{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "neural-ordinary-differential-equations-2018",
    "title": "Chen and colleagues: neural ordinary differential equations",
    "summary": "Parameterized the derivative of hidden state with a neural network and used differential-equation solvers to define continuous-depth models, latent time-series models and continuous normalizing flows.",
    "boundary": "The record is the exact 2018 NeurIPS paper. Classical ODE solvers, residual networks, later augmented neural ODEs and claims about universal superiority or physical discovery remain separate.",
    "area": "Neural and deep learning",
    "year": 2018,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "neural-ordinary-differential-equations-2018",
    "target": {
      "record_id": "urn:uuid:57d43b51-d49b-43e0-a575-f366a2ad1733",
      "version": 1,
      "content_hash": "sha256:c1717ed27dbd0b13ca13cab8497a19cbfd15f81dadabe3250782b6563bdaa335"
    },
    "humans": [
      "Ricky T. Q. Chen",
      "Yulia Rubanova",
      "Jesse Bettencourt",
      "David K. Duvenaud"
    ],
    "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": "neurips-neural-ode-2018",
        "title": "NeurIPS, Neural Ordinary Differential Equations",
        "url": "https://proceedings.neurips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html"
      },
      {
        "id": "arxiv-neural-ode-2018",
        "title": "Chen et al., Neural Ordinary Differential Equations preprint",
        "url": "https://arxiv.org/abs/1806.07366"
      }
    ],
    "geography": {
      "country_codes": [
        "CA"
      ],
      "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://papers.nips.cc/paper_files/paper/2018/file/69386f6bb1dfed68692a24c8686939b9-Paper.pdf",
      "target": {
        "record_id": "urn:uuid:57d43b51-d49b-43e0-a575-f366a2ad1733",
        "version": 1,
        "content_hash": "sha256:c1717ed27dbd0b13ca13cab8497a19cbfd15f81dadabe3250782b6563bdaa335"
      },
      "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION",
      "reviewed_on": "2026-09-26",
      "nationality_inferred": false,
      "sources": [
        {
          "title": "Attribution source",
          "url": "https://papers.nips.cc/paper_files/paper/2018/file/69386f6bb1dfed68692a24c8686939b9-Paper.pdf"
        }
      ],
      "coverage_status": "COMPLETE",
      "country_labels": {
        "CA": "Canada"
      }
    },
    "points": "175000",
    "published_grade": {
      "id": "neural-ordinary-differential-equations-2018",
      "entry_id": "neural-ordinary-differential-equations-2018",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:57d43b51-d49b-43e0-a575-f366a2ad1733",
        "version": 1,
        "content_hash": "sha256:c1717ed27dbd0b13ca13cab8497a19cbfd15f81dadabe3250782b6563bdaa335"
      },
      "what_changed": "Network depth could be treated as a continuous integration variable in trainable models.",
      "scope": "Exact four-author 2018 paper; earlier ODE mathematics and later augmented neural ODEs separate.",
      "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:57d43b51-d49b-43e0-a575-f366a2ad1733",
        "version": 1,
        "content_hash": "sha256:c1717ed27dbd0b13ca13cab8497a19cbfd15f81dadabe3250782b6563bdaa335"
      },
      "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": "Ricky T. Q. Chen",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "NeurIPS, Neural Ordinary Differential Equations",
            "url": "https://proceedings.neurips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yulia Rubanova",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "NeurIPS, Neural Ordinary Differential Equations",
            "url": "https://proceedings.neurips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jesse Bettencourt",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "NeurIPS, Neural Ordinary Differential Equations",
            "url": "https://proceedings.neurips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "David K. Duvenaud",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "NeurIPS, Neural Ordinary Differential Equations",
            "url": "https://proceedings.neurips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "NeurIPS, Neural Ordinary Differential Equations",
            "url": "https://proceedings.neurips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Chen et al., Neural Ordinary Differential Equations preprint",
            "url": "https://arxiv.org/abs/1806.07366"
          }
        }
      ],
