{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ETF75T2LANCSO27CP6HRHBXA2V","short_pith_number":"pith:ETF75T2L","canonical_record":{"source":{"id":"2106.06909","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-13T04:09:16Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"52c2ee6a45fed9e3a76b8f02bb73f45d62494df3719a7878707d1148396fb447","abstract_canon_sha256":"985aead5c96abcd46b6e7426a6570d18ad94690c7f2f68656b9a5421c9a6c0c9"},"schema_version":"1.0"},"canonical_sha256":"24cbfecf4b0345276be27f8f1386e0d56f333d32fa2acc4cfa5c80b3dbb901e3","source":{"kind":"arxiv","id":"2106.06909","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06909","created_at":"2026-07-05T10:57:51Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06909v1","created_at":"2026-07-05T10:57:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06909","created_at":"2026-07-05T10:57:51Z"},{"alias_kind":"pith_short_12","alias_value":"ETF75T2LANCS","created_at":"2026-07-05T10:57:51Z"},{"alias_kind":"pith_short_16","alias_value":"ETF75T2LANCSO27C","created_at":"2026-07-05T10:57:51Z"},{"alias_kind":"pith_short_8","alias_value":"ETF75T2L","created_at":"2026-07-05T10:57:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ETF75T2LANCSO27CP6HRHBXA2V","target":"record","payload":{"canonical_record":{"source":{"id":"2106.06909","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-13T04:09:16Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"52c2ee6a45fed9e3a76b8f02bb73f45d62494df3719a7878707d1148396fb447","abstract_canon_sha256":"985aead5c96abcd46b6e7426a6570d18ad94690c7f2f68656b9a5421c9a6c0c9"},"schema_version":"1.0"},"canonical_sha256":"24cbfecf4b0345276be27f8f1386e0d56f333d32fa2acc4cfa5c80b3dbb901e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:51.209230Z","signature_b64":"VP743xaYNT/Rw4VgRQxVNFkC6nV/e4cLRP4AjaWJ/9GvGRcXy5yAuXKeo4x4CvVdf3M7/Sxf3QV2ffp74sn8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24cbfecf4b0345276be27f8f1386e0d56f333d32fa2acc4cfa5c80b3dbb901e3","last_reissued_at":"2026-07-05T10:57:51.208719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:51.208719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.06909","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":"2026-07-05T10:57:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zzioP7cKjwcRUjMfRKGTQGlcHL280rSsXNTNjpAWd0j6ZB/1QFwLdB1xcUHUle69aSrT6HLuI5xbLEHiMp0ZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T01:55:31.474695Z"},"content_sha256":"042f1f9b0e93dabadff1a2bb76ccc4a38cfb20196ddee6883039f17d62418b7a","schema_version":"1.0","event_id":"sha256:042f1f9b0e93dabadff1a2bb76ccc4a38cfb20196ddee6883039f17d62418b7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ETF75T2LANCSO27CP6HRHBXA2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Weng, Daniel Povey, Dan Su, Guanbo Wang, Guoguo Chen, Jan Trmal, Jiayu Du, Junbo Zhang, Mingjie Jin, Sanjeev Khudanpur, Shinji Watanabe, Shuaijiang Zhao, Shuzhou Chai, Wei-Qiang Zhang, Wei Zou, Xiangang Li, Xuchen Yao, Yongqing Wang, Yujun Wang, Zhao You, Zhiyong Yan","submitted_at":"2021-06-13T04:09:16Z","abstract_excerpt":"This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06909","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/2106.06909/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":"2026-07-05T10:57:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9UHqmN4pXaxX2z4D/uE5CaaVu9Jw/BUCcZFk9WipXNYdFFutbmOWyHKVckABDCR5TUo2SLe1dvzt55qU81PDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T01:55:31.475062Z"},"content_sha256":"b327239b76a7f41113ecf8e331df5da383ed3fdb4b614d636afd6b190af36765","schema_version":"1.0","event_id":"sha256:b327239b76a7f41113ecf8e331df5da383ed3fdb4b614d636afd6b190af36765"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ETF75T2LANCSO27CP6HRHBXA2V/bundle.json","state_url":"https://pith.science/pith/ETF75T2LANCSO27CP6HRHBXA2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ETF75T2LANCSO27CP6HRHBXA2V/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":"2026-07-21T01:55:31Z","links":{"resolver":"https://pith.science/pith/ETF75T2LANCSO27CP6HRHBXA2V","bundle":"https://pith.science/pith/ETF75T2LANCSO27CP6HRHBXA2V/bundle.json","state":"https://pith.science/pith/ETF75T2LANCSO27CP6HRHBXA2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ETF75T2LANCSO27CP6HRHBXA2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ETF75T2LANCSO27CP6HRHBXA2V","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":"985aead5c96abcd46b6e7426a6570d18ad94690c7f2f68656b9a5421c9a6c0c9","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-13T04:09:16Z","title_canon_sha256":"52c2ee6a45fed9e3a76b8f02bb73f45d62494df3719a7878707d1148396fb447"},"schema_version":"1.0","source":{"id":"2106.06909","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06909","created_at":"2026-07-05T10:57:51Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06909v1","created_at":"2026-07-05T10:57:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06909","created_at":"2026-07-05T10:57:51Z"},{"alias_kind":"pith_short_12","alias_value":"ETF75T2LANCS","created_at":"2026-07-05T10:57:51Z"},{"alias_kind":"pith_short_16","alias_value":"ETF75T2LANCSO27C","created_at":"2026-07-05T10:57:51Z"},{"alias_kind":"pith_short_8","alias_value":"ETF75T2L","created_at":"2026-07-05T10:57:51Z"}],"graph_snapshots":[{"event_id":"sha256:b327239b76a7f41113ecf8e331df5da383ed3fdb4b614d636afd6b190af36765","target":"graph","created_at":"2026-07-05T10:57:51Z","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/2106.06909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition tra","authors_text":"Chao Weng, Daniel Povey, Dan Su, Guanbo Wang, Guoguo Chen, Jan Trmal, Jiayu Du, Junbo Zhang, Mingjie Jin, Sanjeev Khudanpur, Shinji Watanabe, Shuaijiang Zhao, Shuzhou Chai, Wei-Qiang Zhang, Wei Zou, Xiangang Li, Xuchen Yao, Yongqing Wang, Yujun Wang, Zhao You, Zhiyong Yan","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-13T04:09:16Z","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06909","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":"sha256:042f1f9b0e93dabadff1a2bb76ccc4a38cfb20196ddee6883039f17d62418b7a","target":"record","created_at":"2026-07-05T10:57:51Z","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":"985aead5c96abcd46b6e7426a6570d18ad94690c7f2f68656b9a5421c9a6c0c9","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-13T04:09:16Z","title_canon_sha256":"52c2ee6a45fed9e3a76b8f02bb73f45d62494df3719a7878707d1148396fb447"},"schema_version":"1.0","source":{"id":"2106.06909","kind":"arxiv","version":1}},"canonical_sha256":"24cbfecf4b0345276be27f8f1386e0d56f333d32fa2acc4cfa5c80b3dbb901e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24cbfecf4b0345276be27f8f1386e0d56f333d32fa2acc4cfa5c80b3dbb901e3","first_computed_at":"2026-07-05T10:57:51.208719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:51.208719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VP743xaYNT/Rw4VgRQxVNFkC6nV/e4cLRP4AjaWJ/9GvGRcXy5yAuXKeo4x4CvVdf3M7/Sxf3QV2ffp74sn8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:51.209230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06909","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:042f1f9b0e93dabadff1a2bb76ccc4a38cfb20196ddee6883039f17d62418b7a","sha256:b327239b76a7f41113ecf8e331df5da383ed3fdb4b614d636afd6b190af36765"],"state_sha256":"deeb57d8d1c0202170bb2aea37d7b9ac81822fc8d5e3b41729e72118376fc8c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AoCIrFdJg8uL7Oz7Jn0WDRSxevK3SqReY2VUor4W59+qDibb0GO/OOjMlXHEK4b/2gWz7y7eKwdbNrauy2ccBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T01:55:31.477112Z","bundle_sha256":"05fb4953ddc74dc1cd7dc086dca562293139e3f13ff3e1dfbef3b7882ef15ff3"}}