{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JB5NOWYFYKWLN46JRAEGS6NRWN","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":"971abc97cd4430e698f96109e65210e2c86e7c4cc57fae140dc41eac91eaf239","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-02T07:08:29Z","title_canon_sha256":"e8bd2c8b1b78a1c36bd2a330c60ad7b99168ab7687a5034b4dbeb741331de93e"},"schema_version":"1.0","source":{"id":"2501.01108","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01108","created_at":"2026-07-05T09:56:39Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01108v2","created_at":"2026-07-05T09:56:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01108","created_at":"2026-07-05T09:56:39Z"},{"alias_kind":"pith_short_12","alias_value":"JB5NOWYFYKWL","created_at":"2026-07-05T09:56:39Z"},{"alias_kind":"pith_short_16","alias_value":"JB5NOWYFYKWLN46J","created_at":"2026-07-05T09:56:39Z"},{"alias_kind":"pith_short_8","alias_value":"JB5NOWYF","created_at":"2026-07-05T09:56:39Z"}],"graph_snapshots":[{"event_id":"sha256:e2c498feb1218e613b0f8bee8d8d66434862b10255d38ac8b9973e8ed0ce381e","target":"graph","created_at":"2026-07-05T09:56:39Z","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/2501.01108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent years have witnessed the success of foundation models pre-trained with self-supervised learning (SSL) in various music informatics understanding tasks, including music tagging, instrument classification, key detection, and more. In this paper, we propose a self-supervised music representation learning model for music understanding. Distinguished from previous studies adopting random projection or existing neural codec, the proposed model, named MuQ, is trained to predict tokens generated by Mel Residual Vector Quantization (Mel-RVQ). Our Mel-RVQ utilizes residual linear projection struc","authors_text":"Haina Zhu, Hangting Chen, Jianwei Yu, Rongzhi Gu, Wei Tan, Xie Chen, Yi Luo, Yizhi Zhou, Ziyang Ma","cross_cats":["cs.AI","cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-02T07:08:29Z","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01108","kind":"arxiv","version":2},"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":"sha256:4a0d78f13fdfc14a744c64120085341fb808ed7760d8d0ad66d459a86da72209","target":"record","created_at":"2026-07-05T09:56:39Z","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":"971abc97cd4430e698f96109e65210e2c86e7c4cc57fae140dc41eac91eaf239","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-02T07:08:29Z","title_canon_sha256":"e8bd2c8b1b78a1c36bd2a330c60ad7b99168ab7687a5034b4dbeb741331de93e"},"schema_version":"1.0","source":{"id":"2501.01108","kind":"arxiv","version":2}},"canonical_sha256":"487ad75b05c2acb6f3c988086979b1b373a9aa9fcf5bdba06c26b3da09952921","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"487ad75b05c2acb6f3c988086979b1b373a9aa9fcf5bdba06c26b3da09952921","first_computed_at":"2026-07-05T09:56:39.033076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:39.033076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fGs/LuvvXM0yA20/xcUipytsdjjCxHme4nwvdyKilUWJtXcYN3qBE2YYumgk61ZtzcHstkz+F3xJnhwnkUktAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:39.033596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01108","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a0d78f13fdfc14a744c64120085341fb808ed7760d8d0ad66d459a86da72209","sha256:e2c498feb1218e613b0f8bee8d8d66434862b10255d38ac8b9973e8ed0ce381e"],"state_sha256":"54bc59e5a0c6e266b9a534bc3e577edd2ba490f7b284a070f32099d8a36b78b3"}