{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H5DLRUIQV5EP4BTHKKFZ7NH2DX","short_pith_number":"pith:H5DLRUIQ","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"},"canonical_sha256":"3f46b8d110af48fe0667528b9fb4fa1dcafb064423c4671ab9b7a13d987989f9","source":{"kind":"arxiv","id":"2306.00107","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00107","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00107v5","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00107","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"pith_short_12","alias_value":"H5DLRUIQV5EP","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"pith_short_16","alias_value":"H5DLRUIQV5EP4BTH","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"pith_short_8","alias_value":"H5DLRUIQ","created_at":"2026-07-05T09:54:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H5DLRUIQV5EP4BTHKKFZ7NH2DX","target":"record","payload":{"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"},"canonical_sha256":"3f46b8d110af48fe0667528b9fb4fa1dcafb064423c4671ab9b7a13d987989f9","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"},"source_kind":"arxiv","source_id":"2306.00107","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UKDxxVTjvsjKl/19ZMgryCshUW+FD5NnD+HJPMxxaWx5F/09F0lEFBEDdE8RoLD8zUbBVKx+io8bDoL/AG4SCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T15:55:37.059596Z"},"content_sha256":"9dbbcf580b582b2aeae64f03b54c095fea59cca72239206706ecd20cb4d95c20","schema_version":"1.0","event_id":"sha256:9dbbcf580b582b2aeae64f03b54c095fea59cca72239206706ecd20cb4d95c20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H5DLRUIQV5EP4BTHKKFZ7NH2DX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jv45uS88p1J+q+o8VUC2iQRgYo3d3X95dz+13aeS9lA9rEz+pVp2ZsDs9p9lyPogI3byC5XQ1JIKDbrbvUcjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T15:55:37.059980Z"},"content_sha256":"112a834092df5a50f20cc338e5e205a4f14ad6091d7622dfbc284b8e98bbaaf1","schema_version":"1.0","event_id":"sha256:112a834092df5a50f20cc338e5e205a4f14ad6091d7622dfbc284b8e98bbaaf1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/bundle.json","state_url":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/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":"2026-07-11T15:55:37Z","links":{"resolver":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX","bundle":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/bundle.json","state":"https://pith.science/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5DLRUIQV5EP4BTHKKFZ7NH2DX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H5DLRUIQV5EP4BTHKKFZ7NH2DX","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":"f57ce252c21d63c7944cfff2eb7530c95c9568844784669935dbdbafd7719a7f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T18:27:43Z","title_canon_sha256":"5ab310e1757a4af25f288eeae1f0448a317e8a98ca867aa5dcff4806d117c5b0"},"schema_version":"1.0","source":{"id":"2306.00107","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00107","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00107v5","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00107","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"pith_short_12","alias_value":"H5DLRUIQV5EP","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"pith_short_16","alias_value":"H5DLRUIQV5EP4BTH","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"pith_short_8","alias_value":"H5DLRUIQ","created_at":"2026-07-05T09:54:23Z"}],"graph_snapshots":[{"event_id":"sha256:112a834092df5a50f20cc338e5e205a4f14ad6091d7622dfbc284b8e98bbaaf1","target":"graph","created_at":"2026-07-05T09:54:23Z","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/2306.00107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T18:27:43Z","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00107","kind":"arxiv","version":5},"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":"sha256:9dbbcf580b582b2aeae64f03b54c095fea59cca72239206706ecd20cb4d95c20","target":"record","created_at":"2026-07-05T09:54:23Z","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":"f57ce252c21d63c7944cfff2eb7530c95c9568844784669935dbdbafd7719a7f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-31T18:27:43Z","title_canon_sha256":"5ab310e1757a4af25f288eeae1f0448a317e8a98ca867aa5dcff4806d117c5b0"},"schema_version":"1.0","source":{"id":"2306.00107","kind":"arxiv","version":5}},"canonical_sha256":"3f46b8d110af48fe0667528b9fb4fa1dcafb064423c4671ab9b7a13d987989f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f46b8d110af48fe0667528b9fb4fa1dcafb064423c4671ab9b7a13d987989f9","first_computed_at":"2026-07-05T09:54:23.097060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:23.097060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ISsgZYiVbg0kI+Jmq8njAnAL/1ADl9OrC3E04lXLRpYTDZj4fW1Z6G6UraUiWhOBugxRaEXHvG3UthJDScb+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:23.097561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00107","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dbbcf580b582b2aeae64f03b54c095fea59cca72239206706ecd20cb4d95c20","sha256:112a834092df5a50f20cc338e5e205a4f14ad6091d7622dfbc284b8e98bbaaf1"],"state_sha256":"0b667539a13ee804cb17a9b1b0e6bf26eb1f720f9e65891313649528d466e16f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TmMEd3pgNq2W+WVToamSAwCQ+7v8J/x19pwdqZ5I4wjgqJ1/X65p/JPlbKcBW8ISUfX6jq7BX87MF7V8T0I5Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T15:55:37.062192Z","bundle_sha256":"47a35c39d356f87d7e4683cc4e15296db2b85834208683f4263e2a3ff644f074"}}