{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "kingma-papamakarios-et-al-autoregressive-flow-family-2016",
    "title": "Inverse and masked autoregressive flows",
    "summary": "Used triangular autoregressive transforms to enrich variational posteriors and construct flexible density estimators, exploiting complementary fast directions in IAF and MAF.",
    "boundary": "Two related original contributions with separate bylines. IAF supports parallel sampling and density evaluation for its own tracked samples, not fast inversion for every externally given point; MAF supports fast density evaluation but dimension-sequential sampling. A triangular Jacobian does not remove this direction-dependent cost.",
    "area": "Flow-based probabilistic generative modeling",
    "topic": "Artificial intelligence",
    "year": 2016,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "kingma-papamakarios-et-al-autoregressive-flow-family-2016",
    "target": {
      "record_id": "urn:uuid:020ea586-2336-422c-ab10-a45839252995",
      "version": 1,
      "content_hash": "sha256:58b3e58c7322b50800d4e68d451bb721727c50e9614982bcd863f763c282fa98"
    },
    "humans": [
      "Diederik P. Kingma",
      "Tim Salimans",
      "Max Welling",
      "George Papamakarios",
      "Theo Pavlakou",
      "Iain Murray"
    ],
    "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-1606-04934v1",
        "title": "Improving Variational Inference with Inverse Autoregressive Flow",
        "url": "https://arxiv.org/abs/1606.04934v1"
      },
      {
        "id": "cur20261015-arxiv-1705-07057v1",
        "title": "Masked Autoregressive Flow for Density Estimation",
        "url": "https://arxiv.org/abs/1705.07057v1"
      }
    ],
    "points": "155000",
    "published_grade": {
      "id": "kingma-papamakarios-et-al-autoregressive-flow-family-2016",
      "entry_id": "kingma-papamakarios-et-al-autoregressive-flow-family-2016",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:020ea586-2336-422c-ab10-a45839252995",
        "version": 1,
        "content_hash": "sha256:58b3e58c7322b50800d4e68d451bb721727c50e9614982bcd863f763c282fa98"
      },
      "what_changed": "Used triangular autoregressive transforms to enrich variational posteriors and construct flexible density estimators, exploiting complementary fast directions in IAF and MAF.",
      "scope": "Used triangular autoregressive transforms to enrich variational posteriors and construct flexible density estimators, exploiting complementary fast directions in IAF and MAF. Two related original contributions with separate bylines. IAF supports parallel sampling and density evaluation for its own tracked samples, not fast inversion for every externally given point; MAF supports fast density evaluation but dimension-sequential sampling. A triangular Jacobian does not remove this direction-dependent cost.",
      "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:020ea586-2336-422c-ab10-a45839252995",
        "version": 1,
        "content_hash": "sha256:58b3e58c7322b50800d4e68d451bb721727c50e9614982bcd863f763c282fa98"
      },
      "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": "Diederik P. Kingma",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Improving Variational Inference with Inverse Autoregressive Flow",
            "url": "https://arxiv.org/abs/1606.04934v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Tim Salimans",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Improving Variational Inference with Inverse Autoregressive Flow",
            "url": "https://arxiv.org/abs/1606.04934v1"
          }
        },
        {
          "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": "Improving Variational Inference with Inverse Autoregressive Flow",
            "url": "https://arxiv.org/abs/1606.04934v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "George Papamakarios",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Masked Autoregressive Flow for Density Estimation",
            "url": "https://arxiv.org/abs/1705.07057v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Theo Pavlakou",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Masked Autoregressive Flow for Density Estimation",
            "url": "https://arxiv.org/abs/1705.07057v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Iain Murray",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Masked Autoregressive Flow for Density Estimation",
            "url": "https://arxiv.org/abs/1705.07057v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Improving Variational Inference with Inverse Autoregressive Flow",
            "url": "https://arxiv.org/abs/1606.04934v1"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Masked Autoregressive Flow for Density Estimation",
