{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7XODTNZ563BMQE7LSXW3DVLF6O","short_pith_number":"pith:7XODTNZ5","schema_version":"1.0","canonical_sha256":"fddc39b73df6c2c813eb95edb1d565f3b2eb0cb9524edfade7c539ecb9eeacfb","source":{"kind":"arxiv","id":"2509.00051","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Evaluation Metrics for Music Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Faria Binte Kader, Santu Karmaker","submitted_at":"2025-08-24T23:15:37Z","abstract_excerpt":"Despite significant advancements in music generation systems, the methodologies for evaluating generated music have not progressed as expected due to the complex nature of music, with aspects such as structure, coherence, creativity, and emotional expressiveness. In this paper, we shed light on this research gap, introducing a detailed taxonomy for evaluation metrics for both audio and symbolic music representations. We include a critical review identifying major limitations in current evaluation methodologies which includes poor correlation between objective metrics and human perception, cros"},"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":"2509.00051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-24T23:15:37Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"acf18f838658351307aa966f49f2c4e7d43e77cc84e077bdf2e742d661c79db5","abstract_canon_sha256":"60c196ad7499143eda2a496f2d8d0716eeb90b76ea30af75eb2ccfbaf5d24441"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:08.689252Z","signature_b64":"5M1dUqeJ7ndQMWwa4+WDoRZjDwiG6tse8FCO+IXASuG+J2wmpKW4+VPeeOfyKEToss++t4yKPCAdeNfD2ivrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fddc39b73df6c2c813eb95edb1d565f3b2eb0cb9524edfade7c539ecb9eeacfb","last_reissued_at":"2026-07-05T12:02:08.688731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:08.688731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Evaluation Metrics for Music Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Faria Binte Kader, Santu Karmaker","submitted_at":"2025-08-24T23:15:37Z","abstract_excerpt":"Despite significant advancements in music generation systems, the methodologies for evaluating generated music have not progressed as expected due to the complex nature of music, with aspects such as structure, coherence, creativity, and emotional expressiveness. In this paper, we shed light on this research gap, introducing a detailed taxonomy for evaluation metrics for both audio and symbolic music representations. We include a critical review identifying major limitations in current evaluation methodologies which includes poor correlation between objective metrics and human perception, cros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00051","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/2509.00051/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":"2509.00051","created_at":"2026-07-05T12:02:08.688801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00051v1","created_at":"2026-07-05T12:02:08.688801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00051","created_at":"2026-07-05T12:02:08.688801+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XODTNZ563BM","created_at":"2026-07-05T12:02:08.688801+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XODTNZ563BMQE7L","created_at":"2026-07-05T12:02:08.688801+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XODTNZ5","created_at":"2026-07-05T12:02:08.688801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08722","citing_title":"Can LLMs understand LilyPond? A benchmark for symbolic music generation and understanding","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03395","citing_title":"APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03395","citing_title":"APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7XODTNZ563BMQE7LSXW3DVLF6O","json":"https://pith.science/pith/7XODTNZ563BMQE7LSXW3DVLF6O.json","graph_json":"https://pith.science/api/pith-number/7XODTNZ563BMQE7LSXW3DVLF6O/graph.json","events_json":"https://pith.science/api/pith-number/7XODTNZ563BMQE7LSXW3DVLF6O/events.json","paper":"https://pith.science/paper/7XODTNZ5"},"agent_actions":{"view_html":"https://pith.science/pith/7XODTNZ563BMQE7LSXW3DVLF6O","download_json":"https://pith.science/pith/7XODTNZ563BMQE7LSXW3DVLF6O.json","view_paper":"https://pith.science/paper/7XODTNZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00051&json=true","fetch_graph":"https://pith.science/api/pith-number/7XODTNZ563BMQE7LSXW3DVLF6O/graph.json","fetch_events":"https://pith.science/api/pith-number/7XODTNZ563BMQE7LSXW3DVLF6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XODTNZ563BMQE7LSXW3DVLF6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XODTNZ563BMQE7LSXW3DVLF6O/action/storage_attestation","attest_author":"https://pith.science/pith/7XODTNZ563BMQE7LSXW3DVLF6O/action/author_attestation","sign_citation":"https://pith.science/pith/7XODTNZ563BMQE7LSXW3DVLF6O/action/citation_signature","submit_replication":"https://pith.science/pith/7XODTNZ563BMQE7LSXW3DVLF6O/action/replication_record"}},"created_at":"2026-07-05T12:02:08.688801+00:00","updated_at":"2026-07-05T12:02:08.688801+00:00"}