      "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 2018 NeurIPS paper. Classical ODE solvers, residual networks, later augmented neural ODEs and claims about universal superiority or physical discovery remain separate.",
        "domain": "Neural and deep learning"
      },
      "sources": [
        {
          "citation": "NeurIPS, Neural Ordinary Differential Equations",
          "url": "https://proceedings.neurips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html"
        },
        {
          "citation": "Chen et al., Neural Ordinary Differential Equations preprint",
          "url": "https://arxiv.org/abs/1806.07366"
        }
      ],
      "statement": "# Chen and colleagues: neural ordinary differential equations\n\nParameterized the derivative of hidden state with a neural network and used differential-equation solvers to define continuous-depth models, latent time-series models and continuous normalizing flows.\n\n## Scientific scope\n\nThe record is the exact 2018 NeurIPS paper. Classical ODE solvers, residual networks, later augmented neural ODEs and claims about universal superiority or physical discovery remain separate.\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\nRicky T. Q. Chen; Yulia Rubanova; Jesse Bettencourt; David K. Duvenaud\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- [NeurIPS, Neural Ordinary Differential Equations](https://proceedings.neurips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html)\n- [Chen et al., Neural Ordinary Differential Equations preprint](https://arxiv.org/abs/1806.07366)\n",
      "summary": "Parameterized the derivative of hidden state with a neural network and used differential-equation solvers to define continuous-depth models, latent time-series models and continuous normalizing flows.",
      "title": "Chen and colleagues: neural ordinary differential equations"
    },
    "record_id": "urn:uuid:57d43b51-d49b-43e0-a575-f366a2ad1733",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:57d43b51-d49b-43e0-a575-f366a2ad1733",
      "version": 1,
      "content_hash": "sha256:c1717ed27dbd0b13ca13cab8497a19cbfd15f81dadabe3250782b6563bdaa335"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:87247d0ac47f0497e351533566ebfd3d4d64ba44f291942bfeac2a5b1082b87c"
  },
  "target": {
    "record_id": "urn:uuid:57d43b51-d49b-43e0-a575-f366a2ad1733",
    "version": 1,
    "content_hash": "sha256:c1717ed27dbd0b13ca13cab8497a19cbfd15f81dadabe3250782b6563bdaa335"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "neural-ordinary-differential-equations-2018",
    "entry_id": "neural-ordinary-differential-equations-2018",
    "revision": 1,
    "title": "Chen and colleagues: neural ordinary differential equations",
    "context": "Machine learning",
    "track": "Modeling framework",
    "band": "A",
    "modifier": null,
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-25",
    "evidence_cutoff": "2026-09-25",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Network depth could be treated as a continuous integration variable in trainable models.",
    "scope": "Exact four-author 2018 paper; earlier ODE mathematics and later augmented neural ODEs separate.",
    "evidence_summary": "The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact 2018 NeurIPS paper. Classical ODE solvers, residual networks, later augmented neural ODEs and claims about universal superiority or physical discovery remain separate.",
    "references": [
      {
        "title": "NeurIPS, Neural Ordinary Differential Equations",
        "url": "https://proceedings.neurips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      },
      {
        "title": "Chen et al., Neural Ordinary Differential Equations preprint",
        "url": "https://arxiv.org/abs/1806.07366",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      }
    ],
    "roles": [
      {
        "who": "Ricky T. Q. Chen",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Yulia Rubanova",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "Jesse Bettencourt",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      },
      {
        "who": "David K. Duvenaud",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      }
    ],
    "target": {
      "record_id": "urn:uuid:57d43b51-d49b-43e0-a575-f366a2ad1733",
      "version": 1,
      "content_hash": "sha256:c1717ed27dbd0b13ca13cab8497a19cbfd15f81dadabe3250782b6563bdaa335"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "175000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}