{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HXWMX2MY76VFBLLF23A3OC5MMG","short_pith_number":"pith:HXWMX2MY","canonical_record":{"source":{"id":"2406.11546","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T13:44:20Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"b15bfa94c2b1ec4a1944bf578350284d272a3b7832a161186fea099fbb00e9cb","abstract_canon_sha256":"0c67afb709983a764f09fc3bfc5eaaafd0ee477019e8e2e56f7c37cb9d673c0d"},"schema_version":"1.0"},"canonical_sha256":"3deccbe998ffaa50ad65d6c1b70bac61984e8451527e012215ce6ece9cf0b8a7","source":{"kind":"arxiv","id":"2406.11546","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11546","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11546v2","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11546","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"HXWMX2MY76VF","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"HXWMX2MY76VFBLLF","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"HXWMX2MY","created_at":"2026-07-05T11:09:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HXWMX2MY76VFBLLF23A3OC5MMG","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11546","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T13:44:20Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"b15bfa94c2b1ec4a1944bf578350284d272a3b7832a161186fea099fbb00e9cb","abstract_canon_sha256":"0c67afb709983a764f09fc3bfc5eaaafd0ee477019e8e2e56f7c37cb9d673c0d"},"schema_version":"1.0"},"canonical_sha256":"3deccbe998ffaa50ad65d6c1b70bac61984e8451527e012215ce6ece9cf0b8a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:59.604540Z","signature_b64":"WzIyB4gBdEVNV44oiw4m1aZInO1r6+CRqeiCcD50J4LtN+6Zd7TV9TXXAXiQvG6FyUVzOCYB/QFv0e3S8VMcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3deccbe998ffaa50ad65d6c1b70bac61984e8451527e012215ce6ece9cf0b8a7","last_reissued_at":"2026-07-05T11:09:59.604002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:59.604002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11546","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CHbgf0hO3Z6PWRuunoMmp6cvnm6zsbvcQoKgLmyQcRw4VyJ4HFBBNbSCbMzK1gMu+chuGx0q1oAu2KMWXtmrCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:37:39.775657Z"},"content_sha256":"948a2226ef83016e688b1337f21ab28a2c820fbc152f74ff6949d4dd46ad5a69","schema_version":"1.0","event_id":"sha256:948a2226ef83016e688b1337f21ab28a2c820fbc152f74ff6949d4dd46ad5a69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HXWMX2MY76VFBLLF23A3OC5MMG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo Yang, Guoguo Chen, Jianheng Zhuo, Jinpeng Li, Kai Yu, Ke Li, Mingyu Cui, Shuai Fan, Wei-Qiang Zhang, Xie Chen, Xunying Liu, Yexing Du, Yifan Yang, Zheshu Song, Ziyang Ma, Ziyuan Wang","submitted_at":"2024-06-17T13:44:20Z","abstract_excerpt":"The evolution of speech technology has been spurred by the rapid increase in dataset sizes. Traditional speech models generally depend on a large amount of labeled training data, which is scarce for low-resource languages. This paper presents GigaSpeech 2, a large-scale, multi-domain, multilingual speech recognition corpus. It is designed for low-resource languages and does not rely on paired speech and text data. GigaSpeech 2 comprises about 30,000 hours of automatically transcribed speech, including Thai, Indonesian, and Vietnamese, gathered from unlabeled YouTube videos. We also introduce a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11546","kind":"arxiv","version":2},"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/2406.11546/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":"2026-07-05T11:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q8xRwynAHFrJS/Xae4YUMeruDIKHSkLQySivpKrIDyJeJjuuFTSFLxZGXcwGBdeM2dRaEJ+E6/53txffAB8dDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:37:39.776250Z"},"content_sha256":"961ba1d135dca2ba5b49c0820c6d97c73fb58966f8ab1a2ed9d18c76b050883a","schema_version":"1.0","event_id":"sha256:961ba1d135dca2ba5b49c0820c6d97c73fb58966f8ab1a2ed9d18c76b050883a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HXWMX2MY76VFBLLF23A3OC5MMG/bundle.json","state_url":"https://pith.science/pith/HXWMX2MY76VFBLLF23A3OC5MMG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