{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QA6PZHYOA2DWKEGJOGXRZSOBGH","short_pith_number":"pith:QA6PZHYO","schema_version":"1.0","canonical_sha256":"803cfc9f0e06876510c971af1cc9c131fac8eddd48eb6376b1abca294ea086d7","source":{"kind":"arxiv","id":"2305.12328","version":2},"attestation_state":"computed","paper":{"title":"InstructVid2Vid: Controllable Video Editing with Natural Language Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bosheng Qin, Juncheng Li, Siliang Tang, Tat-Seng Chua, Yueting Zhuang","submitted_at":"2023-05-21T03:28:13Z","abstract_excerpt":"We introduce InstructVid2Vid, an end-to-end diffusion-based methodology for video editing guided by human language instructions. Our approach empowers video manipulation guided by natural language directives, eliminating the need for per-example fine-tuning or inversion. The proposed InstructVid2Vid model modifies a pretrained image generation model, Stable Diffusion, to generate a time-dependent sequence of video frames. By harnessing the collective intelligence of disparate models, we engineer a training dataset rich in video-instruction triplets, which is a more cost-efficient alternative t"},"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":"2305.12328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-21T03:28:13Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"0e0199a506409d3f2f9f586aa92368cdf8b04403a7b3737494078dcbfd6c90b8","abstract_canon_sha256":"95d509ec61cc0916199e7581093142a76e29345c3db3155de840ef4778f6fa86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:36.426543Z","signature_b64":"pFqsu3JinAoSMpbWiGU/41BYlDsMSGzGRyPScak89SvlQg1JI3iLJ1nSO2smLhW3VVjKCJh8RcwmjjFdKINBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"803cfc9f0e06876510c971af1cc9c131fac8eddd48eb6376b1abca294ea086d7","last_reissued_at":"2026-07-05T08:24:36.426046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:36.426046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructVid2Vid: Controllable Video Editing with Natural Language Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bosheng Qin, Juncheng Li, Siliang Tang, Tat-Seng Chua, Yueting Zhuang","submitted_at":"2023-05-21T03:28:13Z","abstract_excerpt":"We introduce InstructVid2Vid, an end-to-end diffusion-based methodology for video editing guided by human language instructions. Our approach empowers video manipulation guided by natural language directives, eliminating the need for per-example fine-tuning or inversion. The proposed InstructVid2Vid model modifies a pretrained image generation model, Stable Diffusion, to generate a time-dependent sequence of video frames. By harnessing the collective intelligence of disparate models, we engineer a training dataset rich in video-instruction triplets, which is a more cost-efficient alternative t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12328","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/2305.12328/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":"2305.12328","created_at":"2026-07-05T08:24:36.426107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12328v2","created_at":"2026-07-05T08:24:36.426107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12328","created_at":"2026-07-05T08:24:36.426107+00:00"},{"alias_kind":"pith_short_12","alias_value":"QA6PZHYOA2DW","created_at":"2026-07-05T08:24:36.426107+00:00"},{"alias_kind":"pith_short_16","alias_value":"QA6PZHYOA2DWKEGJ","created_at":"2026-07-05T08:24:36.426107+00:00"},{"alias_kind":"pith_short_8","alias_value":"QA6PZHYO","created_at":"2026-07-05T08:24:36.426107+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15307","citing_title":"Sound Sparks Motion: Audio and Text Tuning for Video Editing","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":190,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QA6PZHYOA2DWKEGJOGXRZSOBGH","json":"https://pith.science/pith/QA6PZHYOA2DWKEGJOGXRZSOBGH.json","graph_json":"https://pith.science/api/pith-number/QA6PZHYOA2DWKEGJOGXRZSOBGH/graph.json","events_json":"https://pith.science/api/pith-number/QA6PZHYOA2DWKEGJOGXRZSOBGH/events.json","paper":"https://pith.science/paper/QA6PZHYO"},"agent_actions":{"view_html":"https://pith.science/pith/QA6PZHYOA2DWKEGJOGXRZSOBGH","download_json":"https://pith.science/pith/QA6PZHYOA2DWKEGJOGXRZSOBGH.json","view_paper":"https://pith.science/paper/QA6PZHYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12328&json=true","fetch_graph":"https://pith.science/api/pith-number/QA6PZHYOA2DWKEGJOGXRZSOBGH/graph.json","fetch_events":"https://pith.science/api/pith-number/QA6PZHYOA2DWKEGJOGXRZSOBGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QA6PZHYOA2DWKEGJOGXRZSOBGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QA6PZHYOA2DWKEGJOGXRZSOBGH/action/storage_attestation","attest_author":"https://pith.science/pith/QA6PZHYOA2DWKEGJOGXRZSOBGH/action/author_attestation","sign_citation":"https://pith.science/pith/QA6PZHYOA2DWKEGJOGXRZSOBGH/action/citation_signature","submit_replication":"https://pith.science/pith/QA6PZHYOA2DWKEGJOGXRZSOBGH/action/replication_record"}},"created_at":"2026-07-05T08:24:36.426107+00:00","updated_at":"2026-07-05T08:24:36.426107+00:00"}