{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2V3I32T7TMB7N4RRU6DQDZFAP7","short_pith_number":"pith:2V3I32T7","schema_version":"1.0","canonical_sha256":"d5768dea7f9b03f6f231a78701e4a07fe3124d442556220859446a579774781c","source":{"kind":"arxiv","id":"2507.13572","version":1},"attestation_state":"computed","paper":{"title":"Temporal Adaptation of Pre-trained Foundation Models for Music Structure Analysis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haonan Chen, Jitong Chen, Ju-Chiang Wang, Yixiao Zhang","submitted_at":"2025-07-17T23:25:58Z","abstract_excerpt":"Audio-based music structure analysis (MSA) is an essential task in Music Information Retrieval that remains challenging due to the complexity and variability of musical form. Recent advances highlight the potential of fine-tuning pre-trained music foundation models for MSA tasks. However, these models are typically trained with high temporal feature resolution and short audio windows, which limits their efficiency and introduces bias when applied to long-form audio. This paper presents a temporal adaptation approach for fine-tuning music foundation models tailored to MSA. Our method enables ef"},"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":"2507.13572","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T23:25:58Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"48b7ae8666c795b13f35acd64db318e4693e2fcce200422a8d0097e1b4e0a564","abstract_canon_sha256":"ff625978951f18a1b5f5c40fa661c8cf3c253360099eb93750c8f60af4ca5535"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:19.417582Z","signature_b64":"bDcFmo2OPR05POufdRqvyVcVTdbBj67sQnIGrhQjSLDzhW2yX5xCr6e7+OhS+8gxn+TRXq4/sPV4LHgNTljVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5768dea7f9b03f6f231a78701e4a07fe3124d442556220859446a579774781c","last_reissued_at":"2026-07-05T11:39:19.417132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:19.417132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Adaptation of Pre-trained Foundation Models for Music Structure Analysis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haonan Chen, Jitong Chen, Ju-Chiang Wang, Yixiao Zhang","submitted_at":"2025-07-17T23:25:58Z","abstract_excerpt":"Audio-based music structure analysis (MSA) is an essential task in Music Information Retrieval that remains challenging due to the complexity and variability of musical form. Recent advances highlight the potential of fine-tuning pre-trained music foundation models for MSA tasks. However, these models are typically trained with high temporal feature resolution and short audio windows, which limits their efficiency and introduces bias when applied to long-form audio. This paper presents a temporal adaptation approach for fine-tuning music foundation models tailored to MSA. Our method enables ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13572","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/2507.13572/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":"2507.13572","created_at":"2026-07-05T11:39:19.417186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13572v1","created_at":"2026-07-05T11:39:19.417186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13572","created_at":"2026-07-05T11:39:19.417186+00:00"},{"alias_kind":"pith_short_12","alias_value":"2V3I32T7TMB7","created_at":"2026-07-05T11:39:19.417186+00:00"},{"alias_kind":"pith_short_16","alias_value":"2V3I32T7TMB7N4RR","created_at":"2026-07-05T11:39:19.417186+00:00"},{"alias_kind":"pith_short_8","alias_value":"2V3I32T7","created_at":"2026-07-05T11:39:19.417186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.02797","citing_title":"SongFormer: Scaling Music Structure Analysis with Heterogeneous Supervision","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2V3I32T7TMB7N4RRU6DQDZFAP7","json":"https://pith.science/pith/2V3I32T7TMB7N4RRU6DQDZFAP7.json","graph_json":"https://pith.science/api/pith-number/2V3I32T7TMB7N4RRU6DQDZFAP7/graph.json","events_json":"https://pith.science/api/pith-number/2V3I32T7TMB7N4RRU6DQDZFAP7/events.json","paper":"https://pith.science/paper/2V3I32T7"},"agent_actions":{"view_html":"https://pith.science/pith/2V3I32T7TMB7N4RRU6DQDZFAP7","download_json":"https://pith.science/pith/2V3I32T7TMB7N4RRU6DQDZFAP7.json","view_paper":"https://pith.science/paper/2V3I32T7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13572&json=true","fetch_graph":"https://pith.science/api/pith-number/2V3I32T7TMB7N4RRU6DQDZFAP7/graph.json","fetch_events":"https://pith.science/api/pith-number/2V3I32T7TMB7N4RRU6DQDZFAP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2V3I32T7TMB7N4RRU6DQDZFAP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2V3I32T7TMB7N4RRU6DQDZFAP7/action/storage_attestation","attest_author":"https://pith.science/pith/2V3I32T7TMB7N4RRU6DQDZFAP7/action/author_attestation","sign_citation":"https://pith.science/pith/2V3I32T7TMB7N4RRU6DQDZFAP7/action/citation_signature","submit_replication":"https://pith.science/pith/2V3I32T7TMB7N4RRU6DQDZFAP7/action/replication_record"}},"created_at":"2026-07-05T11:39:19.417186+00:00","updated_at":"2026-07-05T11:39:19.417186+00:00"}