{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZQ7YVWPKSIMBM3JTNWMYCFO7C3","short_pith_number":"pith:ZQ7YVWPK","schema_version":"1.0","canonical_sha256":"cc3f8ad9ea9218166d336d998115df16e58f50cea5ea410b76635fcb45272275","source":{"kind":"arxiv","id":"2506.23873","version":1},"attestation_state":"computed","paper":{"title":"Emergent musical properties of a transformer under contrastive self-supervised learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gabriel Meseguer-Brocal, Mathieu Lagrange, Romain Hennequin, Vincent Lostanlen, Yuexuan Kong","submitted_at":"2025-06-30T14:04:59Z","abstract_excerpt":"In music information retrieval (MIR), contrastive self-supervised learning for general-purpose representation models is effective for global tasks such as automatic tagging. However, for local tasks such as chord estimation, it is widely assumed that contrastively trained general-purpose self-supervised models are inadequate and that more sophisticated SSL is necessary; e.g., masked modeling. Our paper challenges this assumption by revealing the potential of contrastive SSL paired with a transformer in local MIR tasks. We consider a lightweight vision transformer with one-dimensional patches i"},"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":"2506.23873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-30T14:04:59Z","cross_cats_sorted":["cs.IR","cs.LG","eess.AS"],"title_canon_sha256":"ab5ffbb31c90fabd20214aab5f0c980db28d2e606c416a6ff1af9daa98070404","abstract_canon_sha256":"53444a5616419ba9d70d99ab9bace37f76ab436c8b1448750adb40de9e160968"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:29.430060Z","signature_b64":"TRZSDsxb1AeCdFJy0cUkaU8WonC+egX4QdtfYHaXdyiRrvx70PgRddg+vWwaYlQAKE7GtYfJ3fRWbYwL3GsLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc3f8ad9ea9218166d336d998115df16e58f50cea5ea410b76635fcb45272275","last_reissued_at":"2026-07-05T11:29:29.429564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:29.429564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emergent musical properties of a transformer under contrastive self-supervised learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gabriel Meseguer-Brocal, Mathieu Lagrange, Romain Hennequin, Vincent Lostanlen, Yuexuan Kong","submitted_at":"2025-06-30T14:04:59Z","abstract_excerpt":"In music information retrieval (MIR), contrastive self-supervised learning for general-purpose representation models is effective for global tasks such as automatic tagging. However, for local tasks such as chord estimation, it is widely assumed that contrastively trained general-purpose self-supervised models are inadequate and that more sophisticated SSL is necessary; e.g., masked modeling. Our paper challenges this assumption by revealing the potential of contrastive SSL paired with a transformer in local MIR tasks. We consider a lightweight vision transformer with one-dimensional patches i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23873","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/2506.23873/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":"2506.23873","created_at":"2026-07-05T11:29:29.429622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23873v1","created_at":"2026-07-05T11:29:29.429622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23873","created_at":"2026-07-05T11:29:29.429622+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQ7YVWPKSIMB","created_at":"2026-07-05T11:29:29.429622+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQ7YVWPKSIMBM3JT","created_at":"2026-07-05T11:29:29.429622+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQ7YVWPK","created_at":"2026-07-05T11:29:29.429622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23873","citing_title":"Emergent musical properties of a transformer under contrastive self-supervised learning","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQ7YVWPKSIMBM3JTNWMYCFO7C3","json":"https://pith.science/pith/ZQ7YVWPKSIMBM3JTNWMYCFO7C3.json","graph_json":"https://pith.science/api/pith-number/ZQ7YVWPKSIMBM3JTNWMYCFO7C3/graph.json","events_json":"https://pith.science/api/pith-number/ZQ7YVWPKSIMBM3JTNWMYCFO7C3/events.json","paper":"https://pith.science/paper/ZQ7YVWPK"},"agent_actions":{"view_html":"https://pith.science/pith/ZQ7YVWPKSIMBM3JTNWMYCFO7C3","download_json":"https://pith.science/pith/ZQ7YVWPKSIMBM3JTNWMYCFO7C3.json","view_paper":"https://pith.science/paper/ZQ7YVWPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23873&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQ7YVWPKSIMBM3JTNWMYCFO7C3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQ7YVWPKSIMBM3JTNWMYCFO7C3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQ7YVWPKSIMBM3JTNWMYCFO7C3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQ7YVWPKSIMBM3JTNWMYCFO7C3/action/storage_attestation","attest_author":"https://pith.science/pith/ZQ7YVWPKSIMBM3JTNWMYCFO7C3/action/author_attestation","sign_citation":"https://pith.science/pith/ZQ7YVWPKSIMBM3JTNWMYCFO7C3/action/citation_signature","submit_replication":"https://pith.science/pith/ZQ7YVWPKSIMBM3JTNWMYCFO7C3/action/replication_record"}},"created_at":"2026-07-05T11:29:29.429622+00:00","updated_at":"2026-07-05T11:29:29.429622+00:00"}