{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:K2QNO65JR2TQVTDRS7NXNTXZG4","short_pith_number":"pith:K2QNO65J","canonical_record":{"source":{"id":"2111.13419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-26T10:56:19Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"bcc4df5724608b52d60edda44c69aba321c5f5a0c27050ae38d1f8cdf6220912","abstract_canon_sha256":"17f0acf389decd063ad96e1db93958f051ecea99a79056d615660e6f2485dda8"},"schema_version":"1.0"},"canonical_sha256":"56a0d77ba98ea70acc7197db76cef9370023976b44708632b942616cab8187bf","source":{"kind":"arxiv","id":"2111.13419","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.13419","created_at":"2026-07-05T04:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"2111.13419v2","created_at":"2026-07-05T04:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13419","created_at":"2026-07-05T04:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"K2QNO65JR2TQ","created_at":"2026-07-05T04:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"K2QNO65JR2TQVTDR","created_at":"2026-07-05T04:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"K2QNO65J","created_at":"2026-07-05T04:12:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:K2QNO65JR2TQVTDRS7NXNTXZG4","target":"record","payload":{"canonical_record":{"source":{"id":"2111.13419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-26T10:56:19Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"bcc4df5724608b52d60edda44c69aba321c5f5a0c27050ae38d1f8cdf6220912","abstract_canon_sha256":"17f0acf389decd063ad96e1db93958f051ecea99a79056d615660e6f2485dda8"},"schema_version":"1.0"},"canonical_sha256":"56a0d77ba98ea70acc7197db76cef9370023976b44708632b942616cab8187bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:16.869465Z","signature_b64":"jrbNbEFgH46S1DCBMt0++jfNipMLAYaAWFAi1gfdroWX3RMGNVZr/XuGVdBoBOv7BBlHhDcH6ScWuwo32H0VAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56a0d77ba98ea70acc7197db76cef9370023976b44708632b942616cab8187bf","last_reissued_at":"2026-07-05T04:12:16.869036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:16.869036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.13419","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":"2026-07-05T04:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dMc4sPjUXuX3m1zumb2h5jAf+3XuTpLg5qzXRQH8iq8IBs7Ov850r8CAp9Qu8jAmTHHW3ZpHWF4gF8zLDoExAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:12:50.107737Z"},"content_sha256":"68bb4c6ab56db5766aa80af31f08aa44e864c4e72a9c7d2330121acf31a0198b","schema_version":"1.0","event_id":"sha256:68bb4c6ab56db5766aa80af31f08aa44e864c4e72a9c7d2330121acf31a0198b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:K2QNO65JR2TQVTDRS7NXNTXZG4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KazNERD: Kazakh Named Entity Recognition Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Huseyin Atakan Varol, Rustem Yeshpanov, Yerbolat Khassanov","submitted_at":"2021-11-26T10:56:19Z","abstract_excerpt":"We present the development of a dataset for Kazakh named entity recognition. The dataset was built as there is a clear need for publicly available annotated corpora in Kazakh, as well as annotation guidelines containing straightforward--but rigorous--rules and examples. The dataset annotation, based on the IOB2 scheme, was carried out on television news text by two native Kazakh speakers under the supervision of the first author. The resulting dataset contains 112,702 sentences and 136,333 annotations for 25 entity classes. State-of-the-art machine learning models to automatise Kazakh named en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13419","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/2111.13419/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":"2026-07-05T04:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqfvvXF3S2AU3pQidoBhLiJ9Pa4OwFHjkxsmIwIlV4vJpmqg7oV31AUOOrx9ph0wRXzH+c1Z/H9MzL6TLKZJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:12:50.108293Z"},"content_sha256":"c5729cc90fdd04ad7266a65a27c6c365a9d697515905614931104fe9f565f6e1","schema_version":"1.0","event_id":"sha256:c5729cc90fdd04ad7266a65a27c6c365a9d697515905614931104fe9f565f6e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2QNO65JR2TQVTDRS7NXNTXZG4/bundle.json","state_url":"https://pith