{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "song-ermon-noise-conditioned-score-2019",
    "title": "Song and Ermon: noise-conditioned score generation",
    "summary": "Estimated gradients of noise-perturbed data densities at multiple scales and generated samples with annealed Langevin dynamics.",
    "boundary": "Score matching and Langevin dynamics predate this work. Estimated scores and finite dynamics do not guarantee exact sampling of an arbitrary original data distribution.",
    "area": "Generative-model methods and numerical sampling",
    "topic": "Artificial intelligence",
    "year": 2019,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "song-ermon-noise-conditioned-score-2019",
    "target": {
      "record_id": "urn:uuid:4c643f68-9d74-4b22-a5e5-ff9d4c4b9efb",
      "version": 1,
      "content_hash": "sha256:71b6b9ab0b5830933291845ffb00e48f39bf3a35aaf3f4bc7a5e96b2156bc513"
    },
    "humans": [
      "Yang Song",
      "Stefano Ermon"
    ],
    "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-1907-05600v3",
        "title": "Generative Modeling by Estimating Gradients of the Data Distribution",
        "url": "https://arxiv.org/abs/1907.05600v3"
      }
    ],
    "points": "180000",
    "published_grade": {
      "id": "song-ermon-noise-conditioned-score-2019",
      "entry_id": "song-ermon-noise-conditioned-score-2019",
      "band": "A",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:4c643f68-9d74-4b22-a5e5-ff9d4c4b9efb",
        "version": 1,
        "content_hash": "sha256:71b6b9ab0b5830933291845ffb00e48f39bf3a35aaf3f4bc7a5e96b2156bc513"
      },
      "what_changed": "Estimated gradients of noise-perturbed data densities at multiple scales and generated samples with annealed Langevin dynamics.",
      "scope": "Estimated gradients of noise-perturbed data densities at multiple scales and generated samples with annealed Langevin dynamics. Score matching and Langevin dynamics predate this work. Estimated scores and finite dynamics do not guarantee exact sampling of an arbitrary original data distribution.",
      "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:4c643f68-9d74-4b22-a5e5-ff9d4c4b9efb",
        "version": 1,
        "content_hash": "sha256:71b6b9ab0b5830933291845ffb00e48f39bf3a35aaf3f4bc7a5e96b2156bc513"
      },
      "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": "Yang Song",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Generative Modeling by Estimating Gradients of the Data Distribution",
            "url": "https://arxiv.org/abs/1907.05600v3"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Stefano Ermon",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Generative Modeling by Estimating Gradients of the Data Distribution",
            "url": "https://arxiv.org/abs/1907.05600v3"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Generative Modeling by Estimating Gradients of the Data Distribution",
            "url": "https://arxiv.org/abs/1907.05600v3"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Score matching and Langevin dynamics predate this work. Estimated scores and finite dynamics do not guarantee exact sampling of an arbitrary original data distribution.",
        "domain": "Generative-model methods and numerical sampling"
      },
      "sources": [
        {
          "citation": "Generative Modeling by Estimating Gradients of the Data Distribution",
          "url": "https://arxiv.org/abs/1907.05600v3"
        }
      ],
      "statement": "# Song and Ermon: noise-conditioned score generation\n\nEstimated gradients of noise-perturbed data densities at multiple scales and generated samples with annealed Langevin dynamics.\n\n## Scientific scope\n\nScore matching and Langevin dynamics predate this work. Estimated scores and finite dynamics do not guarantee exact sampling of an arbitrary original data distribution.\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\nYang Song; Stefano Ermon\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- [Generative Modeling by Estimating Gradients of the Data Distribution](https://arxiv.org/abs/1907.05600v3)\n",
      "summary": "Estimated gradients of noise-perturbed data densities at multiple scales and generated samples with annealed Langevin dynamics.",
      "title": "Song and Ermon: noise-conditioned score generation"
    },
    "record_id": "urn:uuid:4c643f68-9d74-4b22-a5e5-ff9d4c4b9efb",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:4c643f68-9d74-4b22-a5e5-ff9d4c4b9efb",
      "version": 1,
      "content_hash": "sha256:71b6b9ab0b5830933291845ffb00e48f39bf3a35aaf3f4bc7a5e96b2156bc513"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:bffe73d502eea1479e3f177c82e7c052e760f842f9a71fb05b4b04f6aede4707"
  },
  "target": {
    "record_id": "urn:uuid:4c643f68-9d74-4b22-a5e5-ff9d4c4b9efb",
    "version": 1,
    "content_hash": "sha256:71b6b9ab0b5830933291845ffb00e48f39bf3a35aaf3f4bc7a5e96b2156bc513"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "song-ermon-noise-conditioned-score-2019",
    "entry_id": "song-ermon-noise-conditioned-score-2019",
    "revision": 1,
    "title": "Song and Ermon: noise-conditioned score generation",
    "context": "Generative-model methods and numerical sampling",
    "track": "Human-designed research method or resource",
    "band": "A",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-16",
    "evidence_cutoff": "2026-10-16",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Estimated gradients of noise-perturbed data densities at multiple scales and generated samples with annealed Langevin dynamics.",
    "scope": "Estimated gradients of noise-perturbed data densities at multiple scales and generated samples with annealed Langevin dynamics. Score matching and Langevin dynamics predate this work. Estimated scores and finite dynamics do not guarantee exact sampling of an arbitrary original data distribution.",
    "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. Score matching and Langevin dynamics predate this work. Estimated scores and finite dynamics do not guarantee exact sampling of an arbitrary original data distribution.",
    "references": [
      {
        "title": "Generative Modeling by Estimating Gradients of the Data Distribution",
        "url": "https://arxiv.org/abs/1907.05600v3",
        "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:4c643f68-9d74-4b22-a5e5-ff9d4c4b9efb",
      "version": 1,
      "content_hash": "sha256:71b6b9ab0b5830933291845ffb00e48f39bf3a35aaf3f4bc7a5e96b2156bc513"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "180000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}