{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H5DLRUIQV5EP4BTHKKFZ7NH2DX","short_pith_number":"pith:H5DLRUIQ","schema_version":"1.0","canonical_sha256":"3f46b8d110af48fe0667528b9fb4fa1dcafb064423c4671ab9b7a13d987989f9","source":{"kind":"arxiv","id":"2306.00107","version":5},"attestation_state":"computed","paper":{"title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Anton Ragni, Chenghao Xiao, Chenghua Lin, Emmanouil Benetos, Ge Zhang, Gus Xia, Hanzhi Yin, Jie Fu, Norbert Gyenge, Roger Dannenberg, Ruibin Yuan, Ruibo Liu, Wenhao Huang, Wenhu Chen, Xingran Chen, Yemin Shi, Yike Guo, Yinghao Ma, Yizhi Li, Zili Wang","submitted_at":"2023-05-31T18:27:43Z","abstract_excerpt":"Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale data in the fields of vision, text, and speech. Although SSL has been proven effective in speech and audio, its application to music audio has yet to be thoroughly explored. This is partially due to the distinctive challenges associated with modelling musical knowledge, particularly tonal and pitched characteristics of music. To address this research gap, we propose an acoustic Music undERstanding model with large-scale self-supervised Training (MERT), which incorporates"},"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":"2306.00107","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T18:27:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"5ab310e1757a4af25f288eeae1f0448a317e8a98ca867aa5dcff4806d117c5b0","abstract_canon_sha256":"f57ce252c21d63c7944cfff2eb7530c95c9568844784669935dbdbafd7719a7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:23.097561Z","signature_b64":"ISsgZYiVbg0kI+Jmq8njAnAL/1ADl9OrC3E04lXLRpYTDZj4fW1Z6G6UraUiWhOBugxRaEXHvG3UthJDScb+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f46b8d110af48fe0667528b9fb4fa1dcafb064423c4671ab9b7a13d987989f9","last_reissued_at":"2026-07-05T09:54:23.097060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:23.097060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Anton Ragni, Chenghao Xiao, Chenghua Lin, Emmanouil Benetos, Ge Zhang, Gus Xia, Hanzhi Yin, Jie Fu, Norbert Gyenge, Roger Dannenberg, Ruibin Yuan, Ruibo Liu, Wenhao Huang, Wenhu Chen, Xingran Chen, Yemin Shi, Yike Guo, Yinghao Ma, Yizhi Li, Zili Wang","submitted_at":"2023-05-31T18:27:43Z","abstract_excerpt":"Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale data in the fields of vision, text, and speech. Although SSL has been proven effective in speech and audio, its application to music audio has yet to be thoroughly explored. This is partially due to the distinctive challenges associated with modelling musical knowledge, particularly tonal and pitched characteristics of music. To address this research gap, we propose an acoustic Music undERstanding model with large-scale self-supervised Training (MERT), which incorporates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00107","kind":"arxiv","version":5},"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/2306.00107/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":"2306.00107","created_at":"2026-07-05T09:54:23.097119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00107v5","created_at":"2026-07-05T09:54:23.097119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00107","created_at":"2026-07-05T09:54:23.097119+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5DLRUIQV5EP","created_at":"2026-07-05T09:54:23.097119+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5DLRUIQV5EP4BTH","created_at":"2026-07-05T09:54:23.097119+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5DLRUIQ","created_at":"2026-07-05T09:54:23.097119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06929","citing_title":"MADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00387","citing_title":"From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30965","citing_title":"ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27346","citing_title":"MERIT: Learning Disentangled Music Representations for Audio Similarity","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15151","citing_title":"Exploring How Audio Effects Alter Emotion with Foundation Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03190","citing_title":"Expectation and Acoustic Neural Network Representations Enhance Music Identification from Brain Activity","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16181","citing_title":"ARIA: A Diagnostic Framework for Music Training Data Attribution","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2310.13289","citing_title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20847","citing_title":"Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23077","citing_title":"Adopting State-of-the-Art Pretrained Audio Representations for Music Recommender Systems","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16254","citing_title":"ArtifactNet: Detecting AI-Generated Music via Forensic Residual Physics","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX","json":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX.json","graph_json":"https://pith.science/api/pith-number/H5DLRUIQV5EP4BTHKKFZ7NH2DX/graph.json","events_json":"https://pith.science/api/pith-number/H5DLRUIQV5EP4BTHKKFZ7NH2DX/events.json","paper":"https://pith.science/paper/H5DLRUIQ"},"agent_actions":{"view_html":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX","download_json":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX.json","view_paper":"https://pith.science/paper/H5DLRUIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00107&json=true","fetch_graph":"https://pith.science/api/pith-number/H5DLRUIQV5EP4BTHKKFZ7NH2DX/graph.json","fetch_events":"https://pith.science/api/pith-number/H5DLRUIQV5EP4BTHKKFZ7NH2DX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/action/storage_attestation","attest_author":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/action/author_attestation","sign_citation":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/action/citation_signature","submit_replication":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/action/replication_record"}},"created_at":"2026-07-05T09:54:23.097119+00:00","updated_at":"2026-07-05T09:54:23.097119+00:00"}