{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6ZEHWPF7EHQF5M6XHY2LEUU2HN","short_pith_number":"pith:6ZEHWPF7","schema_version":"1.0","canonical_sha256":"f6487b3cbf21e05eb3d73e34b2529a3b677679ed7c076c9554861849fda9719a","source":{"kind":"arxiv","id":"2410.13267","version":2},"attestation_state":"computed","paper":{"title":"CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Feng Yu, Ge Zhang, Jiafeng Liu, Jing Chen, Maosong Sun, Monan Zhou, Ruibin Yuan, Shangda Wu, Xiaobing Li, Xuefeng Mu, Xu Tan, Yashan Wang, Yuanliang Dong, Yuejie Gao, Zhancheng Guo","submitted_at":"2024-10-17T06:43:54Z","abstract_excerpt":"Challenges in managing linguistic diversity and integrating various musical modalities are faced by current music information retrieval systems. These limitations reduce their effectiveness in a global, multimodal music environment. To address these issues, we introduce CLaMP 2, a system compatible with 101 languages that supports both ABC notation (a text-based musical notation format) and MIDI (Musical Instrument Digital Interface) for music information retrieval. CLaMP 2, pre-trained on 1.5 million ABC-MIDI-text triplets, includes a multilingual text encoder and a multimodal music encoder a"},"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":"2410.13267","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-17T06:43:54Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"ecb9a0e146addb768e6369acf287d92117dce19ef67b0e5fe11608532ba66bc8","abstract_canon_sha256":"ccbdd7e354b226d65ff95770fd47460e6f1642e5e34e0b5898a8b2363f979528"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:40.433150Z","signature_b64":"Fie62eV5TGBdvu/Um83ihjznkVvtRFdRxqrTMRFKCq1W3HHrIm8Tup2N3er+lDj6FNjbXur8y+kCdl2PoKnjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6487b3cbf21e05eb3d73e34b2529a3b677679ed7c076c9554861849fda9719a","last_reissued_at":"2026-07-05T10:04:40.432551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:40.432551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Feng Yu, Ge Zhang, Jiafeng Liu, Jing Chen, Maosong Sun, Monan Zhou, Ruibin Yuan, Shangda Wu, Xiaobing Li, Xuefeng Mu, Xu Tan, Yashan Wang, Yuanliang Dong, Yuejie Gao, Zhancheng Guo","submitted_at":"2024-10-17T06:43:54Z","abstract_excerpt":"Challenges in managing linguistic diversity and integrating various musical modalities are faced by current music information retrieval systems. These limitations reduce their effectiveness in a global, multimodal music environment. To address these issues, we introduce CLaMP 2, a system compatible with 101 languages that supports both ABC notation (a text-based musical notation format) and MIDI (Musical Instrument Digital Interface) for music information retrieval. CLaMP 2, pre-trained on 1.5 million ABC-MIDI-text triplets, includes a multilingual text encoder and a multimodal music encoder a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13267","kind":"arxiv","version":2},"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/2410.13267/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":"2410.13267","created_at":"2026-07-05T10:04:40.432611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13267v2","created_at":"2026-07-05T10:04:40.432611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13267","created_at":"2026-07-05T10:04:40.432611+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZEHWPF7EHQF","created_at":"2026-07-05T10:04:40.432611+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZEHWPF7EHQF5M6X","created_at":"2026-07-05T10:04:40.432611+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZEHWPF7","created_at":"2026-07-05T10:04:40.432611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04215","citing_title":"PianoBind: A Multimodal Joint Embedding Model for Pop-piano Music","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZEHWPF7EHQF5M6XHY2LEUU2HN","json":"https://pith.science/pith/6ZEHWPF7EHQF5M6XHY2LEUU2HN.json","graph_json":"https://pith.science/api/pith-number/6ZEHWPF7EHQF5M6XHY2LEUU2HN/graph.json","events_json":"https://pith.science/api/pith-number/6ZEHWPF7EHQF5M6XHY2LEUU2HN/events.json","paper":"https://pith.science/paper/6ZEHWPF7"},"agent_actions":{"view_html":"https://pith.science/pith/6ZEHWPF7EHQF5M6XHY2LEUU2HN","download_json":"https://pith.science/pith/6ZEHWPF7EHQF5M6XHY2LEUU2HN.json","view_paper":"https://pith.science/paper/6ZEHWPF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13267&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZEHWPF7EHQF5M6XHY2LEUU2HN/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZEHWPF7EHQF5M6XHY2LEUU2HN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZEHWPF7EHQF5M6XHY2LEUU2HN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZEHWPF7EHQF5M6XHY2LEUU2HN/action/storage_attestation","attest_author":"https://pith.science/pith/6ZEHWPF7EHQF5M6XHY2LEUU2HN/action/author_attestation","sign_citation":"https://pith.science/pith/6ZEHWPF7EHQF5M6XHY2LEUU2HN/action/citation_signature","submit_replication":"https://pith.science/pith/6ZEHWPF7EHQF5M6XHY2LEUU2HN/action/replication_record"}},"created_at":"2026-07-05T10:04:40.432611+00:00","updated_at":"2026-07-05T10:04:40.432611+00:00"}