{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FEVTGIWVPCANYZ7OA7YJQNGIVJ","short_pith_number":"pith:FEVTGIWV","schema_version":"1.0","canonical_sha256":"292b3322d57880dc67ee07f09834c8aa5fc54a70c81dd8374725c014325b65cf","source":{"kind":"arxiv","id":"2506.00338","version":1},"attestation_state":"computed","paper":{"title":"OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chyi-Jiunn Lin, Jinchuan Tian, Shakeel Muhammad, Shinji Watanabe, William Chen, Yifan Peng, Yui Sudo","submitted_at":"2025-05-31T01:44:44Z","abstract_excerpt":"The Open Whisper-style Speech Models (OWSM) project has developed a series of fully open speech foundation models using academic-scale resources, but their training data remains insufficient. This work enhances OWSM by integrating YODAS, a large-scale web-crawled dataset with a Creative Commons license. However, incorporating YODAS is nontrivial due to its wild nature, which introduces challenges such as incorrect language labels and audio-text misalignments. To address this, we develop a scalable data-cleaning pipeline using public toolkits, yielding a dataset with 166,000 hours of speech acr"},"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":"2506.00338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T01:44:44Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ab2902f984d8563d1d5dbf6883edb9046927fa280caaf52ed8884abb63d62eec","abstract_canon_sha256":"fbbdd5cecb36f697c3d87fc1039be4afdb42c472f587d509cd2ee1f406593a70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:32.776389Z","signature_b64":"clVGAWKWUbNOh18zuLEJVo2tDTkqW63n5C/MNpf2Z14YpR6lfSLLl4YNfIYAo4/I2qu5sC7dvnwZ5MjdW+XBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"292b3322d57880dc67ee07f09834c8aa5fc54a70c81dd8374725c014325b65cf","last_reissued_at":"2026-07-05T11:13:32.775925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:32.775925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chyi-Jiunn Lin, Jinchuan Tian, Shakeel Muhammad, Shinji Watanabe, William Chen, Yifan Peng, Yui Sudo","submitted_at":"2025-05-31T01:44:44Z","abstract_excerpt":"The Open Whisper-style Speech Models (OWSM) project has developed a series of fully open speech foundation models using academic-scale resources, but their training data remains insufficient. This work enhances OWSM by integrating YODAS, a large-scale web-crawled dataset with a Creative Commons license. However, incorporating YODAS is nontrivial due to its wild nature, which introduces challenges such as incorrect language labels and audio-text misalignments. To address this, we develop a scalable data-cleaning pipeline using public toolkits, yielding a dataset with 166,000 hours of speech acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00338","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/2506.00338/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":"2506.00338","created_at":"2026-07-05T11:13:32.775981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00338v1","created_at":"2026-07-05T11:13:32.775981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00338","created_at":"2026-07-05T11:13:32.775981+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEVTGIWVPCAN","created_at":"2026-07-05T11:13:32.775981+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEVTGIWVPCANYZ7O","created_at":"2026-07-05T11:13:32.775981+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEVTGIWV","created_at":"2026-07-05T11:13:32.775981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00338","citing_title":"OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEVTGIWVPCANYZ7OA7YJQNGIVJ","json":"https://pith.science/pith/FEVTGIWVPCANYZ7OA7YJQNGIVJ.json","graph_json":"https://pith.science/api/pith-number/FEVTGIWVPCANYZ7OA7YJQNGIVJ/graph.json","events_json":"https://pith.science/api/pith-number/FEVTGIWVPCANYZ7OA7YJQNGIVJ/events.json","paper":"https://pith.science/paper/FEVTGIWV"},"agent_actions":{"view_html":"https://pith.science/pith/FEVTGIWVPCANYZ7OA7YJQNGIVJ","download_json":"https://pith.science/pith/FEVTGIWVPCANYZ7OA7YJQNGIVJ.json","view_paper":"https://pith.science/paper/FEVTGIWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00338&json=true","fetch_graph":"https://pith.science/api/pith-number/FEVTGIWVPCANYZ7OA7YJQNGIVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FEVTGIWVPCANYZ7OA7YJQNGIVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEVTGIWVPCANYZ7OA7YJQNGIVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEVTGIWVPCANYZ7OA7YJQNGIVJ/action/storage_attestation","attest_author":"https://pith.science/pith/FEVTGIWVPCANYZ7OA7YJQNGIVJ/action/author_attestation","sign_citation":"https://pith.science/pith/FEVTGIWVPCANYZ7OA7YJQNGIVJ/action/citation_signature","submit_replication":"https://pith.science/pith/FEVTGIWVPCANYZ7OA7YJQNGIVJ/action/replication_record"}},"created_at":"2026-07-05T11:13:32.775981+00:00","updated_at":"2026-07-05T11:13:32.775981+00:00"}