{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GISJEXDG4MN4FZI3WUCVUKKFWD","short_pith_number":"pith:GISJEXDG","schema_version":"1.0","canonical_sha256":"3224925c66e31bc2e51bb5055a2945b0f2ccd91262e77fcfcb331808e3861960","source":{"kind":"arxiv","id":"2410.12957","version":1},"attestation_state":"computed","paper":{"title":"MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ruiqi Li, Shengpeng Ji, Siqi Zheng, Xize Cheng, Zhou Zhao, Ziang Zhang","submitted_at":"2024-10-16T18:44:56Z","abstract_excerpt":"Generating music that aligns with the visual content of a video has been a challenging task, as it requires a deep understanding of visual semantics and involves generating music whose melody, rhythm, and dynamics harmonize with the visual narratives. This paper presents MuVi, a novel framework that effectively addresses these challenges to enhance the cohesion and immersive experience of audio-visual content. MuVi analyzes video content through a specially designed visual adaptor to extract contextually and temporally relevant features. These features are used to generate music that not only "},"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":"2410.12957","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-16T18:44:56Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"bec28abfbfd6055d20cc94d1abbf60bb73ce76ffd52424303459856fa613e9e2","abstract_canon_sha256":"fc4823bc9c7fcefdc3523bdba3195480a60c4773211ed20140ac49426eb7349a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:53.315706Z","signature_b64":"k7UVByiFKOU4zmt0/z87+vz4LYjROuKgWfVyf3Pz1yX6xUWVQkLNfNX1iYezbqpHbU5PEC5zkD5431xK/Rv6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3224925c66e31bc2e51bb5055a2945b0f2ccd91262e77fcfcb331808e3861960","last_reissued_at":"2026-07-05T09:21:53.315235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:53.315235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ruiqi Li, Shengpeng Ji, Siqi Zheng, Xize Cheng, Zhou Zhao, Ziang Zhang","submitted_at":"2024-10-16T18:44:56Z","abstract_excerpt":"Generating music that aligns with the visual content of a video has been a challenging task, as it requires a deep understanding of visual semantics and involves generating music whose melody, rhythm, and dynamics harmonize with the visual narratives. This paper presents MuVi, a novel framework that effectively addresses these challenges to enhance the cohesion and immersive experience of audio-visual content. MuVi analyzes video content through a specially designed visual adaptor to extract contextually and temporally relevant features. These features are used to generate music that not only "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12957","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/2410.12957/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":"2410.12957","created_at":"2026-07-05T09:21:53.315292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12957v1","created_at":"2026-07-05T09:21:53.315292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12957","created_at":"2026-07-05T09:21:53.315292+00:00"},{"alias_kind":"pith_short_12","alias_value":"GISJEXDG4MN4","created_at":"2026-07-05T09:21:53.315292+00:00"},{"alias_kind":"pith_short_16","alias_value":"GISJEXDG4MN4FZI3","created_at":"2026-07-05T09:21:53.315292+00:00"},{"alias_kind":"pith_short_8","alias_value":"GISJEXDG","created_at":"2026-07-05T09:21:53.315292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12555","citing_title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01703","citing_title":"JenBridge: Adaptive Long-Form Video Soundtracking across Scene Transitions","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GISJEXDG4MN4FZI3WUCVUKKFWD","json":"https://pith.science/pith/GISJEXDG4MN4FZI3WUCVUKKFWD.json","graph_json":"https://pith.science/api/pith-number/GISJEXDG4MN4FZI3WUCVUKKFWD/graph.json","events_json":"https://pith.science/api/pith-number/GISJEXDG4MN4FZI3WUCVUKKFWD/events.json","paper":"https://pith.science/paper/GISJEXDG"},"agent_actions":{"view_html":"https://pith.science/pith/GISJEXDG4MN4FZI3WUCVUKKFWD","download_json":"https://pith.science/pith/GISJEXDG4MN4FZI3WUCVUKKFWD.json","view_paper":"https://pith.science/paper/GISJEXDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12957&json=true","fetch_graph":"https://pith.science/api/pith-number/GISJEXDG4MN4FZI3WUCVUKKFWD/graph.json","fetch_events":"https://pith.science/api/pith-number/GISJEXDG4MN4FZI3WUCVUKKFWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GISJEXDG4MN4FZI3WUCVUKKFWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GISJEXDG4MN4FZI3WUCVUKKFWD/action/storage_attestation","attest_author":"https://pith.science/pith/GISJEXDG4MN4FZI3WUCVUKKFWD/action/author_attestation","sign_citation":"https://pith.science/pith/GISJEXDG4MN4FZI3WUCVUKKFWD/action/citation_signature","submit_replication":"https://pith.science/pith/GISJEXDG4MN4FZI3WUCVUKKFWD/action/replication_record"}},"created_at":"2026-07-05T09:21:53.315292+00:00","updated_at":"2026-07-05T09:21:53.315292+00:00"}