{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XMFVIBJMDFGA3K365UGK7SQB36","short_pith_number":"pith:XMFVIBJM","schema_version":"1.0","canonical_sha256":"bb0b54052c194c0dab7eed0cafca01df97e6f51f2c3895977055ea3d4406060b","source":{"kind":"arxiv","id":"2505.10793","version":1},"attestation_state":"computed","paper":{"title":"SongEval: A Benchmark Dataset for Song Aesthetics Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chunbo Hao, Guobin Ma, Haohe Liu, Hao Liu, Huakang Chen, Huixin Xue, Jin Xu, Jixun Yao, Lei Xie, Ruibin Yuan, Wei Xue, Yuepeng Jiang","submitted_at":"2025-05-16T02:06:25Z","abstract_excerpt":"Aesthetics serve as an implicit and important criterion in song generation tasks that reflect human perception beyond objective metrics. However, evaluating the aesthetics of generated songs remains a fundamental challenge, as the appreciation of music is highly subjective. Existing evaluation metrics, such as embedding-based distances, are limited in reflecting the subjective and perceptual aspects that define musical appeal. To address this issue, we introduce SongEval, the first open-source, large-scale benchmark dataset for evaluating the aesthetics of full-length songs. SongEval includes "},"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":"2505.10793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-16T02:06:25Z","cross_cats_sorted":[],"title_canon_sha256":"31cce975e9ad006176003d7c7dd35c27ef990c2a45639f8f03c9231774d116ae","abstract_canon_sha256":"327c40e38983bb2e518e9fa7d8f615b79fcaed189e3ece263579567f36c9f7c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:05.788324Z","signature_b64":"MaD6S4jU3QOCvtPC1cJjXaUeUOqmXjVWTcK1u8IC2YmVRm1KIV+5Noe5iLujGjS5ESimurHI/9lOSXYiZHC5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb0b54052c194c0dab7eed0cafca01df97e6f51f2c3895977055ea3d4406060b","last_reissued_at":"2026-07-05T11:04:05.787791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:05.787791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SongEval: A Benchmark Dataset for Song Aesthetics Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chunbo Hao, Guobin Ma, Haohe Liu, Hao Liu, Huakang Chen, Huixin Xue, Jin Xu, Jixun Yao, Lei Xie, Ruibin Yuan, Wei Xue, Yuepeng Jiang","submitted_at":"2025-05-16T02:06:25Z","abstract_excerpt":"Aesthetics serve as an implicit and important criterion in song generation tasks that reflect human perception beyond objective metrics. However, evaluating the aesthetics of generated songs remains a fundamental challenge, as the appreciation of music is highly subjective. Existing evaluation metrics, such as embedding-based distances, are limited in reflecting the subjective and perceptual aspects that define musical appeal. To address this issue, we introduce SongEval, the first open-source, large-scale benchmark dataset for evaluating the aesthetics of full-length songs. SongEval includes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10793","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/2505.10793/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":"2505.10793","created_at":"2026-07-05T11:04:05.787859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10793v1","created_at":"2026-07-05T11:04:05.787859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10793","created_at":"2026-07-05T11:04:05.787859+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMFVIBJMDFGA","created_at":"2026-07-05T11:04:05.787859+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMFVIBJMDFGA3K36","created_at":"2026-07-05T11:04:05.787859+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMFVIBJM","created_at":"2026-07-05T11:04:05.787859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06929","citing_title":"MADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21670","citing_title":"Improving Text-to-Music Generation with Human Preference Rewards","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07015","citing_title":"Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03169","citing_title":"SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30642","citing_title":"LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training","ref_index":49,"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":10,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22378","citing_title":"Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22029","citing_title":"MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline","ref_index":56,"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":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10203","citing_title":"Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11052","citing_title":"LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25937","citing_title":"SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMFVIBJMDFGA3K365UGK7SQB36","json":"https://pith.science/pith/XMFVIBJMDFGA3K365UGK7SQB36.json","graph_json":"https://pith.science/api/pith-number/XMFVIBJMDFGA3K365UGK7SQB36/graph.json","events_json":"https://pith.science/api/pith-number/XMFVIBJMDFGA3K365UGK7SQB36/events.json","paper":"https://pith.science/paper/XMFVIBJM"},"agent_actions":{"view_html":"https://pith.science/pith/XMFVIBJMDFGA3K365UGK7SQB36","download_json":"https://pith.science/pith/XMFVIBJMDFGA3K365UGK7SQB36.json","view_paper":"https://pith.science/paper/XMFVIBJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10793&json=true","fetch_graph":"https://pith.science/api/pith-number/XMFVIBJMDFGA3K365UGK7SQB36/graph.json","fetch_events":"https://pith.science/api/pith-number/XMFVIBJMDFGA3K365UGK7SQB36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMFVIBJMDFGA3K365UGK7SQB36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMFVIBJMDFGA3K365UGK7SQB36/action/storage_attestation","attest_author":"https://pith.science/pith/XMFVIBJMDFGA3K365UGK7SQB36/action/author_attestation","sign_citation":"https://pith.science/pith/XMFVIBJMDFGA3K365UGK7SQB36/action/citation_signature","submit_replication":"https://pith.science/pith/XMFVIBJMDFGA3K365UGK7SQB36/action/replication_record"}},"created_at":"2026-07-05T11:04:05.787859+00:00","updated_at":"2026-07-05T11:04:05.787859+00:00"}