{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SUZ5PF4QUWL6FZP2RLOMWRECAP","short_pith_number":"pith:SUZ5PF4Q","schema_version":"1.0","canonical_sha256":"9533d79790a597e2e5fa8adccb448203dbbcee03828cb175ebf622e51922dcfc","source":{"kind":"arxiv","id":"2506.15154","version":1},"attestation_state":"computed","paper":{"title":"SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Abhinaba Roy, Anuradha Chopra, Dorien Herremans","submitted_at":"2025-06-18T05:51:36Z","abstract_excerpt":"Detailed captions that accurately reflect the characteristics of a music piece can enrich music databases and drive forward research in music AI. This paper introduces a multi-task music captioning model, SonicVerse, that integrates caption generation with auxiliary music feature detection tasks such as key detection, vocals detection, and more, so as to directly capture both low-level acoustic details as well as high-level musical attributes. The key contribution is a projection-based architecture that transforms audio input into language tokens, while simultaneously detecting music features "},"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":"2506.15154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-18T05:51:36Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","eess.AS"],"title_canon_sha256":"7675d50c3124ac472b3f61cad6e8a89cfb926ec2b819ecea1ea619b5091e716a","abstract_canon_sha256":"e480a00cc7984942d539d64ba06eb7d944591cccf147ddd04c066268b7fdc1ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:38.236666Z","signature_b64":"F8KDrDLtul79W0HANxjNBUHMoIQgrDdmKDmUhWWKQa5HkBIlnY2a0KlKjY7V6YYmDqw9xdVZ0WGkUDcgb2v4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9533d79790a597e2e5fa8adccb448203dbbcee03828cb175ebf622e51922dcfc","last_reissued_at":"2026-07-05T11:23:38.236091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:38.236091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Abhinaba Roy, Anuradha Chopra, Dorien Herremans","submitted_at":"2025-06-18T05:51:36Z","abstract_excerpt":"Detailed captions that accurately reflect the characteristics of a music piece can enrich music databases and drive forward research in music AI. This paper introduces a multi-task music captioning model, SonicVerse, that integrates caption generation with auxiliary music feature detection tasks such as key detection, vocals detection, and more, so as to directly capture both low-level acoustic details as well as high-level musical attributes. The key contribution is a projection-based architecture that transforms audio input into language tokens, while simultaneously detecting music features "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15154","kind":"arxiv","version":1},"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/2506.15154/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":"2506.15154","created_at":"2026-07-05T11:23:38.236191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15154v1","created_at":"2026-07-05T11:23:38.236191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15154","created_at":"2026-07-05T11:23:38.236191+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUZ5PF4QUWL6","created_at":"2026-07-05T11:23:38.236191+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUZ5PF4QUWL6FZP2","created_at":"2026-07-05T11:23:38.236191+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUZ5PF4Q","created_at":"2026-07-05T11:23:38.236191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27346","citing_title":"MERIT: Learning Disentangled Music Representations for Audio Similarity","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUZ5PF4QUWL6FZP2RLOMWRECAP","json":"https://pith.science/pith/SUZ5PF4QUWL6FZP2RLOMWRECAP.json","graph_json":"https://pith.science/api/pith-number/SUZ5PF4QUWL6FZP2RLOMWRECAP/graph.json","events_json":"https://pith.science/api/pith-number/SUZ5PF4QUWL6FZP2RLOMWRECAP/events.json","paper":"https://pith.science/paper/SUZ5PF4Q"},"agent_actions":{"view_html":"https://pith.science/pith/SUZ5PF4QUWL6FZP2RLOMWRECAP","download_json":"https://pith.science/pith/SUZ5PF4QUWL6FZP2RLOMWRECAP.json","view_paper":"https://pith.science/paper/SUZ5PF4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15154&json=true","fetch_graph":"https://pith.science/api/pith-number/SUZ5PF4QUWL6FZP2RLOMWRECAP/graph.json","fetch_events":"https://pith.science/api/pith-number/SUZ5PF4QUWL6FZP2RLOMWRECAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUZ5PF4QUWL6FZP2RLOMWRECAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUZ5PF4QUWL6FZP2RLOMWRECAP/action/storage_attestation","attest_author":"https://pith.science/pith/SUZ5PF4QUWL6FZP2RLOMWRECAP/action/author_attestation","sign_citation":"https://pith.science/pith/SUZ5PF4QUWL6FZP2RLOMWRECAP/action/citation_signature","submit_replication":"https://pith.science/pith/SUZ5PF4QUWL6FZP2RLOMWRECAP/action/replication_record"}},"created_at":"2026-07-05T11:23:38.236191+00:00","updated_at":"2026-07-05T11:23:38.236191+00:00"}