{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LSJGDII7BO535CJ234PP5SMB3Y","short_pith_number":"pith:LSJGDII7","schema_version":"1.0","canonical_sha256":"5c9261a11f0bbbbe893adf1efec981de2d893aff10b4204d1444e4c967d2acbf","source":{"kind":"arxiv","id":"2605.28618","version":1},"attestation_state":"computed","paper":{"title":"Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Changhao Pan, Chenyuhao Wen, Han Wang, Jingyu Lu, Ke Lei, Ruiqi Li, Rui Yang, Wenxiang Guo, Xiang Yin, Xuming He, Yu Zhang, Zhiyuan Zhu, Zhou Zhao, Zhuan Zhou, Ziyue Jiang","submitted_at":"2026-05-27T15:28:15Z","abstract_excerpt":"Recent advances in speech generation have enabled high-fidelity synthesis, yet systematic evaluation of models under long-context conditions remains largely underexplored. A comprehensive evaluation benchmark for long-form speech is indispensable for two reasons: 1) existing test scenarios are often confined to limited domains, creating a significant gap with the diverse downstream applications; 2) existing metrics overlook critical long-text factors such as consistency and coherence, failing to generalize reliably. To this end, we propose Swanbench-Speech, a comprehensive benchmark that decom"},"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":"2605.28618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-27T15:28:15Z","cross_cats_sorted":[],"title_canon_sha256":"132d755a30ff302465ae200cef31f7b97c467f22ce6fcb1139c225ac77c79176","abstract_canon_sha256":"be0d7cdc2800721af25df7e0c943c762059681ceb4be98c3b800a56ae857e6be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:57.940501Z","signature_b64":"ygwonDKEbwpIzxJxlVCam6hOLoPIVYrL85GFMLpbdlg26aOkNB5SFb0aZ13oFMdX40IoZyA5tjXiBYLYMEDGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c9261a11f0bbbbe893adf1efec981de2d893aff10b4204d1444e4c967d2acbf","last_reissued_at":"2026-05-28T02:04:57.940089Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:57.940089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Changhao Pan, Chenyuhao Wen, Han Wang, Jingyu Lu, Ke Lei, Ruiqi Li, Rui Yang, Wenxiang Guo, Xiang Yin, Xuming He, Yu Zhang, Zhiyuan Zhu, Zhou Zhao, Zhuan Zhou, Ziyue Jiang","submitted_at":"2026-05-27T15:28:15Z","abstract_excerpt":"Recent advances in speech generation have enabled high-fidelity synthesis, yet systematic evaluation of models under long-context conditions remains largely underexplored. A comprehensive evaluation benchmark for long-form speech is indispensable for two reasons: 1) existing test scenarios are often confined to limited domains, creating a significant gap with the diverse downstream applications; 2) existing metrics overlook critical long-text factors such as consistency and coherence, failing to generalize reliably. To this end, we propose Swanbench-Speech, a comprehensive benchmark that decom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28618","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/2605.28618/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":"2605.28618","created_at":"2026-05-28T02:04:57.940146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28618v1","created_at":"2026-05-28T02:04:57.940146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28618","created_at":"2026-05-28T02:04:57.940146+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSJGDII7BO53","created_at":"2026-05-28T02:04:57.940146+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSJGDII7BO535CJ2","created_at":"2026-05-28T02:04:57.940146+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSJGDII7","created_at":"2026-05-28T02:04:57.940146+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/LSJGDII7BO535CJ234PP5SMB3Y","json":"https://pith.science/pith/LSJGDII7BO535CJ234PP5SMB3Y.json","graph_json":"https://pith.science/api/pith-number/LSJGDII7BO535CJ234PP5SMB3Y/graph.json","events_json":"https://pith.science/api/pith-number/LSJGDII7BO535CJ234PP5SMB3Y/events.json","paper":"https://pith.science/paper/LSJGDII7"},"agent_actions":{"view_html":"https://pith.science/pith/LSJGDII7BO535CJ234PP5SMB3Y","download_json":"https://pith.science/pith/LSJGDII7BO535CJ234PP5SMB3Y.json","view_paper":"https://pith.science/paper/LSJGDII7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28618&json=true","fetch_graph":"https://pith.science/api/pith-number/LSJGDII7BO535CJ234PP5SMB3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/LSJGDII7BO535CJ234PP5SMB3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSJGDII7BO535CJ234PP5SMB3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSJGDII7BO535CJ234PP5SMB3Y/action/storage_attestation","attest_author":"https://pith.science/pith/LSJGDII7BO535CJ234PP5SMB3Y/action/author_attestation","sign_citation":"https://pith.science/pith/LSJGDII7BO535CJ234PP5SMB3Y/action/citation_signature","submit_replication":"https://pith.science/pith/LSJGDII7BO535CJ234PP5SMB3Y/action/replication_record"}},"created_at":"2026-05-28T02:04:57.940146+00:00","updated_at":"2026-05-28T02:04:57.940146+00:00"}