{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:72FU3XOXFXHQEY24E2O3BWLG6K","short_pith_number":"pith:72FU3XOX","schema_version":"1.0","canonical_sha256":"fe8b4dddd72dcf02635c269db0d966f28eaf6ef687124105298b59c0b06836aa","source":{"kind":"arxiv","id":"2407.04697","version":1},"attestation_state":"computed","paper":{"title":"VCoME: Verbal Video Composition with Multimodal Editing Effects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dongliang He, Weibo Gong, Xiaojie Jin, Xinglong Wu, Xin Li","submitted_at":"2024-07-05T17:59:02Z","abstract_excerpt":"Verbal videos, featuring voice-overs or text overlays, provide valuable content but present significant challenges in composition, especially when incorporating editing effects to enhance clarity and visual appeal. In this paper, we introduce the novel task of verbal video composition with editing effects. This task aims to generate coherent and visually appealing verbal videos by integrating multimodal editing effects across textual, visual, and audio categories. To achieve this, we curate a large-scale dataset of video effects compositions from publicly available sources. We then formulate 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":"2407.04697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T17:59:02Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"c806eb10ace4cb6fb82e859aa88028cf9f3f2797b1d8f0319fa3002bf1de2682","abstract_canon_sha256":"8af3d2ce9680120bd71f1f3d7e0d479b889cc9943882411f2956e885001ee74a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:37.603424Z","signature_b64":"3ozQyWD3Hd2bx7pJMj0xuvRwBIZQaxESgglCbRNL9AAzaGM1PYfYb25tS1vDOw9njjKwaRLS1UOy+GHc6n9JDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe8b4dddd72dcf02635c269db0d966f28eaf6ef687124105298b59c0b06836aa","last_reissued_at":"2026-07-05T08:40:37.602970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:37.602970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VCoME: Verbal Video Composition with Multimodal Editing Effects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dongliang He, Weibo Gong, Xiaojie Jin, Xinglong Wu, Xin Li","submitted_at":"2024-07-05T17:59:02Z","abstract_excerpt":"Verbal videos, featuring voice-overs or text overlays, provide valuable content but present significant challenges in composition, especially when incorporating editing effects to enhance clarity and visual appeal. In this paper, we introduce the novel task of verbal video composition with editing effects. This task aims to generate coherent and visually appealing verbal videos by integrating multimodal editing effects across textual, visual, and audio categories. To achieve this, we curate a large-scale dataset of video effects compositions from publicly available sources. We then formulate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04697","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/2407.04697/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":"2407.04697","created_at":"2026-07-05T08:40:37.603025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04697v1","created_at":"2026-07-05T08:40:37.603025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04697","created_at":"2026-07-05T08:40:37.603025+00:00"},{"alias_kind":"pith_short_12","alias_value":"72FU3XOXFXHQ","created_at":"2026-07-05T08:40:37.603025+00:00"},{"alias_kind":"pith_short_16","alias_value":"72FU3XOXFXHQEY24","created_at":"2026-07-05T08:40:37.603025+00:00"},{"alias_kind":"pith_short_8","alias_value":"72FU3XOX","created_at":"2026-07-05T08:40:37.603025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72FU3XOXFXHQEY24E2O3BWLG6K","json":"https://pith.science/pith/72FU3XOXFXHQEY24E2O3BWLG6K.json","graph_json":"https://pith.science/api/pith-number/72FU3XOXFXHQEY24E2O3BWLG6K/graph.json","events_json":"https://pith.science/api/pith-number/72FU3XOXFXHQEY24E2O3BWLG6K/events.json","paper":"https://pith.science/paper/72FU3XOX"},"agent_actions":{"view_html":"https://pith.science/pith/72FU3XOXFXHQEY24E2O3BWLG6K","download_json":"https://pith.science/pith/72FU3XOXFXHQEY24E2O3BWLG6K.json","view_paper":"https://pith.science/paper/72FU3XOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04697&json=true","fetch_graph":"https://pith.science/api/pith-number/72FU3XOXFXHQEY24E2O3BWLG6K/graph.json","fetch_events":"https://pith.science/api/pith-number/72FU3XOXFXHQEY24E2O3BWLG6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72FU3XOXFXHQEY24E2O3BWLG6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72FU3XOXFXHQEY24E2O3BWLG6K/action/storage_attestation","attest_author":"https://pith.science/pith/72FU3XOXFXHQEY24E2O3BWLG6K/action/author_attestation","sign_citation":"https://pith.science/pith/72FU3XOXFXHQEY24E2O3BWLG6K/action/citation_signature","submit_replication":"https://pith.science/pith/72FU3XOXFXHQEY24E2O3BWLG6K/action/replication_record"}},"created_at":"2026-07-05T08:40:37.603025+00:00","updated_at":"2026-07-05T08:40:37.603025+00:00"}