{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DF6TYUGMILQGJ544YB5DGTOXVP","short_pith_number":"pith:DF6TYUGM","schema_version":"1.0","canonical_sha256":"197d3c50cc42e064f79cc07a334dd7abc690c74a81624d0d440147eed6f665f9","source":{"kind":"arxiv","id":"2406.15885","version":1},"attestation_state":"computed","paper":{"title":"The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Cong Chen, Hai Zhao, Jiajia Li, Lu Yang, Mingni Tang, Ping Wang, Zuchao Li","submitted_at":"2024-06-22T16:24:42Z","abstract_excerpt":"Benchmark plays a pivotal role in assessing the advancements of large language models (LLMs). While numerous benchmarks have been proposed to evaluate LLMs' capabilities, there is a notable absence of a dedicated benchmark for assessing their musical abilities. To address this gap, we present ZIQI-Eval, a comprehensive and large-scale music benchmark specifically designed to evaluate the music-related capabilities of LLMs. ZIQI-Eval encompasses a wide range of questions, covering 10 major categories and 56 subcategories, resulting in over 14,000 meticulously curated data entries. By leveraging"},"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":"2406.15885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-22T16:24:42Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"e95cd6dc74457be953fef0e13c777a36d1cd4bcb262ce2f48b49588bec431ee4","abstract_canon_sha256":"6785a8dd2a05f8f40b1647257856fd6d674b2e950ab077c14bccc64fbadffb74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:50.101914Z","signature_b64":"gcFJlymGKjguLBTypCAgyfLIqdxG697iefbq9RHwQR9ic2hnbGB2p4u821rqKcmcgHfZcog4N8+4v6nW0OYwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"197d3c50cc42e064f79cc07a334dd7abc690c74a81624d0d440147eed6f665f9","last_reissued_at":"2026-07-05T08:35:50.101478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:50.101478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Cong Chen, Hai Zhao, Jiajia Li, Lu Yang, Mingni Tang, Ping Wang, Zuchao Li","submitted_at":"2024-06-22T16:24:42Z","abstract_excerpt":"Benchmark plays a pivotal role in assessing the advancements of large language models (LLMs). While numerous benchmarks have been proposed to evaluate LLMs' capabilities, there is a notable absence of a dedicated benchmark for assessing their musical abilities. To address this gap, we present ZIQI-Eval, a comprehensive and large-scale music benchmark specifically designed to evaluate the music-related capabilities of LLMs. ZIQI-Eval encompasses a wide range of questions, covering 10 major categories and 56 subcategories, resulting in over 14,000 meticulously curated data entries. By leveraging"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15885","kind":"arxiv","version":1},"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/2406.15885/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":"2406.15885","created_at":"2026-07-05T08:35:50.101552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15885v1","created_at":"2026-07-05T08:35:50.101552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15885","created_at":"2026-07-05T08:35:50.101552+00:00"},{"alias_kind":"pith_short_12","alias_value":"DF6TYUGMILQG","created_at":"2026-07-05T08:35:50.101552+00:00"},{"alias_kind":"pith_short_16","alias_value":"DF6TYUGMILQGJ544","created_at":"2026-07-05T08:35:50.101552+00:00"},{"alias_kind":"pith_short_8","alias_value":"DF6TYUGM","created_at":"2026-07-05T08:35:50.101552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05522","citing_title":"Exploring LLMs for South Asian Music Understanding and Generation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DF6TYUGMILQGJ544YB5DGTOXVP","json":"https://pith.science/pith/DF6TYUGMILQGJ544YB5DGTOXVP.json","graph_json":"https://pith.science/api/pith-number/DF6TYUGMILQGJ544YB5DGTOXVP/graph.json","events_json":"https://pith.science/api/pith-number/DF6TYUGMILQGJ544YB5DGTOXVP/events.json","paper":"https://pith.science/paper/DF6TYUGM"},"agent_actions":{"view_html":"https://pith.science/pith/DF6TYUGMILQGJ544YB5DGTOXVP","download_json":"https://pith.science/pith/DF6TYUGMILQGJ544YB5DGTOXVP.json","view_paper":"https://pith.science/paper/DF6TYUGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15885&json=true","fetch_graph":"https://pith.science/api/pith-number/DF6TYUGMILQGJ544YB5DGTOXVP/graph.json","fetch_events":"https://pith.science/api/pith-number/DF6TYUGMILQGJ544YB5DGTOXVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DF6TYUGMILQGJ544YB5DGTOXVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DF6TYUGMILQGJ544YB5DGTOXVP/action/storage_attestation","attest_author":"https://pith.science/pith/DF6TYUGMILQGJ544YB5DGTOXVP/action/author_attestation","sign_citation":"https://pith.science/pith/DF6TYUGMILQGJ544YB5DGTOXVP/action/citation_signature","submit_replication":"https://pith.science/pith/DF6TYUGMILQGJ544YB5DGTOXVP/action/replication_record"}},"created_at":"2026-07-05T08:35:50.101552+00:00","updated_at":"2026-07-05T08:35:50.101552+00:00"}