{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BJZ6AH4N3GV3A3E5Q2J7TKCKJ7","short_pith_number":"pith:BJZ6AH4N","schema_version":"1.0","canonical_sha256":"0a73e01f8dd9abb06c9d8693f9a84a4fe2bc69b5cb78ce7cdc2cb8146a4fa2ce","source":{"kind":"arxiv","id":"2411.02711","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Multi-View Learning for Disentangled Music Audio Representations","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":"2024-11-05T01:21:28Z","abstract_excerpt":"Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view redundancy to create pretext tasks. However, these approaches often produce entangled representations and lose view-specific information. We propose a novel self-supervised multi-view learning framework for audio designed to incentivize separation between private and shared representation spaces. A case study on audio disentanglement in a controlled setting demons"},"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":"2411.02711","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-05T01:21:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7804ef270fe1818d44a65fffb7c78cac5d647d79fb076f8519759f43c5338817","abstract_canon_sha256":"ad6723b840e13350c31d13089b3e0b82bc8338bbbdd6cc16836e0d7229973714"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:16.708953Z","signature_b64":"qDLeE+yOUpMdbcjuHo5i+V/ntZQiTKpwCgj9g6XLmF4/6AQWbt2GuowGoVoU/3ufasm7JZmtgy6n3nBA8ZUgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a73e01f8dd9abb06c9d8693f9a84a4fe2bc69b5cb78ce7cdc2cb8146a4fa2ce","last_reissued_at":"2026-07-05T09:31:16.708560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:16.708560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Multi-View Learning for Disentangled Music Audio Representations","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":"2024-11-05T01:21:28Z","abstract_excerpt":"Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view redundancy to create pretext tasks. However, these approaches often produce entangled representations and lose view-specific information. We propose a novel self-supervised multi-view learning framework for audio designed to incentivize separation between private and shared representation spaces. A case study on audio disentanglement in a controlled setting demons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02711","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/2411.02711/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":"2411.02711","created_at":"2026-07-05T09:31:16.708612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02711v1","created_at":"2026-07-05T09:31:16.708612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02711","created_at":"2026-07-05T09:31:16.708612+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJZ6AH4N3GV3","created_at":"2026-07-05T09:31:16.708612+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJZ6AH4N3GV3A3E5","created_at":"2026-07-05T09:31:16.708612+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJZ6AH4N","created_at":"2026-07-05T09:31:16.708612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22995","citing_title":"Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7","json":"https://pith.science/pith/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7.json","graph_json":"https://pith.science/api/pith-number/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7/graph.json","events_json":"https://pith.science/api/pith-number/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7/events.json","paper":"https://pith.science/paper/BJZ6AH4N"},"agent_actions":{"view_html":"https://pith.science/pith/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7","download_json":"https://pith.science/pith/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7.json","view_paper":"https://pith.science/paper/BJZ6AH4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02711&json=true","fetch_graph":"https://pith.science/api/pith-number/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7/action/storage_attestation","attest_author":"https://pith.science/pith/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7/action/author_attestation","sign_citation":"https://pith.science/pith/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7/action/citation_signature","submit_replication":"https://pith.science/pith/BJZ6AH4N3GV3A3E5Q2J7TKCKJ7/action/replication_record"}},"created_at":"2026-07-05T09:31:16.708612+00:00","updated_at":"2026-07-05T09:31:16.708612+00:00"}