{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KSQRYU73PO2BNKXBILN2KAJQM5","short_pith_number":"pith:KSQRYU73","schema_version":"1.0","canonical_sha256":"54a11c53fb7bb416aae142dba50130677e513651dd715893f1795ccea0bc1937","source":{"kind":"arxiv","id":"2311.03318","version":1},"attestation_state":"computed","paper":{"title":"A Foundation Model for Music Informatics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Duc Le, Minz Won, Yun-Ning Hung","submitted_at":"2023-11-06T18:12:27Z","abstract_excerpt":"This paper investigates foundation models tailored for music informatics, a domain currently challenged by the scarcity of labeled data and generalization issues. To this end, we conduct an in-depth comparative study among various foundation model variants, examining key determinants such as model architectures, tokenization methods, temporal resolution, data, and model scalability. This research aims to bridge the existing knowledge gap by elucidating how these individual factors contribute to the success of foundation models in music informatics. Employing a careful evaluation framework, we "},"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":"2311.03318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-06T18:12:27Z","cross_cats_sorted":["cs.IR","eess.AS"],"title_canon_sha256":"c87313f82eb889584df565492ccc0a0670505ae57def4b2a3fa38a3727bd73df","abstract_canon_sha256":"fe3efec20b81975b4ee4b51cc48bfcb5e40b358323f7089254989602f2cbee33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:39.823789Z","signature_b64":"rqFgVEld1ZxpdBX4fwz+TnppYEEVZeSJ10vYUp4Ff8C95+tvrZdcJaq/Taa8OZV7QQa5NsirXnX7ZGB6oL0hBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54a11c53fb7bb416aae142dba50130677e513651dd715893f1795ccea0bc1937","last_reissued_at":"2026-07-05T07:09:39.823194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:39.823194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Foundation Model for Music Informatics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Duc Le, Minz Won, Yun-Ning Hung","submitted_at":"2023-11-06T18:12:27Z","abstract_excerpt":"This paper investigates foundation models tailored for music informatics, a domain currently challenged by the scarcity of labeled data and generalization issues. To this end, we conduct an in-depth comparative study among various foundation model variants, examining key determinants such as model architectures, tokenization methods, temporal resolution, data, and model scalability. This research aims to bridge the existing knowledge gap by elucidating how these individual factors contribute to the success of foundation models in music informatics. Employing a careful evaluation framework, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03318","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/2311.03318/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":"2311.03318","created_at":"2026-07-05T07:09:39.823257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.03318v1","created_at":"2026-07-05T07:09:39.823257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03318","created_at":"2026-07-05T07:09:39.823257+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSQRYU73PO2B","created_at":"2026-07-05T07:09:39.823257+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSQRYU73PO2BNKXB","created_at":"2026-07-05T07:09:39.823257+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSQRYU73","created_at":"2026-07-05T07:09:39.823257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.03190","citing_title":"Expectation and Acoustic Neural Network Representations Enhance Music Identification from Brain Activity","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20847","citing_title":"Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23077","citing_title":"Adopting State-of-the-Art Pretrained Audio Representations for Music Recommender Systems","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSQRYU73PO2BNKXBILN2KAJQM5","json":"https://pith.science/pith/KSQRYU73PO2BNKXBILN2KAJQM5.json","graph_json":"https://pith.science/api/pith-number/KSQRYU73PO2BNKXBILN2KAJQM5/graph.json","events_json":"https://pith.science/api/pith-number/KSQRYU73PO2BNKXBILN2KAJQM5/events.json","paper":"https://pith.science/paper/KSQRYU73"},"agent_actions":{"view_html":"https://pith.science/pith/KSQRYU73PO2BNKXBILN2KAJQM5","download_json":"https://pith.science/pith/KSQRYU73PO2BNKXBILN2KAJQM5.json","view_paper":"https://pith.science/paper/KSQRYU73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.03318&json=true","fetch_graph":"https://pith.science/api/pith-number/KSQRYU73PO2BNKXBILN2KAJQM5/graph.json","fetch_events":"https://pith.science/api/pith-number/KSQRYU73PO2BNKXBILN2KAJQM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSQRYU73PO2BNKXBILN2KAJQM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSQRYU73PO2BNKXBILN2KAJQM5/action/storage_attestation","attest_author":"https://pith.science/pith/KSQRYU73PO2BNKXBILN2KAJQM5/action/author_attestation","sign_citation":"https://pith.science/pith/KSQRYU73PO2BNKXBILN2KAJQM5/action/citation_signature","submit_replication":"https://pith.science/pith/KSQRYU73PO2BNKXBILN2KAJQM5/action/replication_record"}},"created_at":"2026-07-05T07:09:39.823257+00:00","updated_at":"2026-07-05T07:09:39.823257+00:00"}