{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T5UZ2QNK5VPLNJ4ZTTTJ7XB222","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":"4aa3981cbabb03f5706673b16fb45e273d74f290e8d3a7292a47dec5f16c24b0","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T19:31:40Z","title_canon_sha256":"a442f079d11d2446284362ff055b0d6d50bf9c4df770ccdbda16c837693b3f24"},"schema_version":"1.0","source":{"id":"2309.08730","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08730","created_at":"2026-07-05T08:03:26Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08730v3","created_at":"2026-07-05T08:03:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08730","created_at":"2026-07-05T08:03:26Z"},{"alias_kind":"pith_short_12","alias_value":"T5UZ2QNK5VPL","created_at":"2026-07-05T08:03:26Z"},{"alias_kind":"pith_short_16","alias_value":"T5UZ2QNK5VPLNJ4Z","created_at":"2026-07-05T08:03:26Z"},{"alias_kind":"pith_short_8","alias_value":"T5UZ2QNK","created_at":"2026-07-05T08:03:26Z"}],"graph_snapshots":[{"event_id":"sha256:73ca7d79e8165e59ae3d33e0d32995bc8fb2fdbfc4610501abe451bf4a96f86a","target":"graph","created_at":"2026-07-05T08:03:26Z","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/2309.08730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Emmanouil Benetos, Ge Zhang, Rongchen Guo, Wenhao Huang, Wenhu Chen, Yinghao Ma, Yudong Liu, Zihao Deng","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T19:31:40Z","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08730","kind":"arxiv","version":3},"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":"sha256:2afa51ee864787ddab61ee483c205e21d010ca17f0b9135be6a35f4bee3203fc","target":"record","created_at":"2026-07-05T08:03:26Z","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":"4aa3981cbabb03f5706673b16fb45e273d74f290e8d3a7292a47dec5f16c24b0","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T19:31:40Z","title_canon_sha256":"a442f079d11d2446284362ff055b0d6d50bf9c4df770ccdbda16c837693b3f24"},"schema_version":"1.0","source":{"id":"2309.08730","kind":"arxiv","version":3}},"canonical_sha256":"9f699d41aaed5eb6a7999ce69fdc3ad6a107c1e996ef1f838f0bbda5d764b049","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f699d41aaed5eb6a7999ce69fdc3ad6a107c1e996ef1f838f0bbda5d764b049","first_computed_at":"2026-07-05T08:03:26.541028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:26.541028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lJ9p+/BeFrvectF63AzGkixjt0JzbitwWydttA13iXSBEG3lxaqHI2a40mjTKuJu/FZuA7kzPHJ5lQj6jdCEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:26.541509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08730","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2afa51ee864787ddab61ee483c205e21d010ca17f0b9135be6a35f4bee3203fc","sha256:73ca7d79e8165e59ae3d33e0d32995bc8fb2fdbfc4610501abe451bf4a96f86a"],"state_sha256":"20a97289258e2a097fb3a94a34de73f2b4f14f0d594038c17305eab379aab405"}