{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:56YSDYNWAZK667XKRTVMFG3J24","short_pith_number":"pith:56YSDYNW","schema_version":"1.0","canonical_sha256":"efb121e1b60655ef7eea8ceac29b69d73bb4060adbf4262e438d32fa9ed577c7","source":{"kind":"arxiv","id":"2501.12907","version":2},"attestation_state":"computed","paper":{"title":"S-KEY: Self-supervised Learning of Major and Minor Keys from Audio","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Gabriel Meseguer-Brocal, Mathieu Lagrange, Romain Hennequin, Vincent Lostanlen, Yuexuan Kong","submitted_at":"2025-01-22T14:35:37Z","abstract_excerpt":"STONE, the current method in self-supervised learning for tonality estimation in music signals, cannot distinguish relative keys, such as C major versus A minor. In this article, we extend the neural network architecture and learning objective of STONE to perform self-supervised learning of major and minor keys (S-KEY). Our main contribution is an auxiliary pretext task to STONE, formulated using transposition-invariant chroma features as a source of pseudo-labels. S-KEY matches the supervised state of the art in tonality estimation on FMAKv2 and GTZAN datasets while requiring no human annotat"},"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":"2501.12907","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-22T14:35:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"47751935056cab18f090a8f5904ee8d0b7c4f57fece4dfe744a0e1cdce6b160c","abstract_canon_sha256":"8679043177c25118eb4f16c5f86e95ba4cb4713128ee87603bf222eaea2dbc31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:41.431695Z","signature_b64":"9c7R5KTzth1x5tvIm4YypZ3QVaxsiuvBdiMStBML58jz2WVDEdjC2VlBUCgxWYqiocFEZac1cE5lLVN2t04iAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efb121e1b60655ef7eea8ceac29b69d73bb4060adbf4262e438d32fa9ed577c7","last_reissued_at":"2026-07-05T11:25:41.431353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:41.431353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"S-KEY: Self-supervised Learning of Major and Minor Keys from Audio","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Gabriel Meseguer-Brocal, Mathieu Lagrange, Romain Hennequin, Vincent Lostanlen, Yuexuan Kong","submitted_at":"2025-01-22T14:35:37Z","abstract_excerpt":"STONE, the current method in self-supervised learning for tonality estimation in music signals, cannot distinguish relative keys, such as C major versus A minor. In this article, we extend the neural network architecture and learning objective of STONE to perform self-supervised learning of major and minor keys (S-KEY). Our main contribution is an auxiliary pretext task to STONE, formulated using transposition-invariant chroma features as a source of pseudo-labels. S-KEY matches the supervised state of the art in tonality estimation on FMAKv2 and GTZAN datasets while requiring no human annotat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12907","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/2501.12907/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":"2501.12907","created_at":"2026-07-05T11:25:41.431409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12907v2","created_at":"2026-07-05T11:25:41.431409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12907","created_at":"2026-07-05T11:25:41.431409+00:00"},{"alias_kind":"pith_short_12","alias_value":"56YSDYNWAZK6","created_at":"2026-07-05T11:25:41.431409+00:00"},{"alias_kind":"pith_short_16","alias_value":"56YSDYNWAZK667XK","created_at":"2026-07-05T11:25:41.431409+00:00"},{"alias_kind":"pith_short_8","alias_value":"56YSDYNW","created_at":"2026-07-05T11:25:41.431409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.11899","citing_title":"Do Text-to-Music Models Really Follow Instructions? A Counterfactual Evaluation of Key and Beat Grouping","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/56YSDYNWAZK667XKRTVMFG3J24","json":"https://pith.science/pith/56YSDYNWAZK667XKRTVMFG3J24.json","graph_json":"https://pith.science/api/pith-number/56YSDYNWAZK667XKRTVMFG3J24/graph.json","events_json":"https://pith.science/api/pith-number/56YSDYNWAZK667XKRTVMFG3J24/events.json","paper":"https://pith.science/paper/56YSDYNW"},"agent_actions":{"view_html":"https://pith.science/pith/56YSDYNWAZK667XKRTVMFG3J24","download_json":"https://pith.science/pith/56YSDYNWAZK667XKRTVMFG3J24.json","view_paper":"https://pith.science/paper/56YSDYNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12907&json=true","fetch_graph":"https://pith.science/api/pith-number/56YSDYNWAZK667XKRTVMFG3J24/graph.json","fetch_events":"https://pith.science/api/pith-number/56YSDYNWAZK667XKRTVMFG3J24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56YSDYNWAZK667XKRTVMFG3J24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56YSDYNWAZK667XKRTVMFG3J24/action/storage_attestation","attest_author":"https://pith.science/pith/56YSDYNWAZK667XKRTVMFG3J24/action/author_attestation","sign_citation":"https://pith.science/pith/56YSDYNWAZK667XKRTVMFG3J24/action/citation_signature","submit_replication":"https://pith.science/pith/56YSDYNWAZK667XKRTVMFG3J24/action/replication_record"}},"created_at":"2026-07-05T11:25:41.431409+00:00","updated_at":"2026-07-05T11:25:41.431409+00:00"}