{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IYAX33LU5LH3K6COKVUNNH4OOA","short_pith_number":"pith:IYAX33LU","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"},"canonical_sha256":"46017ded74eacfb5784e5568d69f8e70151bb6ac72d687fc4a2a8ef322437393","source":{"kind":"arxiv","id":"2507.12996","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12996","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12996v1","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12996","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"pith_short_12","alias_value":"IYAX33LU5LH3","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"pith_short_16","alias_value":"IYAX33LU5LH3K6CO","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"pith_short_8","alias_value":"IYAX33LU","created_at":"2026-07-05T11:38:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IYAX33LU5LH3K6COKVUNNH4OOA","target":"record","payload":{"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"},"canonical_sha256":"46017ded74eacfb5784e5568d69f8e70151bb6ac72d687fc4a2a8ef322437393","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"},"source_kind":"arxiv","source_id":"2507.12996","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:38:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kc+G1pQNgzrrWS8dwsw4+XfTXwJYWFM8WddOlE3yq3Nx4q7CZKRoyHFe3o5ocxsn6ux5d88CUT88+4mlFspBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:11:06.034318Z"},"content_sha256":"7886e00955f9d5a9516fe5cb561985d6dba9ce5698bc0a79fc2c8768d819138a","schema_version":"1.0","event_id":"sha256:7886e00955f9d5a9516fe5cb561985d6dba9ce5698bc0a79fc2c8768d819138a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IYAX33LU5LH3K6COKVUNNH4OOA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:38:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YKFFN4PUPiR4YvKGag+aF2LhNjPA9QTJvbmhk980N0Ym0Y3e7L5LJhpKvC5WBtgJRo60iRTUdcMiGo+Kgw8bBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:11:06.034834Z"},"content_sha256":"d3d7c7fa12e4ee6115ce985170dc017fb05f55803bd32221aa2a10414416157a","schema_version":"1.0","event_id":"sha256:d3d7c7fa12e4ee6115ce985170dc017fb05f55803bd32221aa2a10414416157a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA/bundle.json","state_url":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IYAX33LU5LH3K6COKVUNNH4OOA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T16:11:06Z","links":{"resolver":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA","bundle":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA/bundle.json","state":"https://pith.science/pith/IYAX33LU5LH3K6COKVUNNH4OOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IYAX33LU5LH3K6COKVUNNH4OOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IYAX33LU5LH3K6COKVUNNH4OOA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"45914787e732afc80fc3a0bb292f0a7d0cc76962f8022d3276042e3ee3739e94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T11:13:11Z","title_canon_sha256":"cf59e166983e9cdf11ce2bda539da8380d6687929e8ab9c3170a207bc979d37c"},"schema_version":"1.0","source":{"id":"2507.12996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12996","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12996v1","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12996","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"pith_short_12","alias_value":"IYAX33LU5LH3","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"pith_short_16","alias_value":"IYAX33LU5LH3K6CO","created_at":"2026-07-05T11:38:42Z"},{"alias_kind":"pith_short_8","alias_value":"IYAX33LU","created_at":"2026-07-05T11:38:42Z"}],"graph_snapshots":[{"event_id":"sha256:d3d7c7fa12e4ee6115ce985170dc017fb05f55803bd32221aa2a10414416157a","target":"graph","created_at":"2026-07-05T11:38:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.12996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gabriel Meseguer-Brocal, Mathieu Lagrange, Romain Hennequin, Vincent Lostanlen, Yuexuan Kong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T11:13:11Z","title":"Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12996","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7886e00955f9d5a9516fe5cb561985d6dba9ce5698bc0a79fc2c8768d819138a","target":"record","created_at":"2026-07-05T11:38:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"45914787e732afc80fc3a0bb292f0a7d0cc76962f8022d3276042e3ee3739e94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T11:13:11Z","title_canon_sha256":"cf59e166983e9cdf11ce2bda539da8380d6687929e8ab9c3170a207bc979d37c"},"schema_version":"1.0","source":{"id":"2507.12996","kind":"arxiv","version":1}},"canonical_sha256":"46017ded74eacfb5784e5568d69f8e70151bb6ac72d687fc4a2a8ef322437393","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46017ded74eacfb5784e5568d69f8e70151bb6ac72d687fc4a2a8ef322437393","first_computed_at":"2026-07-05T11:38:42.886269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:42.886269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NvezvEcTkIssudqnpxlEabMFuxqHMtgjkYjJGQLDG4WI8lhRUddmOy/KjL7/icu57NUkM/KQTJJolkv0S4rTCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:42.886787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7886e00955f9d5a9516fe5cb561985d6dba9ce5698bc0a79fc2c8768d819138a","sha256:d3d7c7fa12e4ee6115ce985170dc017fb05f55803bd32221aa2a10414416157a"],"state_sha256":"f79e546efe6cbf22f35733371b2ce3f783eb55454946fa77a18dfdd43cd0f1fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LD/mZioDuoHv1jcuFCufUwUxHQVPd6aJ51ekazb57uzorfJMPD/7/ITfM1o2mwYsAFrN+8X19IQ349Y+bq2tAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:11:06.040687Z","bundle_sha256":"b923fb21b7f841770abb7f5166cfe4aaae8dd79fe54ab0002ba089caf4945680"}}