{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JDL5CSZBOUON2NFCW6MRU3GABP","short_pith_number":"pith:JDL5CSZB","schema_version":"1.0","canonical_sha256":"48d7d14b21751cdd34a2b7991a6cc00beb5013a66d0e51086053bdbd49545188","source":{"kind":"arxiv","id":"2510.08555","version":2},"attestation_state":"computed","paper":{"title":"VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kun Gai, Minghong Cai, Pengfei Wan, Qiulin Wang, Quande Liu, Weicai Ye, Wenze Liu, Xiangyu Yue, Xintao Wang, Zongli Ye","submitted_at":"2025-10-09T17:58:59Z","abstract_excerpt":"Existing controllable video generation methods are typically designed for rigid, task-specific settings, such as first-frame image-to-video, inpainting, or interpolation, treating spatio-temporal control as a set of isolated problems. We formalize a unified task, arbitrary spatio-temporal video completion, where a model generates a coherent video from user-specified patches placed at any spatial location and timestamp. However, realizing such a unified framework within modern latent video diffusion models is non-trivial: causal video VAEs compress multiple frames into a single latent slot, mak"},"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":"2510.08555","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-09T17:58:59Z","cross_cats_sorted":[],"title_canon_sha256":"1b3bb82b382710c74512d91584b7b57bf6e73b2cc605363dabbab5e73b562ec6","abstract_canon_sha256":"505c6dcb5f2ff856ea86d97d350c407fa6052dc4dafa02702df282064088b445"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:43.512376Z","signature_b64":"kiL/fweJ0LqlbI++/UtH/1W16jQnAYumo76fldgwnjQ+fPZ69riZi0ex5JP5UcxuhWz3Nw0lbYv9kUVab+NtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48d7d14b21751cdd34a2b7991a6cc00beb5013a66d0e51086053bdbd49545188","last_reissued_at":"2026-05-28T02:04:43.511849Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:43.511849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kun Gai, Minghong Cai, Pengfei Wan, Qiulin Wang, Quande Liu, Weicai Ye, Wenze Liu, Xiangyu Yue, Xintao Wang, Zongli Ye","submitted_at":"2025-10-09T17:58:59Z","abstract_excerpt":"Existing controllable video generation methods are typically designed for rigid, task-specific settings, such as first-frame image-to-video, inpainting, or interpolation, treating spatio-temporal control as a set of isolated problems. We formalize a unified task, arbitrary spatio-temporal video completion, where a model generates a coherent video from user-specified patches placed at any spatial location and timestamp. However, realizing such a unified framework within modern latent video diffusion models is non-trivial: causal video VAEs compress multiple frames into a single latent slot, mak"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.08555","kind":"arxiv","version":2},"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/2510.08555/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":"2510.08555","created_at":"2026-05-28T02:04:43.511911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.08555v2","created_at":"2026-05-28T02:04:43.511911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08555","created_at":"2026-05-28T02:04:43.511911+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDL5CSZBOUON","created_at":"2026-05-28T02:04:43.511911+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDL5CSZBOUON2NFC","created_at":"2026-05-28T02:04:43.511911+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDL5CSZB","created_at":"2026-05-28T02:04:43.511911+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/JDL5CSZBOUON2NFCW6MRU3GABP","json":"https://pith.science/pith/JDL5CSZBOUON2NFCW6MRU3GABP.json","graph_json":"https://pith.science/api/pith-number/JDL5CSZBOUON2NFCW6MRU3GABP/graph.json","events_json":"https://pith.science/api/pith-number/JDL5CSZBOUON2NFCW6MRU3GABP/events.json","paper":"https://pith.science/paper/JDL5CSZB"},"agent_actions":{"view_html":"https://pith.science/pith/JDL5CSZBOUON2NFCW6MRU3GABP","download_json":"https://pith.science/pith/JDL5CSZBOUON2NFCW6MRU3GABP.json","view_paper":"https://pith.science/paper/JDL5CSZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.08555&json=true","fetch_graph":"https://pith.science/api/pith-number/JDL5CSZBOUON2NFCW6MRU3GABP/graph.json","fetch_events":"https://pith.science/api/pith-number/JDL5CSZBOUON2NFCW6MRU3GABP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDL5CSZBOUON2NFCW6MRU3GABP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDL5CSZBOUON2NFCW6MRU3GABP/action/storage_attestation","attest_author":"https://pith.science/pith/JDL5CSZBOUON2NFCW6MRU3GABP/action/author_attestation","sign_citation":"https://pith.science/pith/JDL5CSZBOUON2NFCW6MRU3GABP/action/citation_signature","submit_replication":"https://pith.science/pith/JDL5CSZBOUON2NFCW6MRU3GABP/action/replication_record"}},"created_at":"2026-05-28T02:04:43.511911+00:00","updated_at":"2026-05-28T02:04:43.511911+00:00"}