{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "yang-et-al-cogvideox-expert-video-transformer-2024",
    "title": "Yang et al.: CogVideoX causal video compression and expert transformer",
    "summary": "Integrated spatial-temporal causal video compression, text/video expert-adaptive normalization, full spatiotemporal attention and progressive-duration/resolution training into an openly released video diffusion system.",
    "boundary": "Diffusion, DiT, VAE compression and text conditioning have earlier sources; this record covers their video-specific expert/compression/training integration. Early released resolution and duration differ from later versions; video examples and comparative quality are source-reported, not a physical world model.",
    "area": "Text-to-video generative modeling",
    "topic": "Artificial intelligence",
    "year": 2024,
    "lane": "HUMAN",
    "result": "EMPIRICAL",
    "package_id": "yang-et-al-cogvideox-expert-video-transformer-2024",
    "target": {
      "record_id": "urn:uuid:a07622a4-9714-4bcd-a68e-ed719c8cc5d8",
      "version": 1,
      "content_hash": "sha256:1ff88db79a4f000ba90891d35323bcd760e3ceaeb5369236308cfaa961fcff0a"
    },
    "humans": [
      "Zhuoyi Yang",
      "Jiayan Teng",
      "Wendi Zheng",
      "Ming Ding",
      "Shiyu Huang",
      "Jiazheng Xu",
      "Yuanming Yang",
      "Wenyi Hong",
      "Xiaohan Zhang",
      "Guanyu Feng",
      "Da Yin",
      "Xiaotao Gu",
      "Yuxuan Zhang",
      "Weihan Wang",
      "Yean Cheng",
      "Ting Liu",
      "Bin Xu",
      "Yuxiao Dong",
      "Jie Tang"
    ],
    "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-2408-06072v1",
        "title": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
        "url": "https://arxiv.org/abs/2408.06072v1"
      },
      {
        "id": "cur20261015-support-yang-et-al-cogvideox-expert-video-transformer-2024",
        "title": "Yang et al.: CogVideoX causal video compression and expert transformer — official research provenance",
        "url": "https://github.com/THUDM/CogVideo"
      }
    ],
    "points": "70000",
    "published_grade": {
      "id": "yang-et-al-cogvideox-expert-video-transformer-2024",
      "entry_id": "yang-et-al-cogvideox-expert-video-transformer-2024",
      "band": "B",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:a07622a4-9714-4bcd-a68e-ed719c8cc5d8",
        "version": 1,
        "content_hash": "sha256:1ff88db79a4f000ba90891d35323bcd760e3ceaeb5369236308cfaa961fcff0a"
      },
      "what_changed": "Integrated spatial-temporal causal video compression, text/video expert-adaptive normalization, full spatiotemporal attention and progressive-duration/resolution training into an openly released video diffusion system.",
      "scope": "Integrated spatial-temporal causal video compression, text/video expert-adaptive normalization, full spatiotemporal attention and progressive-duration/resolution training into an openly released video diffusion system. Diffusion, DiT, VAE compression and text conditioning have earlier sources; this record covers their video-specific expert/compression/training integration. Early released resolution and duration differ from later versions; video examples and comparative quality are source-reported, not a physical world model.",
      "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:a07622a4-9714-4bcd-a68e-ed719c8cc5d8",
        "version": 1,
        "content_hash": "sha256:1ff88db79a4f000ba90891d35323bcd760e3ceaeb5369236308cfaa961fcff0a"
      },
      "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": "Zhuoyi Yang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jiayan Teng",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Wendi Zheng",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ming Ding",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Shiyu Huang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jiazheng Xu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yuanming Yang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Wenyi Hong",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Xiaohan Zhang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Guanyu Feng",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Da Yin",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Xiaotao Gu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yuxuan Zhang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Weihan Wang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yean Cheng",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ting Liu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Bin Xu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yuxiao Dong",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jie Tang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
            "url": "https://arxiv.org/abs/2408.06072v1"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Yang et al.: CogVideoX causal video compression and expert transformer — official research provenance",
