{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UD2LZBYGJIMDNEF3KIMZCECAXG","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":"5b48b0625014d7703530d163f0c9195d9aea769858a3149a9c568ef88141eb28","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-09T16:59:35Z","title_canon_sha256":"b85957615aaf6aa448bba911acb625e987d3c2167ce1a9852b64f0958012225d"},"schema_version":"1.0","source":{"id":"2412.06660","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06660","created_at":"2026-07-05T09:46:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06660v1","created_at":"2026-07-05T09:46:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06660","created_at":"2026-07-05T09:46:35Z"},{"alias_kind":"pith_short_12","alias_value":"UD2LZBYGJIMD","created_at":"2026-07-05T09:46:35Z"},{"alias_kind":"pith_short_16","alias_value":"UD2LZBYGJIMDNEF3","created_at":"2026-07-05T09:46:35Z"},{"alias_kind":"pith_short_8","alias_value":"UD2LZBYG","created_at":"2026-07-05T09:46:35Z"}],"graph_snapshots":[{"event_id":"sha256:d3c84e278eea7e824f612760a4c443bbe9afe7c98a4507a3c0e9692a5092da96","target":"graph","created_at":"2026-07-05T09:46:35Z","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/2412.06660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Research on large language models has advanced significantly across text, speech, images, and videos. However, multi-modal music understanding and generation remain underexplored due to the lack of well-annotated datasets. To address this, we introduce a dataset with 167.69 hours of multi-modal data, including text, images, videos, and music annotations. Based on this dataset, we propose MuMu-LLaMA, a model that leverages pre-trained encoders for music, images, and videos. For music generation, we integrate AudioLDM 2 and MusicGen. Our evaluation across four tasks--music understanding, text-to","authors_text":"Atin Sakkeer Hussain, Chenshuo Sun, Qilong Wu, Shansong Liu, Ying Shan","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-09T16:59:35Z","title":"MuMu-LLaMA: Multi-modal Music Understanding and Generation via Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06660","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":"sha256:1d5d50bc64d42a381853c0fbc546644bc8f613516afb98705fabefc1219e7418","target":"record","created_at":"2026-07-05T09:46:35Z","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":"5b48b0625014d7703530d163f0c9195d9aea769858a3149a9c568ef88141eb28","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-09T16:59:35Z","title_canon_sha256":"b85957615aaf6aa448bba911acb625e987d3c2167ce1a9852b64f0958012225d"},"schema_version":"1.0","source":{"id":"2412.06660","kind":"arxiv","version":1}},"canonical_sha256":"a0f4bc87064a183690bb5219911040b9b6ffe06519064eaa5baa56cb6c9eba1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0f4bc87064a183690bb5219911040b9b6ffe06519064eaa5baa56cb6c9eba1b","first_computed_at":"2026-07-05T09:46:35.731756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:35.731756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nqSLDYLwuUwC/mNxvwjCL3Nvw0hcBy1+d289GwuyH3kX1eP6qOMn1IjgKVoqIgUBvcSaFZELhwpiSQXNbnbHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:35.732179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06660","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d5d50bc64d42a381853c0fbc546644bc8f613516afb98705fabefc1219e7418","sha256:d3c84e278eea7e824f612760a4c443bbe9afe7c98a4507a3c0e9692a5092da96"],"state_sha256":"92a4a5b05f88bd2e468723ba6cd8b0f9a032c5c0b829a98188316bec5bc5a135"}