{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D4BSMNNUKBAMS2LRUOXRGPZ64W","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":"76cc6e976e1099f66259d744d833c79d8bac41de44220f15a7d2d47e68a61496","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-10T09:47:26Z","title_canon_sha256":"f4decca7c1eae58cfda4bfb89a2fca13541911e5c5f6d12fc4c65e5c6425b51b"},"schema_version":"1.0","source":{"id":"2504.07594","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07594","created_at":"2026-07-05T10:47:11Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07594v1","created_at":"2026-07-05T10:47:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07594","created_at":"2026-07-05T10:47:11Z"},{"alias_kind":"pith_short_12","alias_value":"D4BSMNNUKBAM","created_at":"2026-07-05T10:47:11Z"},{"alias_kind":"pith_short_16","alias_value":"D4BSMNNUKBAMS2LR","created_at":"2026-07-05T10:47:11Z"},{"alias_kind":"pith_short_8","alias_value":"D4BSMNNU","created_at":"2026-07-05T10:47:11Z"}],"graph_snapshots":[{"event_id":"sha256:cf18721b4ad2a2f546e6584b82e15da0959e98400dcef65b25ec5a07e7968527","target":"graph","created_at":"2026-07-05T10:47:11Z","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/2504.07594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Music profoundly enhances video production by improving quality, engagement, and emotional resonance, sparking growing interest in video-to-music generation. Despite recent advances, existing approaches remain limited in specific scenarios or undervalue the visual dynamics. To address these limitations, we focus on tackling the complexity of dynamics and resolving temporal misalignment between video and music representations. To this end, we propose DyViM, a novel framework to enhance dynamics modeling for video-to-music generation. Specifically, we extract frame-wise dynamics features via a s","authors_text":"Tat-Seng Chua, Teng Tu, Xiaohao Liu, Yunshan Ma","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-10T09:47:26Z","title":"Extending Visual Dynamics for Video-to-Music Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07594","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":"sha256:7f44cb925c0119382794f04e6c2b1a3fa696d7e463d4fdceb66e79543af297c9","target":"record","created_at":"2026-07-05T10:47:11Z","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":"76cc6e976e1099f66259d744d833c79d8bac41de44220f15a7d2d47e68a61496","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-10T09:47:26Z","title_canon_sha256":"f4decca7c1eae58cfda4bfb89a2fca13541911e5c5f6d12fc4c65e5c6425b51b"},"schema_version":"1.0","source":{"id":"2504.07594","kind":"arxiv","version":1}},"canonical_sha256":"1f032635b45040c96971a3af133f3ee5809b0231d179085179dfb83a41aea682","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f032635b45040c96971a3af133f3ee5809b0231d179085179dfb83a41aea682","first_computed_at":"2026-07-05T10:47:11.591961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:11.591961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0gaGlGlMtMF/6WnTnH0O4hXyEXojTpRoCtjGy2KNqit83OA+/9WpXAZveK4gbthAVKv103c7k1UFntPqo+CeCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:11.592457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07594","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f44cb925c0119382794f04e6c2b1a3fa696d7e463d4fdceb66e79543af297c9","sha256:cf18721b4ad2a2f546e6584b82e15da0959e98400dcef65b25ec5a07e7968527"],"state_sha256":"a52f660c1b5464a9c4c0068306ed2fd6d876f8c86650f51e7765765aafe4d8db"}