{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IYAX33LU5LH3K6COKVUNNH4OOA","short_pith_number":"pith:IYAX33LU","schema_version":"1.0","canonical_sha256":"46017ded74eacfb5784e5568d69f8e70151bb6ac72d687fc4a2a8ef322437393","source":{"kind":"arxiv","id":"2507.12996","version":1},"attestation_state":"computed","paper":{"title":"Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Gabriel Meseguer-Brocal, Mathieu Lagrange, Romain Hennequin, Vincent Lostanlen, Yuexuan Kong","submitted_at":"2025-07-17T11:13:11Z","abstract_excerpt":"Contrastive learning and equivariant learning are effective methods for self-supervised learning (SSL) for audio content analysis. Yet, their application to music information retrieval (MIR) faces a dilemma: the former is more effective on tagging (e.g., instrument recognition) but less effective on structured prediction (e.g., tonality estimation); The latter can match supervised methods on the specific task it is designed for, but it does not generalize well to other tasks. In this article, we adopt a best-of-both-worlds approach by training a deep neural network on both kinds of pretext tas"},"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":"2507.12996","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T11:13:11Z","cross_cats_sorted":[],"title_canon_sha256":"cf59e166983e9cdf11ce2bda539da8380d6687929e8ab9c3170a207bc979d37c","abstract_canon_sha256":"45914787e732afc80fc3a0bb292f0a7d0cc76962f8022d3276042e3ee3739e94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:42.886787Z","signature_b64":"NvezvEcTkIssudqnpxlEabMFuxqHMtgjkYjJGQLDG4WI8lhRUddmOy/KjL7/icu57NUkM/KQTJJolkv0S4rTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46017ded74eacfb5784e5568d69f8e70151bb6ac72d687fc4a2a8ef322437393","last_reissued_at":"2026-07-05T11:38:42.886269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:42.886269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Gabriel Meseguer-Brocal, Mathieu Lagrange, Romain Hennequin, Vincent Lostanlen, Yuexuan Kong","submitted_at":"2025-07-17T11:13:11Z","abstract_excerpt":"Contrastive learning and equivariant learning are effective methods for self-supervised learning (SSL) for audio content analysis. Yet, their application to music information retrieval (MIR) faces a dilemma: the former is more effective on tagging (e.g., instrument recognition) but less effective on structured prediction (e.g., tonality estimation); The latter can match supervised methods on the specific task it is designed for, but it does not generalize well to other tasks. In this article, we adopt a best-of-both-worlds approach by training a deep neural network on both kinds of pretext tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12996","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/2507.12996/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":"2507.12996","created_at":"2026-07-05T11:38:42.886340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12996v1","created_at":"2026-07-05T11:38:42.886340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12996","created_at":"2026-07-05T11:38:42.886340+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYAX33LU5LH3","created_at":"2026-07-05T11:38:42.886340+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYAX33LU5LH3K6CO","created_at":"2026-07-05T11:38:42.886340+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYAX33LU","created_at":"2026-07-05T11:38:42.886340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA","json":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA.json","graph_json":"https://pith.science/api/pith-number/IYAX33LU5LH3K6COKVUNNH4OOA/graph.json","events_json":"https://pith.science/api/pith-number/IYAX33LU5LH3K6COKVUNNH4OOA/events.json","paper":"https://pith.science/paper/IYAX33LU"},"agent_actions":{"view_html":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA","download_json":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA.json","view_paper":"https://pith.science/paper/IYAX33LU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12996&json=true","fetch_graph":"https://pith.science/api/pith-number/IYAX33LU5LH3K6COKVUNNH4OOA/graph.json","fetch_events":"https://pith.science/api/pith-number/IYAX33LU5LH3K6COKVUNNH4OOA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA/action/storage_attestation","attest_author":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA/action/author_attestation","sign_citation":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA/action/citation_signature","submit_replication":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA/action/replication_record"}},"created_at":"2026-07-05T11:38:42.886340+00:00","updated_at":"2026-07-05T11:38:42.886340+00:00"}