{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZGGYMS3GCNPXYQXZSCXG6CUXZC","short_pith_number":"pith:ZGGYMS3G","schema_version":"1.0","canonical_sha256":"c98d864b66135f7c42f990ae6f0a97c88abc1a0d9b757589a67b328a7c2546a0","source":{"kind":"arxiv","id":"2502.10362","version":3},"attestation_state":"computed","paper":{"title":"CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Feng Yu, Gus Xia, Juhan Nam, Junyan Jiang, Maosong Sun, Ruibin Yuan, Seungheon Doh, Shangda Wu, Xiaobing Li, Zhancheng Guo","submitted_at":"2025-02-14T18:42:25Z","abstract_excerpt":"CLaMP 3 is a unified framework developed to address challenges of cross-modal and cross-lingual generalization in music information retrieval. Using contrastive learning, it aligns all major music modalities--including sheet music, performance signals, and audio recordings--with multilingual text in a shared representation space, enabling retrieval across unaligned modalities with text as a bridge. It features a multilingual text encoder adaptable to unseen languages, exhibiting strong cross-lingual generalization. Leveraging retrieval-augmented generation, we curated M4-RAG, a web-scale datas"},"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":"2502.10362","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-14T18:42:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"51c4e352c78309eb871aaccb274751d66f1ec518e3c7044b6c9fa0cc10bd1f62","abstract_canon_sha256":"4c95c81c977e61e24a011aa5b5aadc0f2bab6e3547caac5c2e60e7dcfc77ae29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:45.673331Z","signature_b64":"fi3sz2UvZG/7EXAeFvuhkt1dByhUbyj4XqRkk9j2EgQ+ILyso9CZ5YJL+9EFYzvdTIoPEyaMahUQ+ZSmKPhCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c98d864b66135f7c42f990ae6f0a97c88abc1a0d9b757589a67b328a7c2546a0","last_reissued_at":"2026-07-05T11:04:45.672789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:45.672789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Feng Yu, Gus Xia, Juhan Nam, Junyan Jiang, Maosong Sun, Ruibin Yuan, Seungheon Doh, Shangda Wu, Xiaobing Li, Zhancheng Guo","submitted_at":"2025-02-14T18:42:25Z","abstract_excerpt":"CLaMP 3 is a unified framework developed to address challenges of cross-modal and cross-lingual generalization in music information retrieval. Using contrastive learning, it aligns all major music modalities--including sheet music, performance signals, and audio recordings--with multilingual text in a shared representation space, enabling retrieval across unaligned modalities with text as a bridge. It features a multilingual text encoder adaptable to unseen languages, exhibiting strong cross-lingual generalization. Leveraging retrieval-augmented generation, we curated M4-RAG, a web-scale datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10362","kind":"arxiv","version":3},"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/2502.10362/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":"2502.10362","created_at":"2026-07-05T11:04:45.672859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10362v3","created_at":"2026-07-05T11:04:45.672859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10362","created_at":"2026-07-05T11:04:45.672859+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGGYMS3GCNPX","created_at":"2026-07-05T11:04:45.672859+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGGYMS3GCNPXYQXZ","created_at":"2026-07-05T11:04:45.672859+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGGYMS3G","created_at":"2026-07-05T11:04:45.672859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05971","citing_title":"Multimodal Video-to-Music Recommendation via Semantic Retrieval and Temporal Reranking","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13431","citing_title":"Text2Score: Generating Sheet Music From Textual Prompts","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZGGYMS3GCNPXYQXZSCXG6CUXZC","json":"https://pith.science/pith/ZGGYMS3GCNPXYQXZSCXG6CUXZC.json","graph_json":"https://pith.science/api/pith-number/ZGGYMS3GCNPXYQXZSCXG6CUXZC/graph.json","events_json":"https://pith.science/api/pith-number/ZGGYMS3GCNPXYQXZSCXG6CUXZC/events.json","paper":"https://pith.science/paper/ZGGYMS3G"},"agent_actions":{"view_html":"https://pith.science/pith/ZGGYMS3GCNPXYQXZSCXG6CUXZC","download_json":"https://pith.science/pith/ZGGYMS3GCNPXYQXZSCXG6CUXZC.json","view_paper":"https://pith.science/paper/ZGGYMS3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10362&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGGYMS3GCNPXYQXZSCXG6CUXZC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGGYMS3GCNPXYQXZSCXG6CUXZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGGYMS3GCNPXYQXZSCXG6CUXZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGGYMS3GCNPXYQXZSCXG6CUXZC/action/storage_attestation","attest_author":"https://pith.science/pith/ZGGYMS3GCNPXYQXZSCXG6CUXZC/action/author_attestation","sign_citation":"https://pith.science/pith/ZGGYMS3GCNPXYQXZSCXG6CUXZC/action/citation_signature","submit_replication":"https://pith.science/pith/ZGGYMS3GCNPXYQXZSCXG6CUXZC/action/replication_record"}},"created_at":"2026-07-05T11:04:45.672859+00:00","updated_at":"2026-07-05T11:04:45.672859+00:00"}