.science/pith/K2QNO65JR2TQVTDRS7NXNTXZG4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2QNO65JR2TQVTDRS7NXNTXZG4/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":"2026-08-16T20:12:50Z","links":{"resolver":"https://pith.science/pith/K2QNO65JR2TQVTDRS7NXNTXZG4","bundle":"https://pith.science/pith/K2QNO65JR2TQVTDRS7NXNTXZG4/bundle.json","state":"https://pith.science/pith/K2QNO65JR2TQVTDRS7NXNTXZG4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2QNO65JR2TQVTDRS7NXNTXZG4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:K2QNO65JR2TQVTDRS7NXNTXZG4","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":"17f0acf389decd063ad96e1db93958f051ecea99a79056d615660e6f2485dda8","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-26T10:56:19Z","title_canon_sha256":"bcc4df5724608b52d60edda44c69aba321c5f5a0c27050ae38d1f8cdf6220912"},"schema_version":"1.0","source":{"id":"2111.13419","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.13419","created_at":"2026-07-05T04:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"2111.13419v2","created_at":"2026-07-05T04:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13419","created_at":"2026-07-05T04:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"K2QNO65JR2TQ","created_at":"2026-07-05T04:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"K2QNO65JR2TQVTDR","created_at":"2026-07-05T04:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"K2QNO65J","created_at":"2026-07-05T04:12:16Z"}],"graph_snapshots":[{"event_id":"sha256:c5729cc90fdd04ad7266a65a27c6c365a9d697515905614931104fe9f565f6e1","target":"graph","created_at":"2026-07-05T04:12:16Z","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/2111.13419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the development of a dataset for Kazakh named entity recognition. The dataset was built as there is a clear need for publicly available annotated corpora in Kazakh, as well as annotation guidelines containing straightforward--but rigorous--rules and examples. The dataset annotation, based on the IOB2 scheme, was carried out on television news text by two native Kazakh speakers under the supervision of the first author. The resulting dataset contains 112,702 sentences and 136,333 annotations for 25 entity classes. State-of-the-art machine learning models to automatise Kazakh named en","authors_text":"Huseyin Atakan Varol, Rustem Yeshpanov, Yerbolat Khassanov","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-26T10:56:19Z","title":"KazNERD: Kazakh Named Entity Recognition Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13419","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":"sha256:68bb4c6ab56db5766aa80af31f08aa44e864c4e72a9c7d2330121acf31a0198b","target":"record","created_at":"2026-07-05T04:12:16Z","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":"17f0acf389decd063ad96e1db93958f051ecea99a79056d615660e6f2485dda8","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-26T10:56:19Z","title_canon_sha256":"bcc4df5724608b52d60edda44c69aba321c5f5a0c27050ae38d1f8cdf6220912"},"schema_version":"1.0","source":{"id":"2111.13419","kind":"arxiv","version":2}},"canonical_sha256":"56a0d77ba98ea70acc7197db76cef9370023976b44708632b942616cab8187bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56a0d77ba98ea70acc7197db76cef9370023976b44708632b942616cab8187bf","first_computed_at":"2026-07-05T04:12:16.869036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:16.869036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jrbNbEFgH46S1DCBMt0++jfNipMLAYaAWFAi1gfdroWX3RMGNVZr/XuGVdBoBOv7BBlHhDcH6ScWuwo32H0VAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:16.869465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.13419","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68bb4c6ab56db5766aa80af31f08aa44e864c4e72a9c7d2330121acf31a0198b","sha256:c5729cc90fdd04ad7266a65a27c6c365a9d697515905614931104fe9f565f6e1"],"state_sha256":"a305eceac51ccb82551215cc0b8ee1c61abd3041567411647233f1c1265e484d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z+/jVrkjINELxSciriZS9wBZy+wxcVZCrlKhV+w3fwzvEXGjBW90SrmarjtIpBHS4BGU1+873115j4dAXkJxDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:12:50.113114Z","bundle_sha256":"0a7cad0231976a24852d0bbf749413c89e64c2fd03a0a5109855e67a05d7c693"}}