{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "yu-et-al-parti-compositional-resource-2022",
    "title": "Yu et al.: Parti autoregressive image synthesis and compositional prompt resource",
    "summary": "Documented encoder-decoder modeling of discrete image tokens and released a broad compositional-prompt evaluation resource to characterize scaling, content fidelity and failure modes in text-to-image synthesis.",
    "boundary": "ViT-VQGAN and sequence-to-sequence modeling are inherited. Acquire integrated research/evaluation resource, not an invention for every model scale. Prompt success and benchmark scores do not imply complete visual world knowledge or dependable text rendering.",
    "area": "Text-to-image modeling and evaluation resources",
    "topic": "Artificial intelligence",
    "year": 2022,
    "lane": "HUMAN",
    "result": "EMPIRICAL",
    "package_id": "yu-et-al-parti-compositional-resource-2022",
    "target": {
      "record_id": "urn:uuid:89003a7c-e5bf-4cb1-aa11-c3cebce4d20c",
      "version": 1,
      "content_hash": "sha256:64cf27fa56cfaa40adeb37bd39a1d46ec47331e0f157c1210cc6bde3020b6d3a"
    },
    "humans": [
      "Jiahui Yu",
      "Yuanzhong Xu",
      "Jing Yu Koh",
      "Thang Luong",
      "Gunjan Baid",
      "Zirui Wang",
      "Vijay Vasudevan",
      "Alexander Ku",
      "Yinfei Yang",
      "Burcu Karagol Ayan",
      "Ben Hutchinson",
      "Wei Han",
      "Zarana Parekh",
      "Xin Li",
      "Han Zhang",
      "Jason Baldridge",
      "Yonghui Wu"
    ],
    "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-2206-10789v1",
        "title": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
        "url": "https://arxiv.org/abs/2206.10789v1"
      },
      {
        "id": "cur20261015-support-yu-et-al-parti-compositional-resource-2022",
        "title": "Yu et al.: Parti autoregressive image synthesis and compositional prompt resource — author/institutional project",
        "url": "https://parti.research.google/"
      }
    ],
    "points": "75000",
    "published_grade": {
      "id": "yu-et-al-parti-compositional-resource-2022",
      "entry_id": "yu-et-al-parti-compositional-resource-2022",
      "band": "B",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:89003a7c-e5bf-4cb1-aa11-c3cebce4d20c",
        "version": 1,
        "content_hash": "sha256:64cf27fa56cfaa40adeb37bd39a1d46ec47331e0f157c1210cc6bde3020b6d3a"
      },
      "what_changed": "Documented encoder-decoder modeling of discrete image tokens and released a broad compositional-prompt evaluation resource to characterize scaling, content fidelity and failure modes in text-to-image synthesis.",
      "scope": "Documented encoder-decoder modeling of discrete image tokens and released a broad compositional-prompt evaluation resource to characterize scaling, content fidelity and failure modes in text-to-image synthesis. ViT-VQGAN and sequence-to-sequence modeling are inherited. Acquire integrated research/evaluation resource, not an invention for every model scale. Prompt success and benchmark scores do not imply complete visual world knowledge or dependable text rendering.",
      "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:89003a7c-e5bf-4cb1-aa11-c3cebce4d20c",
        "version": 1,
        "content_hash": "sha256:64cf27fa56cfaa40adeb37bd39a1d46ec47331e0f157c1210cc6bde3020b6d3a"
      },
      "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": "Jiahui Yu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yuanzhong Xu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jing Yu Koh",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Thang Luong",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Gunjan Baid",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zirui Wang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Vijay Vasudevan",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Alexander Ku",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yinfei Yang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Burcu Karagol Ayan",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ben Hutchinson",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Wei Han",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zarana Parekh",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Xin Li",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Han Zhang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jason Baldridge",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yonghui Wu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
            "url": "https://arxiv.org/abs/2206.10789v1"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Yu et al.: Parti autoregressive image synthesis and compositional prompt resource — author/institutional project",
            "url": "https://parti.research.google/"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "ViT-VQGAN and sequence-to-sequence modeling are inherited. Acquire integrated research/evaluation resource, not an invention for every model scale. Prompt success and benchmark scores do not imply complete visual world knowledge or dependable text rendering.",
