{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q2YODDC7U535QNZX3U7GJZ665E","short_pith_number":"pith:Q2YODDC7","schema_version":"1.0","canonical_sha256":"86b0e18c5fa777d83737dd3e64e7dee91f4137fc28b6b2d917345aff0f41db58","source":{"kind":"arxiv","id":"2509.04702","version":1},"attestation_state":"computed","paper":{"title":"OleSpeech-IV: A Large-Scale Multispeaker and Multilingual Conversational Speech Dataset with Diverse Topics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhiksha Raj, Chanwoo Kim, Chenfeng Miao, Dong Han, Ke Tan, Rita Singh, Ruchao Fan, Wei Chu, Xavier Menendez-Pidal, Yuanzhe Dong","submitted_at":"2025-09-04T23:14:52Z","abstract_excerpt":"OleSpeech-IV dataset is a large-scale multispeaker and multilingual conversational speech dataset with diverse topics. The audio content comes from publicly-available English podcasts, talk shows, teleconferences, and other conversations. Speaker names, turns, and transcripts are human-sourced and refined by a proprietary pipeline, while additional information such as timestamps and confidence scores is derived from the pipeline. The IV denotes its position as Tier IV in the Olewave dataset series. In addition, we have open-sourced a subset, OleSpeech-IV-2025-EN-AR-100, for non-commercial rese"},"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":"2509.04702","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T23:14:52Z","cross_cats_sorted":[],"title_canon_sha256":"c02a036d471e9edf7b3bc0af9b11b9a8101a1012c88ae6a8daa8715f6411831b","abstract_canon_sha256":"099016ccb48d5f015828fa8f1d87b6a3831bb3da68e8c4ede5824f95f0b1aabb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:27.960301Z","signature_b64":"+fa/E0G4F3HNEhFqYlXHkO56aIsWPFZtCxC9lXnFJzhKpCPLzfmDCW9Evoc+sVbxBGZYlmXW0M1pbtf9luYiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86b0e18c5fa777d83737dd3e64e7dee91f4137fc28b6b2d917345aff0f41db58","last_reissued_at":"2026-07-05T12:05:27.959891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:27.959891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OleSpeech-IV: A Large-Scale Multispeaker and Multilingual Conversational Speech Dataset with Diverse Topics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhiksha Raj, Chanwoo Kim, Chenfeng Miao, Dong Han, Ke Tan, Rita Singh, Ruchao Fan, Wei Chu, Xavier Menendez-Pidal, Yuanzhe Dong","submitted_at":"2025-09-04T23:14:52Z","abstract_excerpt":"OleSpeech-IV dataset is a large-scale multispeaker and multilingual conversational speech dataset with diverse topics. The audio content comes from publicly-available English podcasts, talk shows, teleconferences, and other conversations. Speaker names, turns, and transcripts are human-sourced and refined by a proprietary pipeline, while additional information such as timestamps and confidence scores is derived from the pipeline. The IV denotes its position as Tier IV in the Olewave dataset series. In addition, we have open-sourced a subset, OleSpeech-IV-2025-EN-AR-100, for non-commercial rese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04702","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/2509.04702/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":"2509.04702","created_at":"2026-07-05T12:05:27.959948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04702v1","created_at":"2026-07-05T12:05:27.959948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04702","created_at":"2026-07-05T12:05:27.959948+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2YODDC7U535","created_at":"2026-07-05T12:05:27.959948+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2YODDC7U535QNZX","created_at":"2026-07-05T12:05:27.959948+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2YODDC7","created_at":"2026-07-05T12:05:27.959948+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/Q2YODDC7U535QNZX3U7GJZ665E","json":"https://pith.science/pith/Q2YODDC7U535QNZX3U7GJZ665E.json","graph_json":"https://pith.science/api/pith-number/Q2YODDC7U535QNZX3U7GJZ665E/graph.json","events_json":"https://pith.science/api/pith-number/Q2YODDC7U535QNZX3U7GJZ665E/events.json","paper":"https://pith.science/paper/Q2YODDC7"},"agent_actions":{"view_html":"https://pith.science/pith/Q2YODDC7U535QNZX3U7GJZ665E","download_json":"https://pith.science/pith/Q2YODDC7U535QNZX3U7GJZ665E.json","view_paper":"https://pith.science/paper/Q2YODDC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04702&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2YODDC7U535QNZX3U7GJZ665E/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2YODDC7U535QNZX3U7GJZ665E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2YODDC7U535QNZX3U7GJZ665E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2YODDC7U535QNZX3U7GJZ665E/action/storage_attestation","attest_author":"https://pith.science/pith/Q2YODDC7U535QNZX3U7GJZ665E/action/author_attestation","sign_citation":"https://pith.science/pith/Q2YODDC7U535QNZX3U7GJZ665E/action/citation_signature","submit_replication":"https://pith.science/pith/Q2YODDC7U535QNZX3U7GJZ665E/action/replication_record"}},"created_at":"2026-07-05T12:05:27.959948+00:00","updated_at":"2026-07-05T12:05:27.959948+00:00"}