{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:45HBOASOYDYA6WHWAVJ5F2BOTP","short_pith_number":"pith:45HBOASO","schema_version":"1.0","canonical_sha256":"e74e17024ec0f00f58f60553d2e82e9bdb8a97b0ce35b2e97c541d594f7ec42d","source":{"kind":"arxiv","id":"2507.20627","version":1},"attestation_state":"computed","paper":{"title":"Controllable Video-to-Music Generation with Multiple Time-Varying Conditions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Dengming Zhang, Heda Zuo, Junxian Wu, Lingyun Sun, Pei Chen, Weitao You","submitted_at":"2025-07-28T08:41:20Z","abstract_excerpt":"Music enhances video narratives and emotions, driving demand for automatic video-to-music (V2M) generation. However, existing V2M methods relying solely on visual features or supplementary textual inputs generate music in a black-box manner, often failing to meet user expectations. To address this challenge, we propose a novel multi-condition guided V2M generation framework that incorporates multiple time-varying conditions for enhanced control over music generation. Our method uses a two-stage training strategy that enables learning of V2M fundamentals and audiovisual temporal synchronization"},"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":"2507.20627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-28T08:41:20Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"12f0c21c1fdf6e15f0fa1d83c5032d00c189a718c40a19605c4bcc02031bb3fb","abstract_canon_sha256":"be4b2b92535109001f3a67f19c9674c9edfc78c365d713e3b4e9783ff9a04afe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:22.792549Z","signature_b64":"HQAP90R4biRRmctgpZAGvjtAa6og9KeKGhJiseA7kyvIX42goaMeE8NfX8ybchVuR800yM/LDOYiwDnkV9j2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e74e17024ec0f00f58f60553d2e82e9bdb8a97b0ce35b2e97c541d594f7ec42d","last_reissued_at":"2026-07-05T11:44:22.792147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:22.792147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Video-to-Music Generation with Multiple Time-Varying Conditions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Dengming Zhang, Heda Zuo, Junxian Wu, Lingyun Sun, Pei Chen, Weitao You","submitted_at":"2025-07-28T08:41:20Z","abstract_excerpt":"Music enhances video narratives and emotions, driving demand for automatic video-to-music (V2M) generation. However, existing V2M methods relying solely on visual features or supplementary textual inputs generate music in a black-box manner, often failing to meet user expectations. To address this challenge, we propose a novel multi-condition guided V2M generation framework that incorporates multiple time-varying conditions for enhanced control over music generation. Our method uses a two-stage training strategy that enables learning of V2M fundamentals and audiovisual temporal synchronization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20627","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/2507.20627/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":"2507.20627","created_at":"2026-07-05T11:44:22.792204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20627v1","created_at":"2026-07-05T11:44:22.792204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20627","created_at":"2026-07-05T11:44:22.792204+00:00"},{"alias_kind":"pith_short_12","alias_value":"45HBOASOYDYA","created_at":"2026-07-05T11:44:22.792204+00:00"},{"alias_kind":"pith_short_16","alias_value":"45HBOASOYDYA6WHW","created_at":"2026-07-05T11:44:22.792204+00:00"},{"alias_kind":"pith_short_8","alias_value":"45HBOASO","created_at":"2026-07-05T11:44:22.792204+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/45HBOASOYDYA6WHWAVJ5F2BOTP","json":"https://pith.science/pith/45HBOASOYDYA6WHWAVJ5F2BOTP.json","graph_json":"https://pith.science/api/pith-number/45HBOASOYDYA6WHWAVJ5F2BOTP/graph.json","events_json":"https://pith.science/api/pith-number/45HBOASOYDYA6WHWAVJ5F2BOTP/events.json","paper":"https://pith.science/paper/45HBOASO"},"agent_actions":{"view_html":"https://pith.science/pith/45HBOASOYDYA6WHWAVJ5F2BOTP","download_json":"https://pith.science/pith/45HBOASOYDYA6WHWAVJ5F2BOTP.json","view_paper":"https://pith.science/paper/45HBOASO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20627&json=true","fetch_graph":"https://pith.science/api/pith-number/45HBOASOYDYA6WHWAVJ5F2BOTP/graph.json","fetch_events":"https://pith.science/api/pith-number/45HBOASOYDYA6WHWAVJ5F2BOTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45HBOASOYDYA6WHWAVJ5F2BOTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45HBOASOYDYA6WHWAVJ5F2BOTP/action/storage_attestation","attest_author":"https://pith.science/pith/45HBOASOYDYA6WHWAVJ5F2BOTP/action/author_attestation","sign_citation":"https://pith.science/pith/45HBOASOYDYA6WHWAVJ5F2BOTP/action/citation_signature","submit_replication":"https://pith.science/pith/45HBOASOYDYA6WHWAVJ5F2BOTP/action/replication_record"}},"created_at":"2026-07-05T11:44:22.792204+00:00","updated_at":"2026-07-05T11:44:22.792204+00:00"}