{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "esser-et-al-multimodal-rectified-transformer-2024",
    "title": "Esser and colleagues: multimodal rectified-flow Transformers",
    "summary": "Combined rectified-flow training-scale choices with separate text/image weights and bidirectional token interactions for high-resolution text-to-image generation.",
    "boundary": "Rectified flow and diffusion Transformers have prior sources. The contribution is their tested multimodal architecture and training design, not every Stable Diffusion 3 checkpoint.",
    "area": "Generative-model methods and numerical sampling",
    "topic": "Artificial intelligence",
    "year": 2024,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "esser-et-al-multimodal-rectified-transformer-2024",
    "target": {
      "record_id": "urn:uuid:e7622bc5-3201-479c-a7ac-a2274a23a3c8",
      "version": 1,
      "content_hash": "sha256:2bd6fa038bf877cbfb356d09a8f6333fef70228028af011729609cb76a7635cf"
    },
    "humans": [
      "Patrick Esser",
      "Sumith Kulal",
      "Andreas Blattmann",
      "Rahim Entezari",
      "Jonas Müller",
      "Harry Saini",
      "Yam Levi",
      "Dominik Lorenz",
      "Axel Sauer",
      "Frederic Boesel",
      "Dustin Podell",
      "Tim Dockhorn",
      "Zion English",
      "Kyle Lacey",
      "Alex Goodwin",
      "Yannik Marek",
      "Robin Rombach"
    ],
    "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-2403-03206v1",
        "title": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
        "url": "https://arxiv.org/abs/2403.03206v1"
      }
    ],
    "points": "150000",
    "published_grade": {
      "id": "esser-et-al-multimodal-rectified-transformer-2024",
      "entry_id": "esser-et-al-multimodal-rectified-transformer-2024",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:e7622bc5-3201-479c-a7ac-a2274a23a3c8",
        "version": 1,
        "content_hash": "sha256:2bd6fa038bf877cbfb356d09a8f6333fef70228028af011729609cb76a7635cf"
      },
      "what_changed": "Combined rectified-flow training-scale choices with separate text/image weights and bidirectional token interactions for high-resolution text-to-image generation.",
      "scope": "Combined rectified-flow training-scale choices with separate text/image weights and bidirectional token interactions for high-resolution text-to-image generation. Rectified flow and diffusion Transformers have prior sources. The contribution is their tested multimodal architecture and training design, not every Stable Diffusion 3 checkpoint.",
      "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:e7622bc5-3201-479c-a7ac-a2274a23a3c8",
        "version": 1,
        "content_hash": "sha256:2bd6fa038bf877cbfb356d09a8f6333fef70228028af011729609cb76a7635cf"
      },
      "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": "Patrick Esser",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Sumith Kulal",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Andreas Blattmann",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Rahim Entezari",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jonas Müller",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Harry Saini",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yam Levi",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Dominik Lorenz",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Axel Sauer",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Frederic Boesel",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Dustin Podell",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Tim Dockhorn",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zion English",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Kyle Lacey",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Alex Goodwin",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yannik Marek",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Robin Rombach",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
            "url": "https://arxiv.org/abs/2403.03206v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Rectified flow and diffusion Transformers have prior sources. The contribution is their tested multimodal architecture and training design, not every Stable Diffusion 3 checkpoint.",
        "domain": "Generative-model methods and numerical sampling"
      },
      "sources": [
        {
          "citation": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
          "url": "https://arxiv.org/abs/2403.03206v1"
        }
      ],
      "statement": "# Esser and colleagues: multimodal rectified-flow Transformers\n\nCombined rectified-flow training-scale choices with separate text/image weights and bidirectional token interactions for high-resolution text-to-image generation.\n\n## Scientific scope\n\nRectified flow and diffusion Transformers have prior sources. The contribution is their tested multimodal architecture and training design, not every Stable Diffusion 3 checkpoint.\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\nPatrick Esser; Sumith Kulal; Andreas Blattmann; Rahim Entezari; Jonas Müller; Harry Saini; Yam Levi; Dominik Lorenz; Axel Sauer; Frederic Boesel; Dustin Podell; Tim Dockhorn; Zion English; Kyle Lacey; Alex Goodwin; Yannik Marek; Robin Rombach\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- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://arxiv.org/abs/2403.03206v1)\n",
      "summary": "Combined rectified-flow training-scale choices with separate text/image weights and bidirectional token interactions for high-resolution text-to-image generation.",
      "title": "Esser and colleagues: multimodal rectified-flow Transformers"
    },
    "record_id": "urn:uuid:e7622bc5-3201-479c-a7ac-a2274a23a3c8",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:e7622bc5-3201-479c-a7ac-a2274a23a3c8",
      "version": 1,
      "content_hash": "sha256:2bd6fa038bf877cbfb356d09a8f6333fef70228028af011729609cb76a7635cf"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:0f707430d05ab347368e4bb63ac7924e7d8fc7fda6ebbe24d7c8fe4995dc47f0"
  },
  "target": {
    "record_id": "urn:uuid:e7622bc5-3201-479c-a7ac-a2274a23a3c8",
    "version": 1,
    "content_hash": "sha256:2bd6fa038bf877cbfb356d09a8f6333fef70228028af011729609cb76a7635cf"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "esser-et-al-multimodal-rectified-transformer-2024",
    "entry_id": "esser-et-al-multimodal-rectified-transformer-2024",
    "revision": 1,
    "title": "Esser and colleagues: multimodal rectified-flow Transformers",
    "context": "Generative-model methods and numerical sampling",
    "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": "Combined rectified-flow training-scale choices with separate text/image weights and bidirectional token interactions for high-resolution text-to-image generation.",
    "scope": "Combined rectified-flow training-scale choices with separate text/image weights and bidirectional token interactions for high-resolution text-to-image generation. Rectified flow and diffusion Transformers have prior sources. The contribution is their tested multimodal architecture and training design, not every Stable Diffusion 3 checkpoint.",
    "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. Rectified flow and diffusion Transformers have prior sources. The contribution is their tested multimodal architecture and training design, not every Stable Diffusion 3 checkpoint.",
    "references": [
      {
        "title": "Scaling Rectified Flow Transformers for High-Resolution Image Synthesis",
        "url": "https://arxiv.org/abs/2403.03206v1",
        "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:e7622bc5-3201-479c-a7ac-a2274a23a3c8",
      "version": 1,
      "content_hash": "sha256:2bd6fa038bf877cbfb356d09a8f6333fef70228028af011729609cb76a7635cf"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "150000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}