{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GISJEXDG4MN4FZI3WUCVUKKFWD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fc4823bc9c7fcefdc3523bdba3195480a60c4773211ed20140ac49426eb7349a","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-16T18:44:56Z","title_canon_sha256":"bec28abfbfd6055d20cc94d1abbf60bb73ce76ffd52424303459856fa613e9e2"},"schema_version":"1.0","source":{"id":"2410.12957","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12957","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12957v1","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12957","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"pith_short_12","alias_value":"GISJEXDG4MN4","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"pith_short_16","alias_value":"GISJEXDG4MN4FZI3","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"pith_short_8","alias_value":"GISJEXDG","created_at":"2026-07-05T09:21:53Z"}],"graph_snapshots":[{"event_id":"sha256:a85cb81bfc76429d145be64e8e83ed1e0f0cce4ec18f1492a4e1bfa741efcfcd","target":"graph","created_at":"2026-07-05T09:21:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.12957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Ruiqi Li, Shengpeng Ji, Siqi Zheng, Xize Cheng, Zhou Zhao, Ziang Zhang","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-16T18:44:56Z","title":"MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12957","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a48f766596c2e055a04a538a08a0f0257a8003ac8bee67193762dbc33e029412","target":"record","created_at":"2026-07-05T09:21:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fc4823bc9c7fcefdc3523bdba3195480a60c4773211ed20140ac49426eb7349a","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-16T18:44:56Z","title_canon_sha256":"bec28abfbfd6055d20cc94d1abbf60bb73ce76ffd52424303459856fa613e9e2"},"schema_version":"1.0","source":{"id":"2410.12957","kind":"arxiv","version":1}},"canonical_sha256":"3224925c66e31bc2e51bb5055a2945b0f2ccd91262e77fcfcb331808e3861960","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3224925c66e31bc2e51bb5055a2945b0f2ccd91262e77fcfcb331808e3861960","first_computed_at":"2026-07-05T09:21:53.315235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:53.315235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k7UVByiFKOU4zmt0/z87+vz4LYjROuKgWfVyf3Pz1yX6xUWVQkLNfNX1iYezbqpHbU5PEC5zkD5431xK/Rv6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:53.315706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12957","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a48f766596c2e055a04a538a08a0f0257a8003ac8bee67193762dbc33e029412","sha256:a85cb81bfc76429d145be64e8e83ed1e0f0cce4ec18f1492a4e1bfa741efcfcd"],"state_sha256":"498efc5b3b56067b9be91463882c7d733990db3c2d9499f4002c192aecb0e97e"}