HXWMX2MY76VFBLLF23A3OC5MMG/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":"2026-08-04T07:37:39Z","links":{"resolver":"https://pith.science/pith/HXWMX2MY76VFBLLF23A3OC5MMG","bundle":"https://pith.science/pith/HXWMX2MY76VFBLLF23A3OC5MMG/bundle.json","state":"https://pith.science/pith/HXWMX2MY76VFBLLF23A3OC5MMG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HXWMX2MY76VFBLLF23A3OC5MMG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HXWMX2MY76VFBLLF23A3OC5MMG","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":"0c67afb709983a764f09fc3bfc5eaaafd0ee477019e8e2e56f7c37cb9d673c0d","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T13:44:20Z","title_canon_sha256":"b15bfa94c2b1ec4a1944bf578350284d272a3b7832a161186fea099fbb00e9cb"},"schema_version":"1.0","source":{"id":"2406.11546","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11546","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11546v2","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11546","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"HXWMX2MY76VF","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"HXWMX2MY76VFBLLF","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"HXWMX2MY","created_at":"2026-07-05T11:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:961ba1d135dca2ba5b49c0820c6d97c73fb58966f8ab1a2ed9d18c76b050883a","target":"graph","created_at":"2026-07-05T11:09:59Z","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/2406.11546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The evolution of speech technology has been spurred by the rapid increase in dataset sizes. Traditional speech models generally depend on a large amount of labeled training data, which is scarce for low-resource languages. This paper presents GigaSpeech 2, a large-scale, multi-domain, multilingual speech recognition corpus. It is designed for low-resource languages and does not rely on paired speech and text data. GigaSpeech 2 comprises about 30,000 hours of automatically transcribed speech, including Thai, Indonesian, and Vietnamese, gathered from unlabeled YouTube videos. We also introduce a","authors_text":"Bo Yang, Guoguo Chen, Jianheng Zhuo, Jinpeng Li, Kai Yu, Ke Li, Mingyu Cui, Shuai Fan, Wei-Qiang Zhang, Xie Chen, Xunying Liu, Yexing Du, Yifan Yang, Zheshu Song, Ziyang Ma, Ziyuan Wang","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T13:44:20Z","title":"GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11546","kind":"arxiv","version":2},"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":"sha256:948a2226ef83016e688b1337f21ab28a2c820fbc152f74ff6949d4dd46ad5a69","target":"record","created_at":"2026-07-05T11:09:59Z","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":"0c67afb709983a764f09fc3bfc5eaaafd0ee477019e8e2e56f7c37cb9d673c0d","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T13:44:20Z","title_canon_sha256":"b15bfa94c2b1ec4a1944bf578350284d272a3b7832a161186fea099fbb00e9cb"},"schema_version":"1.0","source":{"id":"2406.11546","kind":"arxiv","version":2}},"canonical_sha256":"3deccbe998ffaa50ad65d6c1b70bac61984e8451527e012215ce6ece9cf0b8a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3deccbe998ffaa50ad65d6c1b70bac61984e8451527e012215ce6ece9cf0b8a7","first_computed_at":"2026-07-05T11:09:59.604002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:59.604002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WzIyB4gBdEVNV44oiw4m1aZInO1r6+CRqeiCcD50J4LtN+6Zd7TV9TXXAXiQvG6FyUVzOCYB/QFv0e3S8VMcDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:59.604540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11546","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:948a2226ef83016e688b1337f21ab28a2c820fbc152f74ff6949d4dd46ad5a69","sha256:961ba1d135dca2ba5b49c0820c6d97c73fb58966f8ab1a2ed9d18c76b050883a"],"state_sha256":"cbe78115372fd5305c75fe0cd66088471cc269c88858477693fa401281947682"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sLt1TW1Ctudx45Ly3eKAlDOd7A0rWf4GdmyPy/K2vzBVnlzn13EAXBYtpBMzjvhqWNkSoewkhI+ZFGZBVFfBCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:37:39.779456Z","bundle_sha256":"b33fbb413ce53cfc39a486f75d9b816ea7f50c3bf708e35ded0de5b831a8a72c"}}