{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IMZ3AWREPVNI3CFT6D6QBVREXZ","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":"14270f67a34ebf4037410badf3d6621de18d687fe79ae56aabcf3349f548cb6e","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T16:33:21Z","title_canon_sha256":"cbc20bd9398b6a4469a2aa4f010aaf57a6ff9da70c3737e02d5a71662b2e35ca"},"schema_version":"1.0","source":{"id":"2412.09428","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09428","created_at":"2026-07-05T09:48:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09428v1","created_at":"2026-07-05T09:48:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09428","created_at":"2026-07-05T09:48:24Z"},{"alias_kind":"pith_short_12","alias_value":"IMZ3AWREPVNI","created_at":"2026-07-05T09:48:24Z"},{"alias_kind":"pith_short_16","alias_value":"IMZ3AWREPVNI3CFT","created_at":"2026-07-05T09:48:24Z"},{"alias_kind":"pith_short_8","alias_value":"IMZ3AWRE","created_at":"2026-07-05T09:48:24Z"}],"graph_snapshots":[{"event_id":"sha256:ef1c8f1683843345b897404d0469b688d5d7969c58cbdac55d4ea01c6b3d8d61","target":"graph","created_at":"2026-07-05T09:48:24Z","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/2412.09428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal music generation aims to produce music from diverse input modalities, including text, videos, and images. Existing methods use a common embedding space for multimodal fusion. Despite their effectiveness in other modalities, their application in multimodal music generation faces challenges of data scarcity, weak cross-modal alignment, and limited controllability. This paper addresses these issues by using explicit bridges of text and music for multimodal alignment. We introduce a novel method named Visuals Music Bridge (VMB). Specifically, a Multimodal Music Description Model convert","authors_text":"Baisen Wang, Chenxi Bao, Jiao Dai, Jizhong Han, Le Zhuo, Si Liu, Wu Chengjing, Xuecheng Nie, Yue Liao, Zhaokai Wang","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T16:33:21Z","title":"Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09428","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:e4b69065736883a5fcb6720762c7f0478e8fefe40d1f72a441fc706dbad04d35","target":"record","created_at":"2026-07-05T09:48:24Z","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":"14270f67a34ebf4037410badf3d6621de18d687fe79ae56aabcf3349f548cb6e","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T16:33:21Z","title_canon_sha256":"cbc20bd9398b6a4469a2aa4f010aaf57a6ff9da70c3737e02d5a71662b2e35ca"},"schema_version":"1.0","source":{"id":"2412.09428","kind":"arxiv","version":1}},"canonical_sha256":"4333b05a247d5a8d88b3f0fd00d624be596b498a5fde122877221626170f9908","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4333b05a247d5a8d88b3f0fd00d624be596b498a5fde122877221626170f9908","first_computed_at":"2026-07-05T09:48:24.399589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:24.399589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lq12aOeq/rSr8LGIIoYIF4uq9fru0FMbwC9opNnU4A0kI1937AKjfB7oX8GmdAS91DviHLYna5CMvF95vCB9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:24.400098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09428","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4b69065736883a5fcb6720762c7f0478e8fefe40d1f72a441fc706dbad04d35","sha256:ef1c8f1683843345b897404d0469b688d5d7969c58cbdac55d4ea01c6b3d8d61"],"state_sha256":"1df2882c8dcf963993f2ac9da47a13b866a24c4267f1fb0326a9dc7d5bc157e2"}