            "url": "https://arxiv.org/abs/1705.07057v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Two related original contributions with separate bylines. IAF supports parallel sampling and density evaluation for its own tracked samples, not fast inversion for every externally given point; MAF supports fast density evaluation but dimension-sequential sampling. A triangular Jacobian does not remove this direction-dependent cost.",
        "domain": "Flow-based probabilistic generative modeling"
      },
      "sources": [
        {
          "citation": "Improving Variational Inference with Inverse Autoregressive Flow",
          "url": "https://arxiv.org/abs/1606.04934v1"
        },
        {
          "citation": "Masked Autoregressive Flow for Density Estimation",
          "url": "https://arxiv.org/abs/1705.07057v1"
        }
      ],
      "statement": "# Inverse and masked autoregressive flows\n\nUsed triangular autoregressive transforms to enrich variational posteriors and construct flexible density estimators, exploiting complementary fast directions in IAF and MAF.\n\n## Scientific scope\n\nTwo related original contributions with separate bylines. IAF supports parallel sampling and density evaluation for its own tracked samples, not fast inversion for every externally given point; MAF supports fast density evaluation but dimension-sequential sampling. A triangular Jacobian does not remove this direction-dependent cost.\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; Tim Salimans; Max Welling; George Papamakarios; Theo Pavlakou; Iain Murray\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- [Improving Variational Inference with Inverse Autoregressive Flow](https://arxiv.org/abs/1606.04934v1)\n- [Masked Autoregressive Flow for Density Estimation](https://arxiv.org/abs/1705.07057v1)\n",
      "summary": "Used triangular autoregressive transforms to enrich variational posteriors and construct flexible density estimators, exploiting complementary fast directions in IAF and MAF.",
      "title": "Inverse and masked autoregressive flows"
    },
    "record_id": "urn:uuid:020ea586-2336-422c-ab10-a45839252995",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:020ea586-2336-422c-ab10-a45839252995",
      "version": 1,
      "content_hash": "sha256:58b3e58c7322b50800d4e68d451bb721727c50e9614982bcd863f763c282fa98"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:387eb6dcd14b79520545750bdb26d9b5f3bd94603736c3b438bde2f492e7b28b"
  },
  "target": {
    "record_id": "urn:uuid:020ea586-2336-422c-ab10-a45839252995",
    "version": 1,
    "content_hash": "sha256:58b3e58c7322b50800d4e68d451bb721727c50e9614982bcd863f763c282fa98"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "kingma-papamakarios-et-al-autoregressive-flow-family-2016",
    "entry_id": "kingma-papamakarios-et-al-autoregressive-flow-family-2016",
    "revision": 1,
    "title": "Inverse and masked autoregressive flows",
    "context": "Flow-based probabilistic generative modeling",
    "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": "Used triangular autoregressive transforms to enrich variational posteriors and construct flexible density estimators, exploiting complementary fast directions in IAF and MAF.",
    "scope": "Used triangular autoregressive transforms to enrich variational posteriors and construct flexible density estimators, exploiting complementary fast directions in IAF and MAF. Two related original contributions with separate bylines. IAF supports parallel sampling and density evaluation for its own tracked samples, not fast inversion for every externally given point; MAF supports fast density evaluation but dimension-sequential sampling. A triangular Jacobian does not remove this direction-dependent cost.",
    "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. Two related original contributions with separate bylines. IAF supports parallel sampling and density evaluation for its own tracked samples, not fast inversion for every externally given point; MAF supports fast density evaluation but dimension-sequential sampling. A triangular Jacobian does not remove this direction-dependent cost.",
    "references": [
      {
        "title": "Improving Variational Inference with Inverse Autoregressive Flow",
        "url": "https://arxiv.org/abs/1606.04934v1",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      },
      {
        "title": "Masked Autoregressive Flow for Density Estimation",
        "url": "https://arxiv.org/abs/1705.07057v1",
        "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:020ea586-2336-422c-ab10-a45839252995",
      "version": 1,
      "content_hash": "sha256:58b3e58c7322b50800d4e68d451bb721727c50e9614982bcd863f763c282fa98"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "155000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}