{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RZ3OHK563P4V5E4QBEE2WKWRUZ","short_pith_number":"pith:RZ3OHK56","canonical_record":{"source":{"id":"2009.10334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-09-22T05:57:15Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"6332db2ec22f4aee3b4e3612f19534d37ae7711eb89af7aa656cd52d7815b6c3","abstract_canon_sha256":"28cf23186bc9bab8338f20a6a8ed1f593379417245fcef1bd0123e5db5ab64ff"},"schema_version":"1.0"},"canonical_sha256":"8e76e3abbedbf95e93900909ab2ad1a67b3189933c7f521ee8a4b78ef0a55d8d","source":{"kind":"arxiv","id":"2009.10334","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10334","created_at":"2026-07-05T02:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10334v2","created_at":"2026-07-05T02:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10334","created_at":"2026-07-05T02:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"RZ3OHK563P4V","created_at":"2026-07-05T02:59:35Z"},{"alias_kind":"pith_short_16","alias_value":"RZ3OHK563P4V5E4Q","created_at":"2026-07-05T02:59:35Z"},{"alias_kind":"pith_short_8","alias_value":"RZ3OHK56","created_at":"2026-07-05T02:59:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RZ3OHK563P4V5E4QBEE2WKWRUZ","target":"record","payload":{"canonical_record":{"source":{"id":"2009.10334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-09-22T05:57:15Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"6332db2ec22f4aee3b4e3612f19534d37ae7711eb89af7aa656cd52d7815b6c3","abstract_canon_sha256":"28cf23186bc9bab8338f20a6a8ed1f593379417245fcef1bd0123e5db5ab64ff"},"schema_version":"1.0"},"canonical_sha256":"8e76e3abbedbf95e93900909ab2ad1a67b3189933c7f521ee8a4b78ef0a55d8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:35.403706Z","signature_b64":"7j8KjEBCvjBYHxgOhLISCn4ZxmfT9aqAgWrRodN1EN/U+2a7MgAbO94ALPo2O2tQi175Q5UdxABgCyazWmJeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e76e3abbedbf95e93900909ab2ad1a67b3189933c7f521ee8a4b78ef0a55d8d","last_reissued_at":"2026-07-05T02:59:35.403308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:35.403308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.10334","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":"2026-07-05T02:59:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yyolvmkCwrZi1mEpXwoIas4tmtw7FKn+KDcUnKHX5deIFFI/5Gc1oe6+VNV87tUl430xJF/6yt15RTKc3+3kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:57:40.624588Z"},"content_sha256":"b6091cf4ab6b80a3f86c64b68462521e17c22e6553e5149ac8a0c4ff6e87bb90","schema_version":"1.0","event_id":"sha256:b6091cf4ab6b80a3f86c64b68462521e17c22e6553e5149ac8a0c4ff6e87bb90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RZ3OHK563P4V5E4QBEE2WKWRUZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alen Adiyev, Almas Mirzakhmetov, Huseyin Atakan Varol, Mukhamet Nurpeiissov, Saida Mussakhojayeva, Yerbolat Khassanov","submitted_at":"2020-09-22T05:57:15Z","abstract_excerpt":"We present an open-source speech corpus for the Kazakh language. The Kazakh speech corpus (KSC) contains around 332 hours of transcribed audio comprising over 153,000 utterances spoken by participants from different regions and age groups, as well as both genders. It was carefully inspected by native Kazakh speakers to ensure high quality. The KSC is the largest publicly available database developed to advance various Kazakh speech and language processing applications. In this paper, we first describe the data collection and preprocessing procedures followed by a description of the database sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10334","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/2009.10334/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":"2026-07-05T02:59:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2JleFzE2Vh89PIj8KGld2J1lwqRNxtw8waUsRBbecSNXDbygw8aIDaOB35sQq8f5pJRB8INqTWe/7aucu10Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T02:57:40.625495Z"},"content_sha256":"6eb1d89e9331bf8241cae58eae597e994259c73200dec42a7bf3339400941436","schema_version":"1.0","event_id":"sha256:6eb1d89e9331bf8241cae58eae597e994259c73200dec42a7bf3339400941436"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZ3OHK563P4V5E4QBEE2WKWRUZ/bundle.json","state_url":"https://pith.science/pith/RZ3OHK563P