{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CPPOWC4HYPNGUIIALZKV7S4YQO","short_pith_number":"pith:CPPOWC4H","schema_version":"1.0","canonical_sha256":"13deeb0b87c3da6a21005e555fcb988396a80ef70f565b1b30243a252eba331c","source":{"kind":"arxiv","id":"2504.21815","version":1},"attestation_state":"computed","paper":{"title":"From Aesthetics to Human Preferences: Comparative Perspectives of Evaluating Text-to-Music Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Emmanouil Benetos, Huan Zhang, Huy Phan, Jinhua Liang, Wenwu Wang","submitted_at":"2025-04-30T17:21:04Z","abstract_excerpt":"Evaluating generative models remains a fundamental challenge, particularly when the goal is to reflect human preferences. In this paper, we use music generation as a case study to investigate the gap between automatic evaluation metrics and human preferences. We conduct comparative experiments across five state-of-the-art music generation approaches, assessing both perceptual quality and distributional similarity to human-composed music. Specifically, we evaluate synthesis music from various perceptual dimensions and examine reference-based metrics such as Mauve Audio Divergence (MAD) and Kern"},"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":"2504.21815","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-04-30T17:21:04Z","cross_cats_sorted":[],"title_canon_sha256":"44cbc3b965fa63533e37b495a6f5a126b9ee742d584555d1640e638e8391dc12","abstract_canon_sha256":"f172fc5819fa5e4f31eeb2e1c51a14c74d6683a79ad0086159b560e0ef9185e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:29.841045Z","signature_b64":"H/LUnR2lHglTEKHixDGKAjNG6YNAT80uL/08nOB5TevO2cnlWg+Z9mjLIlaRW1/FLEvBGXmo16WekPvdRCMACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13deeb0b87c3da6a21005e555fcb988396a80ef70f565b1b30243a252eba331c","last_reissued_at":"2026-07-05T10:56:29.840577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:29.840577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Aesthetics to Human Preferences: Comparative Perspectives of Evaluating Text-to-Music Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Emmanouil Benetos, Huan Zhang, Huy Phan, Jinhua Liang, Wenwu Wang","submitted_at":"2025-04-30T17:21:04Z","abstract_excerpt":"Evaluating generative models remains a fundamental challenge, particularly when the goal is to reflect human preferences. In this paper, we use music generation as a case study to investigate the gap between automatic evaluation metrics and human preferences. We conduct comparative experiments across five state-of-the-art music generation approaches, assessing both perceptual quality and distributional similarity to human-composed music. Specifically, we evaluate synthesis music from various perceptual dimensions and examine reference-based metrics such as Mauve Audio Divergence (MAD) and Kern"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21815","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/2504.21815/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":"2504.21815","created_at":"2026-07-05T10:56:29.840634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21815v1","created_at":"2026-07-05T10:56:29.840634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21815","created_at":"2026-07-05T10:56:29.840634+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPPOWC4HYPNG","created_at":"2026-07-05T10:56:29.840634+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPPOWC4HYPNGUIIA","created_at":"2026-07-05T10:56:29.840634+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPPOWC4H","created_at":"2026-07-05T10:56:29.840634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPPOWC4HYPNGUIIALZKV7S4YQO","json":"https://pith.science/pith/CPPOWC4HYPNGUIIALZKV7S4YQO.json","graph_json":"https://pith.science/api/pith-number/CPPOWC4HYPNGUIIALZKV7S4YQO/graph.json","events_json":"https://pith.science/api/pith-number/CPPOWC4HYPNGUIIALZKV7S4YQO/events.json","paper":"https://pith.science/paper/CPPOWC4H"},"agent_actions":{"view_html":"https://pith.science/pith/CPPOWC4HYPNGUIIALZKV7S4YQO","download_json":"https://pith.science/pith/CPPOWC4HYPNGUIIALZKV7S4YQO.json","view_paper":"https://pith.science/paper/CPPOWC4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21815&json=true","fetch_graph":"https://pith.science/api/pith-number/CPPOWC4HYPNGUIIALZKV7S4YQO/graph.json","fetch_events":"https://pith.science/api/pith-number/CPPOWC4HYPNGUIIALZKV7S4YQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPPOWC4HYPNGUIIALZKV7S4YQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPPOWC4HYPNGUIIALZKV7S4YQO/action/storage_attestation","attest_author":"https://pith.science/pith/CPPOWC4HYPNGUIIALZKV7S4YQO/action/author_attestation","sign_citation":"https://pith.science/pith/CPPOWC4HYPNGUIIALZKV7S4YQO/action/citation_signature","submit_replication":"https://pith.science/pith/CPPOWC4HYPNGUIIALZKV7S4YQO/action/replication_record"}},"created_at":"2026-07-05T10:56:29.840634+00:00","updated_at":"2026-07-05T10:56:29.840634+00:00"}