{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E6LQAXUSD4RTGWOTQ2ZMHWKIB6","short_pith_number":"pith:E6LQAXUS","schema_version":"1.0","canonical_sha256":"2797005e921f233359d386b2c3d9480fb82af0f3cb5a3e6b10211435e16a35e9","source":{"kind":"arxiv","id":"2505.09325","version":1},"attestation_state":"computed","paper":{"title":"SingNet: Towards a Large-Scale, Diverse, and In-the-Wild Singing Voice Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaoren Wang, Haorui He, Junan Zhang, Xueyao Zhang, Yicheng Gu, Zhizheng Wu, Zihao Fang","submitted_at":"2025-05-14T12:24:05Z","abstract_excerpt":"The lack of a publicly-available large-scale and diverse dataset has long been a significant bottleneck for singing voice applications like Singing Voice Synthesis (SVS) and Singing Voice Conversion (SVC). To tackle this problem, we present SingNet, an extensive, diverse, and in-the-wild singing voice dataset. Specifically, we propose a data processing pipeline to extract ready-to-use training data from sample packs and songs on the internet, forming 3000 hours of singing voices in various languages and styles. Furthermore, to facilitate the use and demonstrate the effectiveness of SingNet, we"},"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":"2505.09325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-14T12:24:05Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"488b698af74db2a55346d0901e92bf4b460463cecc7611807421fc4bca8cadb5","abstract_canon_sha256":"a0fcdb35520fddc7cd194f1206008e28ebdbcf2ef165c355a3e845ec0283ca5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:06.430399Z","signature_b64":"SYC1mthjgY4PXI7E/BuDaDetZisG+UCQ2Krgo9KIY/HzbF+waBOwArlA5+iYgon9YBUCp7UxZwPHZLY6FtkuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2797005e921f233359d386b2c3d9480fb82af0f3cb5a3e6b10211435e16a35e9","last_reissued_at":"2026-07-05T11:03:06.429928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:06.429928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SingNet: Towards a Large-Scale, Diverse, and In-the-Wild Singing Voice Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaoren Wang, Haorui He, Junan Zhang, Xueyao Zhang, Yicheng Gu, Zhizheng Wu, Zihao Fang","submitted_at":"2025-05-14T12:24:05Z","abstract_excerpt":"The lack of a publicly-available large-scale and diverse dataset has long been a significant bottleneck for singing voice applications like Singing Voice Synthesis (SVS) and Singing Voice Conversion (SVC). To tackle this problem, we present SingNet, an extensive, diverse, and in-the-wild singing voice dataset. Specifically, we propose a data processing pipeline to extract ready-to-use training data from sample packs and songs on the internet, forming 3000 hours of singing voices in various languages and styles. Furthermore, to facilitate the use and demonstrate the effectiveness of SingNet, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09325","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/2505.09325/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":"2505.09325","created_at":"2026-07-05T11:03:06.429979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09325v1","created_at":"2026-07-05T11:03:06.429979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09325","created_at":"2026-07-05T11:03:06.429979+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6LQAXUSD4RT","created_at":"2026-07-05T11:03:06.429979+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6LQAXUSD4RTGWOT","created_at":"2026-07-05T11:03:06.429979+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6LQAXUS","created_at":"2026-07-05T11:03:06.429979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.20211","citing_title":"Aliasing-Free Neural Audio Synthesis","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6LQAXUSD4RTGWOTQ2ZMHWKIB6","json":"https://pith.science/pith/E6LQAXUSD4RTGWOTQ2ZMHWKIB6.json","graph_json":"https://pith.science/api/pith-number/E6LQAXUSD4RTGWOTQ2ZMHWKIB6/graph.json","events_json":"https://pith.science/api/pith-number/E6LQAXUSD4RTGWOTQ2ZMHWKIB6/events.json","paper":"https://pith.science/paper/E6LQAXUS"},"agent_actions":{"view_html":"https://pith.science/pith/E6LQAXUSD4RTGWOTQ2ZMHWKIB6","download_json":"https://pith.science/pith/E6LQAXUSD4RTGWOTQ2ZMHWKIB6.json","view_paper":"https://pith.science/paper/E6LQAXUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09325&json=true","fetch_graph":"https://pith.science/api/pith-number/E6LQAXUSD4RTGWOTQ2ZMHWKIB6/graph.json","fetch_events":"https://pith.science/api/pith-number/E6LQAXUSD4RTGWOTQ2ZMHWKIB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6LQAXUSD4RTGWOTQ2ZMHWKIB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6LQAXUSD4RTGWOTQ2ZMHWKIB6/action/storage_attestation","attest_author":"https://pith.science/pith/E6LQAXUSD4RTGWOTQ2ZMHWKIB6/action/author_attestation","sign_citation":"https://pith.science/pith/E6LQAXUSD4RTGWOTQ2ZMHWKIB6/action/citation_signature","submit_replication":"https://pith.science/pith/E6LQAXUSD4RTGWOTQ2ZMHWKIB6/action/replication_record"}},"created_at":"2026-07-05T11:03:06.429979+00:00","updated_at":"2026-07-05T11:03:06.429979+00:00"}