{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2QI3V4EC5R6Y4FFTGG5W6HRQQZ","short_pith_number":"pith:2QI3V4EC","schema_version":"1.0","canonical_sha256":"d411baf082ec7d8e14b331bb6f1e30865ce2938d1bd30a8c6eb0f1ac05f61a9e","source":{"kind":"arxiv","id":"2505.17233","version":3},"attestation_state":"computed","paper":{"title":"Semantic-Aware Interpretable Multimodal Music Auto-Tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Andreas Patakis, Edmund Dervakos, Giorgos Stamou, Spyridon Kantarelis, Vassilis Lyberatos","submitted_at":"2025-05-22T19:15:48Z","abstract_excerpt":"Music auto-tagging is essential for organizing and discovering music in extensive digital libraries. While foundation models achieve exceptional performance in this domain, their outputs often lack interpretability, limiting trust and usability for researchers and end-users alike. In this work, we present an interpretable framework for music auto-tagging that leverages groups of musically meaningful multimodal features, derived from signal processing, deep learning, ontology engineering, and natural language processing. To enhance interpretability, we cluster features semantically and employ a"},"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":"2505.17233","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T19:15:48Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"cdea57740c8e0f7a31c1a4d75cffc267ad3dfbafff53219503a4410130f5432a","abstract_canon_sha256":"5f636aa101d2422e6a1548c097789e4b958c60143b0172ff809a8be585eb8234"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:28.159241Z","signature_b64":"lRaBq9CFlqyId7lGuczPrTd6CN9fZJuyTlbQZ7LtDcFvskinhLyCsbMaALPUwZO7MUQLxVBbReq/bfgLsaurCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d411baf082ec7d8e14b331bb6f1e30865ce2938d1bd30a8c6eb0f1ac05f61a9e","last_reissued_at":"2026-05-28T01:04:28.158651Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:28.158651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic-Aware Interpretable Multimodal Music Auto-Tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Andreas Patakis, Edmund Dervakos, Giorgos Stamou, Spyridon Kantarelis, Vassilis Lyberatos","submitted_at":"2025-05-22T19:15:48Z","abstract_excerpt":"Music auto-tagging is essential for organizing and discovering music in extensive digital libraries. While foundation models achieve exceptional performance in this domain, their outputs often lack interpretability, limiting trust and usability for researchers and end-users alike. In this work, we present an interpretable framework for music auto-tagging that leverages groups of musically meaningful multimodal features, derived from signal processing, deep learning, ontology engineering, and natural language processing. To enhance interpretability, we cluster features semantically and employ a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17233","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/2505.17233/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":"2505.17233","created_at":"2026-05-28T01:04:28.158721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17233v3","created_at":"2026-05-28T01:04:28.158721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17233","created_at":"2026-05-28T01:04:28.158721+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QI3V4EC5R6Y","created_at":"2026-05-28T01:04:28.158721+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QI3V4EC5R6Y4FFT","created_at":"2026-05-28T01:04:28.158721+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QI3V4EC","created_at":"2026-05-28T01:04:28.158721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QI3V4EC5R6Y4FFTGG5W6HRQQZ","json":"https://pith.science/pith/2QI3V4EC5R6Y4FFTGG5W6HRQQZ.json","graph_json":"https://pith.science/api/pith-number/2QI3V4EC5R6Y4FFTGG5W6HRQQZ/graph.json","events_json":"https://pith.science/api/pith-number/2QI3V4EC5R6Y4FFTGG5W6HRQQZ/events.json","paper":"https://pith.science/paper/2QI3V4EC"},"agent_actions":{"view_html":"https://pith.science/pith/2QI3V4EC5R6Y4FFTGG5W6HRQQZ","download_json":"https://pith.science/pith/2QI3V4EC5R6Y4FFTGG5W6HRQQZ.json","view_paper":"https://pith.science/paper/2QI3V4EC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17233&json=true","fetch_graph":"https://pith.science/api/pith-number/2QI3V4EC5R6Y4FFTGG5W6HRQQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2QI3V4EC5R6Y4FFTGG5W6HRQQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QI3V4EC5R6Y4FFTGG5W6HRQQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QI3V4EC5R6Y4FFTGG5W6HRQQZ/action/storage_attestation","attest_author":"https://pith.science/pith/2QI3V4EC5R6Y4FFTGG5W6HRQQZ/action/author_attestation","sign_citation":"https://pith.science/pith/2QI3V4EC5R6Y4FFTGG5W6HRQQZ/action/citation_signature","submit_replication":"https://pith.science/pith/2QI3V4EC5R6Y4FFTGG5W6HRQQZ/action/replication_record"}},"created_at":"2026-05-28T01:04:28.158721+00:00","updated_at":"2026-05-28T01:04:28.158721+00:00"}