{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T5UZ2QNK5VPLNJ4ZTTTJ7XB222","short_pith_number":"pith:T5UZ2QNK","schema_version":"1.0","canonical_sha256":"9f699d41aaed5eb6a7999ce69fdc3ad6a107c1e996ef1f838f0bbda5d764b049","source":{"kind":"arxiv","id":"2309.08730","version":3},"attestation_state":"computed","paper":{"title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Emmanouil Benetos, Ge Zhang, Rongchen Guo, Wenhao Huang, Wenhu Chen, Yinghao Ma, Yudong Liu, Zihao Deng","submitted_at":"2023-09-15T19:31:40Z","abstract_excerpt":"Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains not well-explored. To address this gap, we present MusiLingo, a novel system for music caption generation and music-related query responses. MusiLingo employs a single projection layer to align music representations from the pre-trained frozen music audio model MERT with a frozen LLM, bridging the gap between music audio and textual contexts. We train it on an extensive music caption dataset and fine-tune it with instructional data. Due to the scarcit"},"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":"2309.08730","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T19:31:40Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD"],"title_canon_sha256":"a442f079d11d2446284362ff055b0d6d50bf9c4df770ccdbda16c837693b3f24","abstract_canon_sha256":"4aa3981cbabb03f5706673b16fb45e273d74f290e8d3a7292a47dec5f16c24b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:26.541509Z","signature_b64":"lJ9p+/BeFrvectF63AzGkixjt0JzbitwWydttA13iXSBEG3lxaqHI2a40mjTKuJu/FZuA7kzPHJ5lQj6jdCEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f699d41aaed5eb6a7999ce69fdc3ad6a107c1e996ef1f838f0bbda5d764b049","last_reissued_at":"2026-07-05T08:03:26.541028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:26.541028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Emmanouil Benetos, Ge Zhang, Rongchen Guo, Wenhao Huang, Wenhu Chen, Yinghao Ma, Yudong Liu, Zihao Deng","submitted_at":"2023-09-15T19:31:40Z","abstract_excerpt":"Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains not well-explored. To address this gap, we present MusiLingo, a novel system for music caption generation and music-related query responses. MusiLingo employs a single projection layer to align music representations from the pre-trained frozen music audio model MERT with a frozen LLM, bridging the gap between music audio and textual contexts. We train it on an extensive music caption dataset and fine-tune it with instructional data. Due to the scarcit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08730","kind":"arxiv","version":3},"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/2309.08730/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":"2309.08730","created_at":"2026-07-05T08:03:26.541083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08730v3","created_at":"2026-07-05T08:03:26.541083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08730","created_at":"2026-07-05T08:03:26.541083+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5UZ2QNK5VPL","created_at":"2026-07-05T08:03:26.541083+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5UZ2QNK5VPLNJ4Z","created_at":"2026-07-05T08:03:26.541083+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5UZ2QNK","created_at":"2026-07-05T08:03:26.541083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.20638","citing_title":"Music Audio-Visual Question Answering Requires Specialized Multimodal Designs","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2507.08128","citing_title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5UZ2QNK5VPLNJ4ZTTTJ7XB222","json":"https://pith.science/pith/T5UZ2QNK5VPLNJ4ZTTTJ7XB222.json","graph_json":"https://pith.science/api/pith-number/T5UZ2QNK5VPLNJ4ZTTTJ7XB222/graph.json","events_json":"https://pith.science/api/pith-number/T5UZ2QNK5VPLNJ4ZTTTJ7XB222/events.json","paper":"https://pith.science/paper/T5UZ2QNK"},"agent_actions":{"view_html":"https://pith.science/pith/T5UZ2QNK5VPLNJ4ZTTTJ7XB222","download_json":"https://pith.science/pith/T5UZ2QNK5VPLNJ4ZTTTJ7XB222.json","view_paper":"https://pith.science/paper/T5UZ2QNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08730&json=true","fetch_graph":"https://pith.science/api/pith-number/T5UZ2QNK5VPLNJ4ZTTTJ7XB222/graph.json","fetch_events":"https://pith.science/api/pith-number/T5UZ2QNK5VPLNJ4ZTTTJ7XB222/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5UZ2QNK5VPLNJ4ZTTTJ7XB222/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5UZ2QNK5VPLNJ4ZTTTJ7XB222/action/storage_attestation","attest_author":"https://pith.science/pith/T5UZ2QNK5VPLNJ4ZTTTJ7XB222/action/author_attestation","sign_citation":"https://pith.science/pith/T5UZ2QNK5VPLNJ4ZTTTJ7XB222/action/citation_signature","submit_replication":"https://pith.science/pith/T5UZ2QNK5VPLNJ4ZTTTJ7XB222/action/replication_record"}},"created_at":"2026-07-05T08:03:26.541083+00:00","updated_at":"2026-07-05T08:03:26.541083+00:00"}