{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "vae-method",
    "title": "Variational autoencoders through reparameterized inference",
    "summary": "Kingma and Welling used reparameterization to make variational learning in continuous latent-variable models amenable to stochastic gradient optimization.",
    "boundary": "Optimization uses a variational lower bound and an approximate posterior. This is not exact inference for every latent-variable model. The pinned v11 is a later revision of a work first posted in 2013.",
    "area": "Generative modeling",
    "topic": "Computing & AI",
    "year": 2013,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "vae-method",
    "target": {
      "record_id": "urn:uuid:98c06142-6023-4b58-a8fd-4b142a879aaf",
      "version": 1,
      "content_hash": "sha256:474fc6f9accc97791d14f352fe978a0a90d6d1f620f5a9e07ceec88a45902c91"
    },
    "humans": [
      "Diederik P Kingma",
      "Max Welling"
    ],
    "authors_complete": true,
    "human_role_note": "Source paper byline retained, including repeated label positions. Names are not verified unique identities or measurements of individual effort.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "cov13-arxiv-vae-method",
        "title": "Auto-Encoding Variational Bayes",
        "url": "https://arxiv.org/abs/1312.6114v11"
      }
    ],
    "geography": {
      "country_codes": [
        "NL"
      ],
      "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://arxiv.org/pdf/1312.6114",
      "target": {
        "record_id": "urn:uuid:98c06142-6023-4b58-a8fd-4b142a879aaf",
        "version": 1,
        "content_hash": "sha256:474fc6f9accc97791d14f352fe978a0a90d6d1f620f5a9e07ceec88a45902c91"
      },
      "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION",
      "reviewed_on": "2026-09-26",
      "nationality_inferred": false,
      "sources": [
        {
          "title": "Attribution source",
          "url": "https://arxiv.org/pdf/1312.6114"
        }
      ],
      "coverage_status": "COMPLETE",
      "country_labels": {
        "NL": "Netherlands"
      }
    },
    "points": "45000",
    "published_grade": {
      "id": "vae-method",
      "entry_id": "vae-method",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:98c06142-6023-4b58-a8fd-4b142a879aaf",
        "version": 1,
        "content_hash": "sha256:474fc6f9accc97791d14f352fe978a0a90d6d1f620f5a9e07ceec88a45902c91"
      },
      "what_changed": "Kingma and Welling used reparameterization to make variational learning in continuous latent-variable models amenable to stochastic gradient optimization.",
      "scope": "Kingma and Welling used reparameterization to make variational learning in continuous latent-variable models amenable to stochastic gradient optimization. Scope limitation: Optimization uses a variational lower bound and an approximate posterior. This is not exact inference for every latent-variable model. The pinned v11 is a later revision of a work first posted in 2013.",
      "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:98c06142-6023-4b58-a8fd-4b142a879aaf",
        "version": 1,
        "content_hash": "sha256:474fc6f9accc97791d14f352fe978a0a90d6d1f620f5a9e07ceec88a45902c91"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-09-13T00:00:00Z",
    "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": "Diederik P Kingma",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Auto-Encoding Variational Bayes",
            "url": "https://arxiv.org/abs/1312.6114v11"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Max Welling",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Auto-Encoding Variational Bayes",
            "url": "https://arxiv.org/abs/1312.6114v11"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Auto-Encoding Variational Bayes",
            "url": "https://arxiv.org/abs/1312.6114v11"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Optimization uses a variational lower bound and an approximate posterior. This is not exact inference for every latent-variable model. The pinned v11 is a later revision of a work first posted in 2013.",
        "domain": "Generative modeling"
      },
      "sources": [
        {
          "citation": "Auto-Encoding Variational Bayes",
          "url": "https://arxiv.org/abs/1312.6114v11"
        }
      ],
      "statement": "# Variational autoencoders through reparameterized inference\n\nKingma and Welling used reparameterization to make variational learning in continuous latent-variable models amenable to stochastic gradient optimization.\n\n## Scientific scope\n\nOptimization uses a variational lower bound and an approximate posterior. This is not exact inference for every latent-variable model. The pinned v11 is a later revision of a work first posted in 2013.\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\nDiederik P Kingma; Max Welling\n\nSource paper byline retained, including repeated label positions. Names are not verified unique identities or measurements of individual effort.\n\n\n\n## Original sources\n\n- [Auto-Encoding Variational Bayes](https://arxiv.org/abs/1312.6114v11)\n",
      "summary": "Kingma and Welling used reparameterization to make variational learning in continuous latent-variable models amenable to stochastic gradient optimization.",
      "title": "Variational autoencoders through reparameterized inference"
    },
    "record_id": "urn:uuid:98c06142-6023-4b58-a8fd-4b142a879aaf",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:98c06142-6023-4b58-a8fd-4b142a879aaf",
      "version": 1,
      "content_hash": "sha256:474fc6f9accc97791d14f352fe978a0a90d6d1f620f5a9e07ceec88a45902c91"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:cce819c0ae65bef6c9cd280829144c080876d7a6d8e10a8c60fa2a59ff3c7149"
  },
  "target": {
    "record_id": "urn:uuid:98c06142-6023-4b58-a8fd-4b142a879aaf",
    "version": 1,
    "content_hash": "sha256:474fc6f9accc97791d14f352fe978a0a90d6d1f620f5a9e07ceec88a45902c91"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "vae-method",
    "entry_id": "vae-method",
    "revision": 1,
    "title": "Variational autoencoders through reparameterized inference",
    "context": "Generative modeling",
    "track": "Scoped scientific or research-capability contribution",
    "band": "A",
    "modifier": null,
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-14",
    "evidence_cutoff": "2026-09-14",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Kingma and Welling used reparameterization to make variational learning in continuous latent-variable models amenable to stochastic gradient optimization.",
    "scope": "Kingma and Welling used reparameterization to make variational learning in continuous latent-variable models amenable to stochastic gradient optimization. Scope limitation: Optimization uses a variational lower bound and an approximate posterior. This is not exact inference for every latent-variable model. The pinned v11 is a later revision of a work first posted in 2013.",
    "evidence_summary": "Assessment uses the catalogue-linked source evidence for the stated contribution. Optimization uses a variational lower bound and an approximate posterior. This is not exact inference for every latent-variable model. The pinned v11 is a later revision of a work first posted in 2013.",
    "references": [
      {
        "title": "Auto-Encoding Variational Bayes",
        "url": "https://arxiv.org/abs/1312.6114v11",
        "locator": "Retained catalogue source evidence; Versioned author abstract and full deposited byline, not full experimental or proof review."
      }
    ],
    "roles": [
      {
        "who": "Diederik P Kingma",
        "credit": "SCIENCE",
        "did": "Named source contributor; exact labor shares are not measured."
      },
      {
        "who": "Max Welling",
        "credit": "SCIENCE",
        "did": "Named source contributor; exact labor shares are not measured."
      }
    ],
    "target": {
      "record_id": "urn:uuid:98c06142-6023-4b58-a8fd-4b142a879aaf",
      "version": 1,
      "content_hash": "sha256:474fc6f9accc97791d14f352fe978a0a90d6d1f620f5a9e07ceec88a45902c91"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "45000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}