{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W262CC7KBFRQDEIH4NQTZK7JAI","short_pith_number":"pith:W262CC7K","schema_version":"1.0","canonical_sha256":"b6bda10bea0963019107e3613cabe9021ae3f8dd9e74d8daf1fbda9d22cccc08","source":{"kind":"arxiv","id":"2411.17592","version":3},"attestation_state":"computed","paper":{"title":"VideoDirector: Precise Video Editing via Text-to-Video Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Xu, Longguang Wang, Qibin Hu, Yukun Wang, Yulan Guo, Zhiyuan Ma","submitted_at":"2024-11-26T16:56:53Z","abstract_excerpt":"Despite the typical inversion-then-editing paradigm using text-to-image (T2I) models has demonstrated promising results, directly extending it to text-to-video (T2V) models still suffers severe artifacts such as color flickering and content distortion. Consequently, current video editing methods primarily rely on T2I models, which inherently lack temporal-coherence generative ability, often resulting in inferior editing results. In this paper, we attribute the failure of the typical editing paradigm to: 1) Tightly Spatial-temporal Coupling. The vanilla pivotal-based inversion strategy struggle"},"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":"2411.17592","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T16:56:53Z","cross_cats_sorted":[],"title_canon_sha256":"0fb1902e95028004b75f61382daebffafb8008bc2af05fe95a2bfb71ed91ebf2","abstract_canon_sha256":"dee8c669232e2cbf870d057617582ba418abde3237c7078b1b3b5b67dca6daf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:12.821467Z","signature_b64":"UvRcRl4jLfHTYbLKs0dqvi30l4B65of8dZvM6VF1y/9v6Hblen+S4oc6ULELxn5gLlLFlv5+gT2Bk2eDOb/IAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6bda10bea0963019107e3613cabe9021ae3f8dd9e74d8daf1fbda9d22cccc08","last_reissued_at":"2026-07-05T10:34:12.820652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:12.820652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoDirector: Precise Video Editing via Text-to-Video Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kai Xu, Longguang Wang, Qibin Hu, Yukun Wang, Yulan Guo, Zhiyuan Ma","submitted_at":"2024-11-26T16:56:53Z","abstract_excerpt":"Despite the typical inversion-then-editing paradigm using text-to-image (T2I) models has demonstrated promising results, directly extending it to text-to-video (T2V) models still suffers severe artifacts such as color flickering and content distortion. Consequently, current video editing methods primarily rely on T2I models, which inherently lack temporal-coherence generative ability, often resulting in inferior editing results. In this paper, we attribute the failure of the typical editing paradigm to: 1) Tightly Spatial-temporal Coupling. The vanilla pivotal-based inversion strategy struggle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17592","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/2411.17592/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":"2411.17592","created_at":"2026-07-05T10:34:12.820761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17592v3","created_at":"2026-07-05T10:34:12.820761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17592","created_at":"2026-07-05T10:34:12.820761+00:00"},{"alias_kind":"pith_short_12","alias_value":"W262CC7KBFRQ","created_at":"2026-07-05T10:34:12.820761+00:00"},{"alias_kind":"pith_short_16","alias_value":"W262CC7KBFRQDEIH","created_at":"2026-07-05T10:34:12.820761+00:00"},{"alias_kind":"pith_short_8","alias_value":"W262CC7K","created_at":"2026-07-05T10:34:12.820761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":263,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W262CC7KBFRQDEIH4NQTZK7JAI","json":"https://pith.science/pith/W262CC7KBFRQDEIH4NQTZK7JAI.json","graph_json":"https://pith.science/api/pith-number/W262CC7KBFRQDEIH4NQTZK7JAI/graph.json","events_json":"https://pith.science/api/pith-number/W262CC7KBFRQDEIH4NQTZK7JAI/events.json","paper":"https://pith.science/paper/W262CC7K"},"agent_actions":{"view_html":"https://pith.science/pith/W262CC7KBFRQDEIH4NQTZK7JAI","download_json":"https://pith.science/pith/W262CC7KBFRQDEIH4NQTZK7JAI.json","view_paper":"https://pith.science/paper/W262CC7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17592&json=true","fetch_graph":"https://pith.science/api/pith-number/W262CC7KBFRQDEIH4NQTZK7JAI/graph.json","fetch_events":"https://pith.science/api/pith-number/W262CC7KBFRQDEIH4NQTZK7JAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W262CC7KBFRQDEIH4NQTZK7JAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W262CC7KBFRQDEIH4NQTZK7JAI/action/storage_attestation","attest_author":"https://pith.science/pith/W262CC7KBFRQDEIH4NQTZK7JAI/action/author_attestation","sign_citation":"https://pith.science/pith/W262CC7KBFRQDEIH4NQTZK7JAI/action/citation_signature","submit_replication":"https://pith.science/pith/W262CC7KBFRQDEIH4NQTZK7JAI/action/replication_record"}},"created_at":"2026-07-05T10:34:12.820761+00:00","updated_at":"2026-07-05T10:34:12.820761+00:00"}