        "domain": "Text-to-image modeling and evaluation resources"
      },
      "sources": [
        {
          "citation": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
          "url": "https://arxiv.org/abs/2206.10789v1"
        },
        {
          "citation": "Yu et al.: Parti autoregressive image synthesis and compositional prompt resource — author/institutional project",
          "url": "https://parti.research.google/"
        }
      ],
      "statement": "# Yu et al.: Parti autoregressive image synthesis and compositional prompt resource\n\nDocumented encoder-decoder modeling of discrete image tokens and released a broad compositional-prompt evaluation resource to characterize scaling, content fidelity and failure modes in text-to-image synthesis.\n\n## Scientific scope\n\nViT-VQGAN and sequence-to-sequence modeling are inherited. Acquire integrated research/evaluation resource, not an invention for every model scale. Prompt success and benchmark scores do not imply complete visual world knowledge or dependable text rendering.\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\nJiahui Yu; Yuanzhong Xu; Jing Yu Koh; Thang Luong; Gunjan Baid; Zirui Wang; Vijay Vasudevan; Alexander Ku; Yinfei Yang; Burcu Karagol Ayan; Ben Hutchinson; Wei Han; Zarana Parekh; Xin Li; Han Zhang; Jason Baldridge; Yonghui Wu\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 Autoregressive Models for Content-Rich Text-to-Image Generation](https://arxiv.org/abs/2206.10789v1)\n- [Yu et al.: Parti autoregressive image synthesis and compositional prompt resource — author/institutional project](https://parti.research.google/)\n",
      "summary": "Documented encoder-decoder modeling of discrete image tokens and released a broad compositional-prompt evaluation resource to characterize scaling, content fidelity and failure modes in text-to-image synthesis.",
      "title": "Yu et al.: Parti autoregressive image synthesis and compositional prompt resource"
    },
    "record_id": "urn:uuid:89003a7c-e5bf-4cb1-aa11-c3cebce4d20c",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:89003a7c-e5bf-4cb1-aa11-c3cebce4d20c",
      "version": 1,
      "content_hash": "sha256:64cf27fa56cfaa40adeb37bd39a1d46ec47331e0f157c1210cc6bde3020b6d3a"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:f782f90d3ddf05f101b7d63e3062f8cb32db6d7aa70249d1146c3d84ab9f4506"
  },
  "target": {
    "record_id": "urn:uuid:89003a7c-e5bf-4cb1-aa11-c3cebce4d20c",
    "version": 1,
    "content_hash": "sha256:64cf27fa56cfaa40adeb37bd39a1d46ec47331e0f157c1210cc6bde3020b6d3a"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "yu-et-al-parti-compositional-resource-2022",
    "entry_id": "yu-et-al-parti-compositional-resource-2022",
    "revision": 1,
    "title": "Yu et al.: Parti autoregressive image synthesis and compositional prompt resource",
    "context": "Text-to-image modeling and evaluation resources",
    "track": "Human-designed research method or resource",
    "band": "B",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-16",
    "evidence_cutoff": "2026-10-16",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Documented encoder-decoder modeling of discrete image tokens and released a broad compositional-prompt evaluation resource to characterize scaling, content fidelity and failure modes in text-to-image synthesis.",
    "scope": "Documented encoder-decoder modeling of discrete image tokens and released a broad compositional-prompt evaluation resource to characterize scaling, content fidelity and failure modes in text-to-image synthesis. ViT-VQGAN and sequence-to-sequence modeling are inherited. Acquire integrated research/evaluation resource, not an invention for every model scale. Prompt success and benchmark scores do not imply complete visual world knowledge or dependable text rendering.",
    "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. ViT-VQGAN and sequence-to-sequence modeling are inherited. Acquire integrated research/evaluation resource, not an invention for every model scale. Prompt success and benchmark scores do not imply complete visual world knowledge or dependable text rendering.",
    "references": [
      {
        "title": "Scaling Autoregressive Models for Content-Rich Text-to-Image Generation",
        "url": "https://arxiv.org/abs/2206.10789v1",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      },
      {
        "title": "Yu et al.: Parti autoregressive image synthesis and compositional prompt resource — author/institutional project",
        "url": "https://parti.research.google/",
        "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:89003a7c-e5bf-4cb1-aa11-c3cebce4d20c",
      "version": 1,
      "content_hash": "sha256:64cf27fa56cfaa40adeb37bd39a1d46ec47331e0f157c1210cc6bde3020b6d3a"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "75000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}