{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WECHKIVZILCM2NDMKYNAZYRWQC","short_pith_number":"pith:WECHKIVZ","canonical_record":{"source":{"id":"2110.03370","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-07T12:05:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fa99ec6d25c195b5d31fa6f600c5c49caf9b8695e594166ac283b7947ada4bd5","abstract_canon_sha256":"3bdfc17293d3f52349169bfa8732825e5cd51ee1f18964e520d6c6b23efd6694"},"schema_version":"1.0"},"canonical_sha256":"b1047522b942c4cd346c561a0ce23680b20730215ccdef1f7597949a98af3ed4","source":{"kind":"arxiv","id":"2110.03370","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03370","created_at":"2026-07-05T03:59:24Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03370v5","created_at":"2026-07-05T03:59:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03370","created_at":"2026-07-05T03:59:24Z"},{"alias_kind":"pith_short_12","alias_value":"WECHKIVZILCM","created_at":"2026-07-05T03:59:24Z"},{"alias_kind":"pith_short_16","alias_value":"WECHKIVZILCM2NDM","created_at":"2026-07-05T03:59:24Z"},{"alias_kind":"pith_short_8","alias_value":"WECHKIVZ","created_at":"2026-07-05T03:59:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WECHKIVZILCM2NDMKYNAZYRWQC","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03370","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-07T12:05:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fa99ec6d25c195b5d31fa6f600c5c49caf9b8695e594166ac283b7947ada4bd5","abstract_canon_sha256":"3bdfc17293d3f52349169bfa8732825e5cd51ee1f18964e520d6c6b23efd6694"},"schema_version":"1.0"},"canonical_sha256":"b1047522b942c4cd346c561a0ce23680b20730215ccdef1f7597949a98af3ed4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:24.891083Z","signature_b64":"hkReyBcUZPM8kqOceOQIRkVsHEzI0X53aOjqLVSLzbSVk8TftkKlaro33IChTyxYZnp4FdX+okU/ToGjTWuqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1047522b942c4cd346c561a0ce23680b20730215ccdef1f7597949a98af3ed4","last_reissued_at":"2026-07-05T03:59:24.890604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:24.890604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03370","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:59:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"THOIPuJrqmcrcAIi2oR9BCNh3RfBvk6dMnE77nBDkOhIoqa0V4EPx/02EpizQtqetHYbD6YWq3RQhDakB+FODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:44:07.304236Z"},"content_sha256":"6fde90a1eed189537239338795e90c1344fb87706b02df2b641a315748d2186c","schema_version":"1.0","event_id":"sha256:6fde90a1eed189537239338795e90c1344fb87706b02df2b641a315748d2186c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WECHKIVZILCM2NDMKYNAZYRWQC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Binbin Zhang, Chao Yang, Chenchen Zeng, Di Wu, Hang Lv, Hui Bu, Lei Xie, Pengcheng Guo, Qijie Shao, Xiaoyu Chen, Xin Xu, Zhendong Peng","submitted_at":"2021-10-07T12:05:29Z","abstract_excerpt":"In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total. We collect the data from YouTube and Podcast, which covers a variety of speaking styles, scenarios, domains, topics, and noisy conditions. An optical character recognition (OCR) based method is introduced to generate the audio/text segmentation candidates for the YouTube data on its corresponding video captions, while a high-quality ASR transcription system is used to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03370","kind":"arxiv","version":5},"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/2110.03370/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":"2026-07-05T03:59:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"546H11ZC7MKiCv1lkonVsAdHL471elf7tpJYnE5RoEzFxytQ/Ha3FW/ZnaAlqIzivwKdH4D5nizAZr9tySBGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:44:07.304625Z"},"content_sha256":"cff9f05bffa7758d7d6e30eb6250023554072792069fe2290e3322360e04fe6c","schema_version":"1.0","event_id":"sha256:cff9f05bffa7758d7d6e30eb6250023554072792069fe2290e3322360e04fe6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WECHKIVZILCM2NDMKYNAZYRWQC/bundle.json","state_url":"https://pith.science/pith/WECHKIVZILCM2NDMKYNAZYRWQC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WECHKIVZILCM2NDMKYNAZYRWQC/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":"2026-07-07T10:44:07Z","links":{"resolver":"https://pith.science/pith/WECHKIVZILCM2NDMKYNAZYRWQC","bundle":"https://pith.science/pith/WECHKIVZILCM2NDMKYNAZYRWQC/bundle.json","state":"https://pith.science/pith/WECHKIVZILCM2NDMKYNAZYRWQC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WECHKIVZILCM2NDMKYNAZYRWQC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WECHKIVZILCM2NDMKYNAZYRWQC","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":"3bdfc17293d3f52349169bfa8732825e5cd51ee1f18964e520d6c6b23efd6694","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-07T12:05:29Z","title_canon_sha256":"fa99ec6d25c195b5d31fa6f600c5c49caf9b8695e594166ac283b7947ada4bd5"},"schema_version":"1.0","source":{"id":"2110.03370","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03370","created_at":"2026-07-05T03:59:24Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03370v5","created_at":"2026-07-05T03:59:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03370","created_at":"2026-07-05T03:59:24Z"},{"alias_kind":"pith_short_12","alias_value":"WECHKIVZILCM","created_at":"2026-07-05T03:59:24Z"},{"alias_kind":"pith_short_16","alias_value":"WECHKIVZILCM2NDM","created_at":"2026-07-05T03:59:24Z"},{"alias_kind":"pith_short_8","alias_value":"WECHKIVZ","created_at":"2026-07-05T03:59:24Z"}],"graph_snapshots":[{"event_id":"sha256:cff9f05bffa7758d7d6e30eb6250023554072792069fe2290e3322360e04fe6c","target":"graph","created_at":"2026-07-05T03:59:24Z","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/2110.03370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total. We collect the data from YouTube and Podcast, which covers a variety of speaking styles, scenarios, domains, topics, and noisy conditions. An optical character recognition (OCR) based method is introduced to generate the audio/text segmentation candidates for the YouTube data on its corresponding video captions, while a high-quality ASR transcription system is used to ","authors_text":"Binbin Zhang, Chao Yang, Chenchen Zeng, Di Wu, Hang Lv, Hui Bu, Lei Xie, Pengcheng Guo, Qijie Shao, Xiaoyu Chen, Xin Xu, Zhendong Peng","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-07T12:05:29Z","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03370","kind":"arxiv","version":5},"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":"sha256:6fde90a1eed189537239338795e90c1344fb87706b02df2b641a315748d2186c","target":"record","created_at":"2026-07-05T03:59:24Z","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":"3bdfc17293d3f52349169bfa8732825e5cd51ee1f18964e520d6c6b23efd6694","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-10-07T12:05:29Z","title_canon_sha256":"fa99ec6d25c195b5d31fa6f600c5c49caf9b8695e594166ac283b7947ada4bd5"},"schema_version":"1.0","source":{"id":"2110.03370","kind":"arxiv","version":5}},"canonical_sha256":"b1047522b942c4cd346c561a0ce23680b20730215ccdef1f7597949a98af3ed4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1047522b942c4cd346c561a0ce23680b20730215ccdef1f7597949a98af3ed4","first_computed_at":"2026-07-05T03:59:24.890604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:59:24.890604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hkReyBcUZPM8kqOceOQIRkVsHEzI0X53aOjqLVSLzbSVk8TftkKlaro33IChTyxYZnp4FdX+okU/ToGjTWuqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:59:24.891083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03370","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fde90a1eed189537239338795e90c1344fb87706b02df2b641a315748d2186c","sha256:cff9f05bffa7758d7d6e30eb6250023554072792069fe2290e3322360e04fe6c"],"state_sha256":"3a583173c49845fe7f3386ccce8b6e5619727b229a626cf162960ffcfc2ab732"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A25OoinpFOhXdOysa9cOsRLc1NhkhsY+nBgl+sLmWbKklJeBvOHWD6fZGVR1sKL6An4Xn7z8UWpd4XTf9x8mCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:44:07.306706Z","bundle_sha256":"c7598c8e21ae4c5641686bbafcf8cf13cd8372b9d21d411c95f96ba5c3208315"}}