{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7IKT5FY5RVE5MLQ2WLTDND7PFO","short_pith_number":"pith:7IKT5FY5","schema_version":"1.0","canonical_sha256":"fa153e971d8d49d62e1ab2e6368fef2bb598b8e95b35081594283f5ce943a2f3","source":{"kind":"arxiv","id":"2607.27380","version":1},"attestation_state":"computed","paper":{"title":"VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Boxue Yang, Chunmei Qing, Dongzhi Jiang, Feng Zhao, Haodong Li, Haoyu Wu, Jialv Zou, Jinjing Zhao, Ji Xie, Juanxi Tian, Junyan Ye, Lin Chen, Pheng-Ann Heng, Renye Yan, Ruichuan An, Sipeng He, Tianfei Ren, Wenhao Yan, Xiaotong Li, Xiaoxiao Ma, Xu Huang, Yaxin Luo, Yihang Zou, Yuzhu Wang, Zehui Chen, Zhen Fang, Zhengrong Yue, Ziyu Guo","submitted_at":"2026-07-29T18:38:23Z","abstract_excerpt":"Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be inferred implicitly from a highly compressed text prompt. Existing chain-of-thought approaches introduce intermediate plans or visual states, but these representations are typically non-executable or temporally sparse, limiting their ability to instantiate and control the complete spatiotemporal process. To address this limitation, we introduce VideoCoCo, an agentic dual-engine framework in which executable Blender co"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.27380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T18:38:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"932d3b34cf36194534e136615ab0b6923245c7c3bfedf8a917900730e0257a0e","abstract_canon_sha256":"86fddc28fa9dd50ba8762f9f2d4750fcae2a1449924f9010cc0be95fe00efb2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa153e971d8d49d62e1ab2e6368fef2bb598b8e95b35081594283f5ce943a2f3","last_reissued_at":"2026-07-31T00:10:50.171748Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:10:50.171748Z"},"graph_snapshot":{"paper":{"title":"VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Boxue Yang, Chunmei Qing, Dongzhi Jiang, Feng Zhao, Haodong Li, Haoyu Wu, Jialv Zou, Jinjing Zhao, Ji Xie, Juanxi Tian, Junyan Ye, Lin Chen, Pheng-Ann Heng, Renye Yan, Ruichuan An, Sipeng He, Tianfei Ren, Wenhao Yan, Xiaotong Li, Xiaoxiao Ma, Xu Huang, Yaxin Luo, Yihang Zou, Yuzhu Wang, Zehui Chen, Zhen Fang, Zhengrong Yue, Ziyu Guo","submitted_at":"2026-07-29T18:38:23Z","abstract_excerpt":"Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be inferred implicitly from a highly compressed text prompt. Existing chain-of-thought approaches introduce intermediate plans or visual states, but these representations are typically non-executable or temporally sparse, limiting their ability to instantiate and control the complete spatiotemporal process. To address this limitation, we introduce VideoCoCo, an agentic dual-engine framework in which executable Blender co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27380","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.27380/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.27380","created_at":"2026-07-31T00:10:50.174152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27380v1","created_at":"2026-07-31T00:10:50.174152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27380","created_at":"2026-07-31T00:10:50.174152+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IKT5FY5RVE5","created_at":"2026-07-31T00:10:50.174152+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IKT5FY5RVE5MLQ2","created_at":"2026-07-31T00:10:50.174152+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IKT5FY5","created_at":"2026-07-31T00:10:50.174152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IKT5FY5RVE5MLQ2WLTDND7PFO","json":"https://pith.science/pith/7IKT5FY5RVE5MLQ2WLTDND7PFO.json","graph_json":"https://pith.science/api/pith-number/7IKT5FY5RVE5MLQ2WLTDND7PFO/graph.json","events_json":"https://pith.science/api/pith-number/7IKT5FY5RVE5MLQ2WLTDND7PFO/events.json","paper":"https://pith.science/paper/7IKT5FY5"},"agent_actions":{"view_html":"https://pith.science/pith/7IKT5FY5RVE5MLQ2WLTDND7PFO","download_json":"https://pith.science/pith/7IKT5FY5RVE5MLQ2WLTDND7PFO.json","view_paper":"https://pith.science/paper/7IKT5FY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27380&json=true","fetch_graph":"https://pith.science/api/pith-number/7IKT5FY5RVE5MLQ2WLTDND7PFO/graph.json","fetch_events":"https://pith.science/api/pith-number/7IKT5FY5RVE5MLQ2WLTDND7PFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IKT5FY5RVE5MLQ2WLTDND7PFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IKT5FY5RVE5MLQ2WLTDND7PFO/action/storage_attestation","attest_author":"https://pith.science/pith/7IKT5FY5RVE5MLQ2WLTDND7PFO/action/author_attestation","sign_citation":"https://pith.science/pith/7IKT5FY5RVE5MLQ2WLTDND7PFO/action/citation_signature","submit_replication":"https://pith.science/pith/7IKT5FY5RVE5MLQ2WLTDND7PFO/action/replication_record"}},"created_at":"2026-07-31T00:10:50.174152+00:00","updated_at":"2026-07-31T00:10:50.174152+00:00"}