{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QCQGBZDW5GFPBYBE6GHTTCUNA5","short_pith_number":"pith:QCQGBZDW","schema_version":"1.0","canonical_sha256":"80a060e476e98af0e024f18f398a8d075aa058d946ba126c1d47f0f1552a0aad","source":{"kind":"arxiv","id":"2407.14841","version":1},"attestation_state":"computed","paper":{"title":"Text-based Talking Video Editing with Cascaded Conditional Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Han, Chng Eng Siong, Guangcong Wang, Haoyang Li, Heqing Zou","submitted_at":"2024-07-20T10:55:19Z","abstract_excerpt":"Text-based talking-head video editing aims to efficiently insert, delete, and substitute segments of talking videos through a user-friendly text editing approach. It is challenging because of \\textbf{1)} generalizable talking-face representation, \\textbf{2)} seamless audio-visual transitions, and \\textbf{3)} identity-preserved talking faces. Previous works either require minutes of talking-face video training data and expensive test-time optimization for customized talking video editing or directly generate a video sequence without considering in-context information, leading to a poor generali"},"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":"2407.14841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-20T10:55:19Z","cross_cats_sorted":[],"title_canon_sha256":"ce77cb44c946db8a11ba12891c1d1bd6c2fc76814c0459eb2bc864849215ef43","abstract_canon_sha256":"518e826d19bda87bd08eee99715bad10814075a0d6dc7e97715ac9b330bfa4b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:34.862880Z","signature_b64":"C+QaIsCGONpuBZjNZjFu2qfQejhZ4p/HcgpjSy71K6QKm83VxRlVOvevMHDkrJXyL8LTCrkSvKjhllVnHRf3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80a060e476e98af0e024f18f398a8d075aa058d946ba126c1d47f0f1552a0aad","last_reissued_at":"2026-07-05T08:46:34.862414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:34.862414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-based Talking Video Editing with Cascaded Conditional Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Han, Chng Eng Siong, Guangcong Wang, Haoyang Li, Heqing Zou","submitted_at":"2024-07-20T10:55:19Z","abstract_excerpt":"Text-based talking-head video editing aims to efficiently insert, delete, and substitute segments of talking videos through a user-friendly text editing approach. It is challenging because of \\textbf{1)} generalizable talking-face representation, \\textbf{2)} seamless audio-visual transitions, and \\textbf{3)} identity-preserved talking faces. Previous works either require minutes of talking-face video training data and expensive test-time optimization for customized talking video editing or directly generate a video sequence without considering in-context information, leading to a poor generali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14841","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/2407.14841/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":"2407.14841","created_at":"2026-07-05T08:46:34.862473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14841v1","created_at":"2026-07-05T08:46:34.862473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14841","created_at":"2026-07-05T08:46:34.862473+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCQGBZDW5GFP","created_at":"2026-07-05T08:46:34.862473+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCQGBZDW5GFPBYBE","created_at":"2026-07-05T08:46:34.862473+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCQGBZDW","created_at":"2026-07-05T08:46:34.862473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07554","citing_title":"SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCQGBZDW5GFPBYBE6GHTTCUNA5","json":"https://pith.science/pith/QCQGBZDW5GFPBYBE6GHTTCUNA5.json","graph_json":"https://pith.science/api/pith-number/QCQGBZDW5GFPBYBE6GHTTCUNA5/graph.json","events_json":"https://pith.science/api/pith-number/QCQGBZDW5GFPBYBE6GHTTCUNA5/events.json","paper":"https://pith.science/paper/QCQGBZDW"},"agent_actions":{"view_html":"https://pith.science/pith/QCQGBZDW5GFPBYBE6GHTTCUNA5","download_json":"https://pith.science/pith/QCQGBZDW5GFPBYBE6GHTTCUNA5.json","view_paper":"https://pith.science/paper/QCQGBZDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14841&json=true","fetch_graph":"https://pith.science/api/pith-number/QCQGBZDW5GFPBYBE6GHTTCUNA5/graph.json","fetch_events":"https://pith.science/api/pith-number/QCQGBZDW5GFPBYBE6GHTTCUNA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCQGBZDW5GFPBYBE6GHTTCUNA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCQGBZDW5GFPBYBE6GHTTCUNA5/action/storage_attestation","attest_author":"https://pith.science/pith/QCQGBZDW5GFPBYBE6GHTTCUNA5/action/author_attestation","sign_citation":"https://pith.science/pith/QCQGBZDW5GFPBYBE6GHTTCUNA5/action/citation_signature","submit_replication":"https://pith.science/pith/QCQGBZDW5GFPBYBE6GHTTCUNA5/action/replication_record"}},"created_at":"2026-07-05T08:46:34.862473+00:00","updated_at":"2026-07-05T08:46:34.862473+00:00"}