factorization machines and residual normalization are not new here.\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\nBuyun Zhang; Liang Luo; Yuxin Chen; Jade Nie; Xi Liu; Daifeng Guo; Yanli Zhao; Shen Li; Yuchen Hao; Yantao Yao; Guna Lakshminarayanan; Ellie Dingqiao Wen; Jongsoo Park; Maxim Naumov; Wenlin Chen\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- [Wukong: Towards a Scaling Law for Large-Scale Recommendation](https://arxiv.org/abs/2403.02545v1)\n",
      "summary": "Combined factorization-machine interaction blocks, learned low-rank projections and linear compression blocks in a residual stack, with coordinated depth/width scaling for large recommendation datasets.",
      "title": "Wukong: scalable stacked factorization-machine recommendation"
    },
    "record_id": "urn:uuid:f3750f65-1fb3-41bf-a832-1ca82dfbe6a5",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:f3750f65-1fb3-41bf-a832-1ca82dfbe6a5",
      "version": 1,
      "content_hash": "sha256:22cc88cd471c9646ee65d404aa055c412b0235d7bb29317b898a209a503639ff"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:3248727df139f0370a953020c33f43e981059978b6e679533370a1bee68cf29d"
  },
  "target": {
    "record_id": "urn:uuid:f3750f65-1fb3-41bf-a832-1ca82dfbe6a5",
    "version": 1,
    "content_hash": "sha256:22cc88cd471c9646ee65d404aa055c412b0235d7bb29317b898a209a503639ff"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "zhang-et-al-wukong-2024",
    "entry_id": "zhang-et-al-wukong-2024",
    "revision": 1,
    "title": "Wukong: scalable stacked factorization-machine recommendation",
    "context": "Recommendation architectures",
    "track": "Human-designed research method or resource",
    "band": "B",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-16",
    "evidence_cutoff": "2026-10-16",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Combined factorization-machine interaction blocks, learned low-rank projections and linear compression blocks in a residual stack, with coordinated depth/width scaling for large recommendation datasets.",
    "scope": "Combined factorization-machine interaction blocks, learned low-rank projections and linear compression blocks in a residual stack, with coordinated depth/width scaling for large recommendation datasets. Empirical scaling over the tested compute/model/data ranges is not an all-scale law. Low-rank interaction compression depends on dimensions and learned projections; the interaction-order explanation does not certify learning every interaction. Distinct from DHEN's heterogeneous-module ensemble; inherited factorization machines and residual normalization are not new here.",
    "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. Empirical scaling over the tested compute/model/data ranges is not an all-scale law. Low-rank interaction compression depends on dimensions and learned projections; the interaction-order explanation does not certify learning every interaction. Distinct from DHEN's heterogeneous-module ensemble; inherited factorization machines and residual normalization are not new here.",
    "references": [
      {
        "title": "Wukong: Towards a Scaling Law for Large-Scale Recommendation",
        "url": "https://arxiv.org/abs/2403.02545v1",
        "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:f3750f65-1fb3-41bf-a832-1ca82dfbe6a5",
      "version": 1,
      "content_hash": "sha256:22cc88cd471c9646ee65d404aa055c412b0235d7bb29317b898a209a503639ff"
    },
    "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"
}