            "url": "https://github.com/THUDM/CogVideo"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Diffusion, DiT, VAE compression and text conditioning have earlier sources; this record covers their video-specific expert/compression/training integration. Early released resolution and duration differ from later versions; video examples and comparative quality are source-reported, not a physical world model.",
        "domain": "Text-to-video generative modeling"
      },
      "sources": [
        {
          "citation": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
          "url": "https://arxiv.org/abs/2408.06072v1"
        },
        {
          "citation": "Yang et al.: CogVideoX causal video compression and expert transformer — official research provenance",
          "url": "https://github.com/THUDM/CogVideo"
        }
      ],
      "statement": "# Yang et al.: CogVideoX causal video compression and expert transformer\n\nIntegrated spatial-temporal causal video compression, text/video expert-adaptive normalization, full spatiotemporal attention and progressive-duration/resolution training into an openly released video diffusion system.\n\n## Scientific scope\n\nDiffusion, DiT, VAE compression and text conditioning have earlier sources; this record covers their video-specific expert/compression/training integration. Early released resolution and duration differ from later versions; video examples and comparative quality are source-reported, not a physical world model.\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\nZhuoyi Yang; Jiayan Teng; Wendi Zheng; Ming Ding; Shiyu Huang; Jiazheng Xu; Yuanming Yang; Wenyi Hong; Xiaohan Zhang; Guanyu Feng; Da Yin; Xiaotao Gu; Yuxuan Zhang; Weihan Wang; Yean Cheng; Ting Liu; Bin Xu; Yuxiao Dong; Jie Tang\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- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://arxiv.org/abs/2408.06072v1)\n- [Yang et al.: CogVideoX causal video compression and expert transformer — official research provenance](https://github.com/THUDM/CogVideo)\n",
      "summary": "Integrated spatial-temporal causal video compression, text/video expert-adaptive normalization, full spatiotemporal attention and progressive-duration/resolution training into an openly released video diffusion system.",
      "title": "Yang et al.: CogVideoX causal video compression and expert transformer"
    },
    "record_id": "urn:uuid:a07622a4-9714-4bcd-a68e-ed719c8cc5d8",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:a07622a4-9714-4bcd-a68e-ed719c8cc5d8",
      "version": 1,
      "content_hash": "sha256:1ff88db79a4f000ba90891d35323bcd760e3ceaeb5369236308cfaa961fcff0a"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:9df949f805b63ccff206e0ec140cb733c9cd17d2b394d0ec454515ecbffb4df3"
  },
  "target": {
    "record_id": "urn:uuid:a07622a4-9714-4bcd-a68e-ed719c8cc5d8",
    "version": 1,
    "content_hash": "sha256:1ff88db79a4f000ba90891d35323bcd760e3ceaeb5369236308cfaa961fcff0a"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "yang-et-al-cogvideox-expert-video-transformer-2024",
    "entry_id": "yang-et-al-cogvideox-expert-video-transformer-2024",
    "revision": 1,
    "title": "Yang et al.: CogVideoX causal video compression and expert transformer",
    "context": "Text-to-video generative modeling",
    "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": "Integrated spatial-temporal causal video compression, text/video expert-adaptive normalization, full spatiotemporal attention and progressive-duration/resolution training into an openly released video diffusion system.",
    "scope": "Integrated spatial-temporal causal video compression, text/video expert-adaptive normalization, full spatiotemporal attention and progressive-duration/resolution training into an openly released video diffusion system. Diffusion, DiT, VAE compression and text conditioning have earlier sources; this record covers their video-specific expert/compression/training integration. Early released resolution and duration differ from later versions; video examples and comparative quality are source-reported, not a physical world model.",
    "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. Diffusion, DiT, VAE compression and text conditioning have earlier sources; this record covers their video-specific expert/compression/training integration. Early released resolution and duration differ from later versions; video examples and comparative quality are source-reported, not a physical world model.",
    "references": [
      {
        "title": "CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer",
        "url": "https://arxiv.org/abs/2408.06072v1",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      },
      {
        "title": "Yang et al.: CogVideoX causal video compression and expert transformer — official research provenance",
        "url": "https://github.com/THUDM/CogVideo",
        "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:a07622a4-9714-4bcd-a68e-ed719c8cc5d8",
      "version": 1,
      "content_hash": "sha256:1ff88db79a4f000ba90891d35323bcd760e3ceaeb5369236308cfaa961fcff0a"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "70000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}