{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CFSNBJ25DW74HTADSEZDKLX2Y5","short_pith_number":"pith:CFSNBJ25","schema_version":"1.0","canonical_sha256":"1164d0a75d1dbfc3cc039132352efac74126b6d9188bacd61b42831ec45e659d","source":{"kind":"arxiv","id":"2103.09410","version":2},"attestation_state":"computed","paper":{"title":"Contrastive Learning of Musical Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Janne Spijkervet, John Ashley Burgoyne","submitted_at":"2021-03-17T02:53:55Z","abstract_excerpt":"While deep learning has enabled great advances in many areas of music, labeled music datasets remain especially hard, expensive, and time-consuming to create. In this work, we introduce SimCLR to the music domain and contribute a large chain of audio data augmentations to form a simple framework for self-supervised, contrastive learning of musical representations: CLMR. This approach works on raw time-domain music data and requires no labels to learn useful representations. We evaluate CLMR in the downstream task of music classification on the MagnaTagATune and Million Song datasets and presen"},"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":"2103.09410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-03-17T02:53:55Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"9d2599b2440c2d83e5957c94597669bd5e51fcd135b7ff6d8d48e7de6b596c18","abstract_canon_sha256":"7402be0e2c32babcf296a65e2cf7d2d38c39d8b679ba2d77053da1cd3df8ed2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:14.181503Z","signature_b64":"xQsVxZy6yX3iA8bQqtxAoOKT7Is7rxcHYwSAN0eH7P1yORXzkHryxnC1rvuJy0g2AtIMx/SiD3HMEnT31F2pAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1164d0a75d1dbfc3cc039132352efac74126b6d9188bacd61b42831ec45e659d","last_reissued_at":"2026-07-05T03:17:14.181045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:14.181045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Learning of Musical Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Janne Spijkervet, John Ashley Burgoyne","submitted_at":"2021-03-17T02:53:55Z","abstract_excerpt":"While deep learning has enabled great advances in many areas of music, labeled music datasets remain especially hard, expensive, and time-consuming to create. In this work, we introduce SimCLR to the music domain and contribute a large chain of audio data augmentations to form a simple framework for self-supervised, contrastive learning of musical representations: CLMR. This approach works on raw time-domain music data and requires no labels to learn useful representations. We evaluate CLMR in the downstream task of music classification on the MagnaTagATune and Million Song datasets and presen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09410","kind":"arxiv","version":2},"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/2103.09410/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":"2103.09410","created_at":"2026-07-05T03:17:14.181107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09410v2","created_at":"2026-07-05T03:17:14.181107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09410","created_at":"2026-07-05T03:17:14.181107+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFSNBJ25DW74","created_at":"2026-07-05T03:17:14.181107+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFSNBJ25DW74HTAD","created_at":"2026-07-05T03:17:14.181107+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFSNBJ25","created_at":"2026-07-05T03:17:14.181107+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27346","citing_title":"MERIT: Learning Disentangled Music Representations for Audio Similarity","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03929","citing_title":"PHALAR: Phasors for Learned Musical Audio Representations","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03929","citing_title":"PHALAR: Phasors for Learned Musical Audio Representations","ref_index":6,"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":80,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07090","citing_title":"Leveraging Artist Catalogs for Cold-Start Music Recommendation","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03929","citing_title":"PHALAR: Phasors for Learned Musical Audio Representations","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFSNBJ25DW74HTADSEZDKLX2Y5","json":"https://pith.science/pith/CFSNBJ25DW74HTADSEZDKLX2Y5.json","graph_json":"https://pith.science/api/pith-number/CFSNBJ25DW74HTADSEZDKLX2Y5/graph.json","events_json":"https://pith.science/api/pith-number/CFSNBJ25DW74HTADSEZDKLX2Y5/events.json","paper":"https://pith.science/paper/CFSNBJ25"},"agent_actions":{"view_html":"https://pith.science/pith/CFSNBJ25DW74HTADSEZDKLX2Y5","download_json":"https://pith.science/pith/CFSNBJ25DW74HTADSEZDKLX2Y5.json","view_paper":"https://pith.science/paper/CFSNBJ25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09410&json=true","fetch_graph":"https://pith.science/api/pith-number/CFSNBJ25DW74HTADSEZDKLX2Y5/graph.json","fetch_events":"https://pith.science/api/pith-number/CFSNBJ25DW74HTADSEZDKLX2Y5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFSNBJ25DW74HTADSEZDKLX2Y5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFSNBJ25DW74HTADSEZDKLX2Y5/action/storage_attestation","attest_author":"https://pith.science/pith/CFSNBJ25DW74HTADSEZDKLX2Y5/action/author_attestation","sign_citation":"https://pith.science/pith/CFSNBJ25DW74HTADSEZDKLX2Y5/action/citation_signature","submit_replication":"https://pith.science/pith/CFSNBJ25DW74HTADSEZDKLX2Y5/action/replication_record"}},"created_at":"2026-07-05T03:17:14.181107+00:00","updated_at":"2026-07-05T03:17:14.181107+00:00"}