4V5E4QBEE2WKWRUZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZ3OHK563P4V5E4QBEE2WKWRUZ/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":"2026-08-01T02:57:40Z","links":{"resolver":"https://pith.science/pith/RZ3OHK563P4V5E4QBEE2WKWRUZ","bundle":"https://pith.science/pith/RZ3OHK563P4V5E4QBEE2WKWRUZ/bundle.json","state":"https://pith.science/pith/RZ3OHK563P4V5E4QBEE2WKWRUZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZ3OHK563P4V5E4QBEE2WKWRUZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RZ3OHK563P4V5E4QBEE2WKWRUZ","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":"28cf23186bc9bab8338f20a6a8ed1f593379417245fcef1bd0123e5db5ab64ff","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-09-22T05:57:15Z","title_canon_sha256":"6332db2ec22f4aee3b4e3612f19534d37ae7711eb89af7aa656cd52d7815b6c3"},"schema_version":"1.0","source":{"id":"2009.10334","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10334","created_at":"2026-07-05T02:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10334v2","created_at":"2026-07-05T02:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10334","created_at":"2026-07-05T02:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"RZ3OHK563P4V","created_at":"2026-07-05T02:59:35Z"},{"alias_kind":"pith_short_16","alias_value":"RZ3OHK563P4V5E4Q","created_at":"2026-07-05T02:59:35Z"},{"alias_kind":"pith_short_8","alias_value":"RZ3OHK56","created_at":"2026-07-05T02:59:35Z"}],"graph_snapshots":[{"event_id":"sha256:6eb1d89e9331bf8241cae58eae597e994259c73200dec42a7bf3339400941436","target":"graph","created_at":"2026-07-05T02:59:35Z","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/2009.10334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an open-source speech corpus for the Kazakh language. The Kazakh speech corpus (KSC) contains around 332 hours of transcribed audio comprising over 153,000 utterances spoken by participants from different regions and age groups, as well as both genders. It was carefully inspected by native Kazakh speakers to ensure high quality. The KSC is the largest publicly available database developed to advance various Kazakh speech and language processing applications. In this paper, we first describe the data collection and preprocessing procedures followed by a description of the database sp","authors_text":"Alen Adiyev, Almas Mirzakhmetov, Huseyin Atakan Varol, Mukhamet Nurpeiissov, Saida Mussakhojayeva, Yerbolat Khassanov","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-09-22T05:57:15Z","title":"A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10334","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:b6091cf4ab6b80a3f86c64b68462521e17c22e6553e5149ac8a0c4ff6e87bb90","target":"record","created_at":"2026-07-05T02:59:35Z","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":"28cf23186bc9bab8338f20a6a8ed1f593379417245fcef1bd0123e5db5ab64ff","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-09-22T05:57:15Z","title_canon_sha256":"6332db2ec22f4aee3b4e3612f19534d37ae7711eb89af7aa656cd52d7815b6c3"},"schema_version":"1.0","source":{"id":"2009.10334","kind":"arxiv","version":2}},"canonical_sha256":"8e76e3abbedbf95e93900909ab2ad1a67b3189933c7f521ee8a4b78ef0a55d8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e76e3abbedbf95e93900909ab2ad1a67b3189933c7f521ee8a4b78ef0a55d8d","first_computed_at":"2026-07-05T02:59:35.403308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:59:35.403308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7j8KjEBCvjBYHxgOhLISCn4ZxmfT9aqAgWrRodN1EN/U+2a7MgAbO94ALPo2O2tQi175Q5UdxABgCyazWmJeBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:59:35.403706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.10334","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6091cf4ab6b80a3f86c64b68462521e17c22e6553e5149ac8a0c4ff6e87bb90","sha256:6eb1d89e9331bf8241cae58eae597e994259c73200dec42a7bf3339400941436"],"state_sha256":"477fbe5cc22e696279b6b1d11081193964e6590348f1f8caadd1b4dd3813f0a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+zV2/Te2hRsX+nhX/itpx4NOJvsffRnPB1gafjAvlqUz2wr0R7v2OoggYCo+fmRqaaTUUU0Xcdf9W/VZF0YZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T02:57:40.633233Z","bundle_sha256":"efcc56ff3567989a734cfa662056683ad620c45e4b573ec691ea01fe2b39c6d2"}}