{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5THSX5GVFLKORBY5ZC7PM5P45D","short_pith_number":"pith:5THSX5GV","canonical_record":{"source":{"id":"2406.00899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T23:43:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d1df57584bfda5cb1f785e2b04662570f9c854e3ffbbce9f6de8447e5c730119","abstract_canon_sha256":"fd2589350f683a044c5fd3225b00d50a0b0784afa23227bc629a14325be51bbc"},"schema_version":"1.0"},"canonical_sha256":"eccf2bf4d52ad4e8871dc8bef675fce8cf7778792b07d86c11f51a1b77f68e84","source":{"kind":"arxiv","id":"2406.00899","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00899","created_at":"2026-07-05T08:26:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00899v1","created_at":"2026-07-05T08:26:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00899","created_at":"2026-07-05T08:26:32Z"},{"alias_kind":"pith_short_12","alias_value":"5THSX5GVFLKO","created_at":"2026-07-05T08:26:32Z"},{"alias_kind":"pith_short_16","alias_value":"5THSX5GVFLKORBY5","created_at":"2026-07-05T08:26:32Z"},{"alias_kind":"pith_short_8","alias_value":"5THSX5GV","created_at":"2026-07-05T08:26:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5THSX5GVFLKORBY5ZC7PM5P45D","target":"record","payload":{"canonical_record":{"source":{"id":"2406.00899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T23:43:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d1df57584bfda5cb1f785e2b04662570f9c854e3ffbbce9f6de8447e5c730119","abstract_canon_sha256":"fd2589350f683a044c5fd3225b00d50a0b0784afa23227bc629a14325be51bbc"},"schema_version":"1.0"},"canonical_sha256":"eccf2bf4d52ad4e8871dc8bef675fce8cf7778792b07d86c11f51a1b77f68e84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:32.364438Z","signature_b64":"8jsh+ZcSpZVhEwcLJ6gZHu8E0/y7gfquB9HZnvhhw9M4iGd1wvak7oVw0y+QPPoZwJ/nXG1I1aT79kl9EigEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eccf2bf4d52ad4e8871dc8bef675fce8cf7778792b07d86c11f51a1b77f68e84","last_reissued_at":"2026-07-05T08:26:32.363969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:32.363969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.00899","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PK5AHzi+LmpN2t+N/1w8xF4L91njfXs66d5X3HCkqa/np68R1dgHFW7D2SOj0dQeqoUdEZ+sWbWk3urKoShCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:38:48.649488Z"},"content_sha256":"c821e84279ce046239e86d6dd518338008c8dc17fe628a7bce06c38cb03e6fd1","schema_version":"1.0","event_id":"sha256:c821e84279ce046239e86d6dd518338008c8dc17fe628a7bce06c38cb03e6fd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5THSX5GVFLKORBY5ZC7PM5P45D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"YODAS: Youtube-Oriented Dataset for Audio and Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Sayaka Shiota, Shinji Watanabe, Shinnosuke Takamichi, Takaaki Saeki, William Chen, Xinjian Li","submitted_at":"2024-06-02T23:43:27Z","abstract_excerpt":"In this study, we introduce YODAS (YouTube-Oriented Dataset for Audio and Speech), a large-scale, multilingual dataset comprising currently over 500k hours of speech data in more than 100 languages, sourced from both labeled and unlabeled YouTube speech datasets. The labeled subsets, including manual or automatic subtitles, facilitate supervised model training. Conversely, the unlabeled subsets are apt for self-supervised learning applications. YODAS is distinctive as the first publicly available dataset of its scale, and it is distributed under a Creative Commons license. We introduce the col"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00899","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/2406.00899/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LQyrywI0lceyYgJDu2EuyKe0rog7fBqyyiS40K87ZWiqXD+6C2IqI7d876qCbyS1FcMQ8Qwil1nXcaacB9wSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:38:48.649990Z"},"content_sha256":"ae0f2aee345e218be646c25616b22b54c38943238dd68af250ba094cb7155b52","schema_version":"1.0","event_id":"sha256:ae0f2aee345e218be646c25616b22b54c38943238dd68af250ba094cb7155b52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5THSX5GVFLKORBY5ZC7PM5P45D/bundle.json","state_url":"https://pith.science/pith/5THSX5GVFLKORBY5ZC7PM5P45D