{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FEVTGIWVPCANYZ7OA7YJQNGIVJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fbbdd5cecb36f697c3d87fc1039be4afdb42c472f587d509cd2ee1f406593a70","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T01:44:44Z","title_canon_sha256":"ab2902f984d8563d1d5dbf6883edb9046927fa280caaf52ed8884abb63d62eec"},"schema_version":"1.0","source":{"id":"2506.00338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00338","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00338v1","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00338","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"FEVTGIWVPCAN","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"FEVTGIWVPCANYZ7O","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"FEVTGIWV","created_at":"2026-07-05T11:13:32Z"}],"graph_snapshots":[{"event_id":"sha256:fd344d8044ac43f91632789d862122478a5fbfd94a1e7206961e27dbe5bfcdb2","target":"graph","created_at":"2026-07-05T11:13:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.00338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chyi-Jiunn Lin, Jinchuan Tian, Shakeel Muhammad, Shinji Watanabe, William Chen, Yifan Peng, Yui Sudo","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T01:44:44Z","title":"OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00338","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:59fbee0da0c2bfb667dcca808302a9d4a4a70d7e9e3ec6557b2ffc65ab6da2e9","target":"record","created_at":"2026-07-05T11:13:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fbbdd5cecb36f697c3d87fc1039be4afdb42c472f587d509cd2ee1f406593a70","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T01:44:44Z","title_canon_sha256":"ab2902f984d8563d1d5dbf6883edb9046927fa280caaf52ed8884abb63d62eec"},"schema_version":"1.0","source":{"id":"2506.00338","kind":"arxiv","version":1}},"canonical_sha256":"292b3322d57880dc67ee07f09834c8aa5fc54a70c81dd8374725c014325b65cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"292b3322d57880dc67ee07f09834c8aa5fc54a70c81dd8374725c014325b65cf","first_computed_at":"2026-07-05T11:13:32.775925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:32.775925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"clVGAWKWUbNOh18zuLEJVo2tDTkqW63n5C/MNpf2Z14YpR6lfSLLl4YNfIYAo4/I2qu5sC7dvnwZ5MjdW+XBDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:32.776389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59fbee0da0c2bfb667dcca808302a9d4a4a70d7e9e3ec6557b2ffc65ab6da2e9","sha256:fd344d8044ac43f91632789d862122478a5fbfd94a1e7206961e27dbe5bfcdb2"],"state_sha256":"bc960c0b12a3cf0d2e23ad3579a04469cb1eef0cc6c208e367275a619f1d66bb"}