{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VVSHEGBXSKX3QJGA2JPCHEOBUI","short_pith_number":"pith:VVSHEGBX","schema_version":"1.0","canonical_sha256":"ad6472183792afb824c0d25e2391c1a20f4daa8dfd2309adb2886872daf67018","source":{"kind":"arxiv","id":"2507.22995","version":1},"attestation_state":"computed","paper":{"title":"Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Juan Pablo Bello, Julia Wilkins, Magdalena Fuentes, Sivan Ding","submitted_at":"2025-07-30T18:00:09Z","abstract_excerpt":"Recent advances in self-supervised learning (SSL) methods offer a range of strategies for capturing useful representations from music audio without the need for labeled data. While some techniques focus on preserving comprehensive details through reconstruction, others favor semantic structure via contrastive objectives. Few works examine the interaction between these paradigms in a unified SSL framework. In this work, we propose a multi-view SSL framework for disentangling music audio representations that combines contrastive and reconstructive objectives. The architecture is designed to prom"},"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":"2507.22995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T18:00:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"261f8646f6602ef0346348427ad965db7ea3a2d11f5d40a688a1b5dc36b72480","abstract_canon_sha256":"fcf05e735a012f991b64a40ff1de28ce4d8ebb495f38b24c5b9ccd30b582ba52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:24.206719Z","signature_b64":"PA7udYWwZ8yal1gtdjSfzkvuuu0M1bxuo7AuT2Jt4QjGTQYmrW7H5euBNNYXMcmRed/KHyO1V2hhbcoRIM4oDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad6472183792afb824c0d25e2391c1a20f4daa8dfd2309adb2886872daf67018","last_reissued_at":"2026-07-05T11:46:24.206205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:24.206205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Juan Pablo Bello, Julia Wilkins, Magdalena Fuentes, Sivan Ding","submitted_at":"2025-07-30T18:00:09Z","abstract_excerpt":"Recent advances in self-supervised learning (SSL) methods offer a range of strategies for capturing useful representations from music audio without the need for labeled data. While some techniques focus on preserving comprehensive details through reconstruction, others favor semantic structure via contrastive objectives. Few works examine the interaction between these paradigms in a unified SSL framework. In this work, we propose a multi-view SSL framework for disentangling music audio representations that combines contrastive and reconstructive objectives. The architecture is designed to prom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22995","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/2507.22995/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":"2507.22995","created_at":"2026-07-05T11:46:24.206265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22995v1","created_at":"2026-07-05T11:46:24.206265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22995","created_at":"2026-07-05T11:46:24.206265+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVSHEGBXSKX3","created_at":"2026-07-05T11:46:24.206265+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVSHEGBXSKX3QJGA","created_at":"2026-07-05T11:46:24.206265+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVSHEGBX","created_at":"2026-07-05T11:46:24.206265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.20759","citing_title":"Controllable Embedding Transformation for Mood-Guided Music Retrieval","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VVSHEGBXSKX3QJGA2JPCHEOBUI","json":"https://pith.science/pith/VVSHEGBXSKX3QJGA2JPCHEOBUI.json","graph_json":"https://pith.science/api/pith-number/VVSHEGBXSKX3QJGA2JPCHEOBUI/graph.json","events_json":"https://pith.science/api/pith-number/VVSHEGBXSKX3QJGA2JPCHEOBUI/events.json","paper":"https://pith.science/paper/VVSHEGBX"},"agent_actions":{"view_html":"https://pith.science/pith/VVSHEGBXSKX3QJGA2JPCHEOBUI","download_json":"https://pith.science/pith/VVSHEGBXSKX3QJGA2JPCHEOBUI.json","view_paper":"https://pith.science/paper/VVSHEGBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22995&json=true","fetch_graph":"https://pith.science/api/pith-number/VVSHEGBXSKX3QJGA2JPCHEOBUI/graph.json","fetch_events":"https://pith.science/api/pith-number/VVSHEGBXSKX3QJGA2JPCHEOBUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVSHEGBXSKX3QJGA2JPCHEOBUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVSHEGBXSKX3QJGA2JPCHEOBUI/action/storage_attestation","attest_author":"https://pith.science/pith/VVSHEGBXSKX3QJGA2JPCHEOBUI/action/author_attestation","sign_citation":"https://pith.science/pith/VVSHEGBXSKX3QJGA2JPCHEOBUI/action/citation_signature","submit_replication":"https://pith.science/pith/VVSHEGBXSKX3QJGA2JPCHEOBUI/action/replication_record"}},"created_at":"2026-07-05T11:46:24.206265+00:00","updated_at":"2026-07-05T11:46:24.206265+00:00"}