{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IIUB3RSLSJURSSBPOPTOFRPAX3","short_pith_number":"pith:IIUB3RSL","schema_version":"1.0","canonical_sha256":"42281dc64b926919482f73e6e2c5e0bec46db4d754dd9ad40be8e227fd552c4b","source":{"kind":"arxiv","id":"2312.03816","version":3},"attestation_state":"computed","paper":{"title":"AVID: Any-Length Video Inpainting with Diffusion Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bichen Wu, Dimitris Metaxas, Licheng Yu, Luxin Zhang, Peter Vajda, Xiaoyan Wang, Yaqiao Luo, Yinan Zhao, Zhixing Zhang","submitted_at":"2023-12-06T18:56:14Z","abstract_excerpt":"Recent advances in diffusion models have successfully enabled text-guided image inpainting. While it seems straightforward to extend such editing capability into the video domain, there have been fewer works regarding text-guided video inpainting. Given a video, a masked region at its initial frame, and an editing prompt, it requires a model to do infilling at each frame following the editing guidance while keeping the out-of-mask region intact. There are three main challenges in text-guided video inpainting: ($i$) temporal consistency of the edited video, ($ii$) supporting different inpaintin"},"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":"2312.03816","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T18:56:14Z","cross_cats_sorted":[],"title_canon_sha256":"58b7d59ca7c0a6bf373731841de58e09446023f42a18077480f726772a3dc0c4","abstract_canon_sha256":"23607f3866cb5d03a0ba82e1c1d68815ee1f75d53e06e80c68329914cb8b9bef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:23.085875Z","signature_b64":"+l+JBJlzu0zVEp92BDYVFlS7c5wK1WLQqCO6gAwbe2+1teN84JFFBvrDGwPX3A0HCjshGFDKEqMzLctvalAeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42281dc64b926919482f73e6e2c5e0bec46db4d754dd9ad40be8e227fd552c4b","last_reissued_at":"2026-07-05T08:02:23.085290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:23.085290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVID: Any-Length Video Inpainting with Diffusion Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bichen Wu, Dimitris Metaxas, Licheng Yu, Luxin Zhang, Peter Vajda, Xiaoyan Wang, Yaqiao Luo, Yinan Zhao, Zhixing Zhang","submitted_at":"2023-12-06T18:56:14Z","abstract_excerpt":"Recent advances in diffusion models have successfully enabled text-guided image inpainting. While it seems straightforward to extend such editing capability into the video domain, there have been fewer works regarding text-guided video inpainting. Given a video, a masked region at its initial frame, and an editing prompt, it requires a model to do infilling at each frame following the editing guidance while keeping the out-of-mask region intact. There are three main challenges in text-guided video inpainting: ($i$) temporal consistency of the edited video, ($ii$) supporting different inpaintin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03816","kind":"arxiv","version":3},"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/2312.03816/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":"2312.03816","created_at":"2026-07-05T08:02:23.085374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03816v3","created_at":"2026-07-05T08:02:23.085374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03816","created_at":"2026-07-05T08:02:23.085374+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIUB3RSLSJUR","created_at":"2026-07-05T08:02:23.085374+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIUB3RSLSJURSSBP","created_at":"2026-07-05T08:02:23.085374+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIUB3RSL","created_at":"2026-07-05T08:02:23.085374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17543","citing_title":"HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08762","citing_title":"Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13906","citing_title":"Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIUB3RSLSJURSSBPOPTOFRPAX3","json":"https://pith.science/pith/IIUB3RSLSJURSSBPOPTOFRPAX3.json","graph_json":"https://pith.science/api/pith-number/IIUB3RSLSJURSSBPOPTOFRPAX3/graph.json","events_json":"https://pith.science/api/pith-number/IIUB3RSLSJURSSBPOPTOFRPAX3/events.json","paper":"https://pith.science/paper/IIUB3RSL"},"agent_actions":{"view_html":"https://pith.science/pith/IIUB3RSLSJURSSBPOPTOFRPAX3","download_json":"https://pith.science/pith/IIUB3RSLSJURSSBPOPTOFRPAX3.json","view_paper":"https://pith.science/paper/IIUB3RSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03816&json=true","fetch_graph":"https://pith.science/api/pith-number/IIUB3RSLSJURSSBPOPTOFRPAX3/graph.json","fetch_events":"https://pith.science/api/pith-number/IIUB3RSLSJURSSBPOPTOFRPAX3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIUB3RSLSJURSSBPOPTOFRPAX3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIUB3RSLSJURSSBPOPTOFRPAX3/action/storage_attestation","attest_author":"https://pith.science/pith/IIUB3RSLSJURSSBPOPTOFRPAX3/action/author_attestation","sign_citation":"https://pith.science/pith/IIUB3RSLSJURSSBPOPTOFRPAX3/action/citation_signature","submit_replication":"https://pith.science/pith/IIUB3RSLSJURSSBPOPTOFRPAX3/action/replication_record"}},"created_at":"2026-07-05T08:02:23.085374+00:00","updated_at":"2026-07-05T08:02:23.085374+00:00"}