{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F5D7W5XMDAQCBSQDH65ZBOG4QQ","short_pith_number":"pith:F5D7W5XM","schema_version":"1.0","canonical_sha256":"2f47fb76ec182020ca033fbb90b8dc841937745a698b5328ddb555429bb39b77","source":{"kind":"arxiv","id":"2303.12688","version":1},"attestation_state":"computed","paper":{"title":"Pix2Video: Video Editing using Image Diffusion","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Hao Paul Huang, Duygu Ceylan, Niloy J. Mitra","submitted_at":"2023-03-22T16:36:10Z","abstract_excerpt":"Image diffusion models, trained on massive image collections, have emerged as the most versatile image generator model in terms of quality and diversity. They support inverting real images and conditional (e.g., text) generation, making them attractive for high-quality image editing applications. We investigate how to use such pre-trained image models for text-guided video editing. The critical challenge is to achieve the target edits while still preserving the content of the source video. Our method works in two simple steps: first, we use a pre-trained structure-guided (e.g., depth) image di"},"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":"2303.12688","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T16:36:10Z","cross_cats_sorted":[],"title_canon_sha256":"5b609832f10abbcca3b265ea14ec4157b8a783000ee1e2f98529075220601a4e","abstract_canon_sha256":"89703cbd6311f522bd6be2efc7d83b2b72848bcf2fdb6c2405db3dc25408451e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:43.979520Z","signature_b64":"LQykNFz9QnKdz1aKEV/eAPHYlK/1FuNyRU350TkB9gC3oNR5nTo5cgYK6NUrZuD2gRx38tNNhoix3FC5qQ3YCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f47fb76ec182020ca033fbb90b8dc841937745a698b5328ddb555429bb39b77","last_reissued_at":"2026-07-05T05:53:43.979114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:43.979114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pix2Video: Video Editing using Image Diffusion","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Hao Paul Huang, Duygu Ceylan, Niloy J. Mitra","submitted_at":"2023-03-22T16:36:10Z","abstract_excerpt":"Image diffusion models, trained on massive image collections, have emerged as the most versatile image generator model in terms of quality and diversity. They support inverting real images and conditional (e.g., text) generation, making them attractive for high-quality image editing applications. We investigate how to use such pre-trained image models for text-guided video editing. The critical challenge is to achieve the target edits while still preserving the content of the source video. Our method works in two simple steps: first, we use a pre-trained structure-guided (e.g., depth) image di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12688","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/2303.12688/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":"2303.12688","created_at":"2026-07-05T05:53:43.979170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12688v1","created_at":"2026-07-05T05:53:43.979170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12688","created_at":"2026-07-05T05:53:43.979170+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5D7W5XMDAQC","created_at":"2026-07-05T05:53:43.979170+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5D7W5XMDAQCBSQD","created_at":"2026-07-05T05:53:43.979170+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5D7W5XM","created_at":"2026-07-05T05:53:43.979170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07568","citing_title":"A Systematic Study of Behavioral Cloning for Scientific Data Annotation","ref_index":260,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":250,"is_internal_anchor":false},{"citing_arxiv_id":"2307.10373","citing_title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2307.04725","citing_title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5D7W5XMDAQCBSQDH65ZBOG4QQ","json":"https://pith.science/pith/F5D7W5XMDAQCBSQDH65ZBOG4QQ.json","graph_json":"https://pith.science/api/pith-number/F5D7W5XMDAQCBSQDH65ZBOG4QQ/graph.json","events_json":"https://pith.science/api/pith-number/F5D7W5XMDAQCBSQDH65ZBOG4QQ/events.json","paper":"https://pith.science/paper/F5D7W5XM"},"agent_actions":{"view_html":"https://pith.science/pith/F5D7W5XMDAQCBSQDH65ZBOG4QQ","download_json":"https://pith.science/pith/F5D7W5XMDAQCBSQDH65ZBOG4QQ.json","view_paper":"https://pith.science/paper/F5D7W5XM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12688&json=true","fetch_graph":"https://pith.science/api/pith-number/F5D7W5XMDAQCBSQDH65ZBOG4QQ/graph.json","fetch_events":"https://pith.science/api/pith-number/F5D7W5XMDAQCBSQDH65ZBOG4QQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5D7W5XMDAQCBSQDH65ZBOG4QQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5D7W5XMDAQCBSQDH65ZBOG4QQ/action/storage_attestation","attest_author":"https://pith.science/pith/F5D7W5XMDAQCBSQDH65ZBOG4QQ/action/author_attestation","sign_citation":"https://pith.science/pith/F5D7W5XMDAQCBSQDH65ZBOG4QQ/action/citation_signature","submit_replication":"https://pith.science/pith/F5D7W5XMDAQCBSQDH65ZBOG4QQ/action/replication_record"}},"created_at":"2026-07-05T05:53:43.979170+00:00","updated_at":"2026-07-05T05:53:43.979170+00:00"}