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5THSX5GVFLKORBY5ZC7PM5P45D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T20:38:48Z","links":{"resolver":"https://pith.science/pith/5THSX5GVFLKORBY5ZC7PM5P45D","bundle":"https://pith.science/pith/5THSX5GVFLKORBY5ZC7PM5P45D/bundle.json","state":"https://pith.science/pith/5THSX5GVFLKORBY5ZC7PM5P45D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5THSX5GVFLKORBY5ZC7PM5P45D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5THSX5GVFLKORBY5ZC7PM5P45D","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":"fd2589350f683a044c5fd3225b00d50a0b0784afa23227bc629a14325be51bbc","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T23:43:27Z","title_canon_sha256":"d1df57584bfda5cb1f785e2b04662570f9c854e3ffbbce9f6de8447e5c730119"},"schema_version":"1.0","source":{"id":"2406.00899","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00899","created_at":"2026-07-05T08:26:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00899v1","created_at":"2026-07-05T08:26:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00899","created_at":"2026-07-05T08:26:32Z"},{"alias_kind":"pith_short_12","alias_value":"5THSX5GVFLKO","created_at":"2026-07-05T08:26:32Z"},{"alias_kind":"pith_short_16","alias_value":"5THSX5GVFLKORBY5","created_at":"2026-07-05T08:26:32Z"},{"alias_kind":"pith_short_8","alias_value":"5THSX5GV","created_at":"2026-07-05T08:26:32Z"}],"graph_snapshots":[{"event_id":"sha256:ae0f2aee345e218be646c25616b22b54c38943238dd68af250ba094cb7155b52","target":"graph","created_at":"2026-07-05T08:26:32Z","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/2406.00899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we introduce YODAS (YouTube-Oriented Dataset for Audio and Speech), a large-scale, multilingual dataset comprising currently over 500k hours of speech data in more than 100 languages, sourced from both labeled and unlabeled YouTube speech datasets. The labeled subsets, including manual or automatic subtitles, facilitate supervised model training. Conversely, the unlabeled subsets are apt for self-supervised learning applications. YODAS is distinctive as the first publicly available dataset of its scale, and it is distributed under a Creative Commons license. We introduce the col","authors_text":"Sayaka Shiota, Shinji Watanabe, Shinnosuke Takamichi, Takaaki Saeki, William Chen, Xinjian Li","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T23:43:27Z","title":"YODAS: Youtube-Oriented Dataset for Audio and Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00899","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:c821e84279ce046239e86d6dd518338008c8dc17fe628a7bce06c38cb03e6fd1","target":"record","created_at":"2026-07-05T08:26:32Z","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":"fd2589350f683a044c5fd3225b00d50a0b0784afa23227bc629a14325be51bbc","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T23:43:27Z","title_canon_sha256":"d1df57584bfda5cb1f785e2b04662570f9c854e3ffbbce9f6de8447e5c730119"},"schema_version":"1.0","source":{"id":"2406.00899","kind":"arxiv","version":1}},"canonical_sha256":"eccf2bf4d52ad4e8871dc8bef675fce8cf7778792b07d86c11f51a1b77f68e84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eccf2bf4d52ad4e8871dc8bef675fce8cf7778792b07d86c11f51a1b77f68e84","first_computed_at":"2026-07-05T08:26:32.363969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:32.363969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8jsh+ZcSpZVhEwcLJ6gZHu8E0/y7gfquB9HZnvhhw9M4iGd1wvak7oVw0y+QPPoZwJ/nXG1I1aT79kl9EigEAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:32.364438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00899","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c821e84279ce046239e86d6dd518338008c8dc17fe628a7bce06c38cb03e6fd1","sha256:ae0f2aee345e218be646c25616b22b54c38943238dd68af250ba094cb7155b52"],"state_sha256":"b90d4692771d71471cee9e2d228f03427cb1b6078ae6e709a870e8a39affdee3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xxyg8oCzl+sKvr6wdZwNiXpyaSUm1/pw3wIIGShWpw19PoF64CyYyEKykbDyKV2q/p1xwUHKrUO5nxoU0wYfAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:38:48.654149Z","bundle_sha256":"6226efab6bedddd7fc376c47571713c369678fe1665fa838a97f350397b23233"}}