{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:TTPO72BK5QO524LW7HLLKYM2OY","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":"a849156ec3542022f2a4a98ac5dfe1a36ea3e59f0b08758d133c568bbf5a712d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T10:45:23Z","title_canon_sha256":"d148a0d611e403b5d8989a32bd058bf0765efa47e1fc2f054888b097fa22703b"},"schema_version":"1.0","source":{"id":"1702.02363","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.02363","created_at":"2026-05-18T00:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"1702.02363v2","created_at":"2026-05-18T00:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02363","created_at":"2026-05-18T00:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"TTPO72BK5QO5","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"TTPO72BK5QO524LW","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"TTPO72BK","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:61a86404852928bb3a196541d0c65ef9a4714ce0eb1b01c4ed6fbdd4d316d251","target":"graph","created_at":"2026-05-18T00:51:02Z","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"},"paper":{"abstract_excerpt":"Turkish Wikipedia Named-Entity Recognition and Text Categorization (TWNERTC) dataset is a collection of automatically categorized and annotated sentences obtained from Wikipedia. We constructed large-scale gazetteers by using a graph crawler algorithm to extract relevant entity and domain information from a semantic knowledge base, Freebase. The constructed gazetteers contains approximately 300K entities with thousands of fine-grained entity types under 77 different domains. Since automated processes are prone to ambiguity, we also introduce two new content specific noise reduction methodologi","authors_text":"Caglar Tirkaz, Eray Yildiz, H. Bahadir Sahin, Mustafa Tolga Eren, Ozan Sonmez","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T10:45:23Z","title":"Automatically Annotated Turkish Corpus for Named Entity Recognition and Text Categorization using Large-Scale Gazetteers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02363","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":"sha256:2827c605908fbe84eceb3b78ba3a9ccdea3fb3dae5bc6e572be0d673cda6602b","target":"record","created_at":"2026-05-18T00:51:02Z","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":"a849156ec3542022f2a4a98ac5dfe1a36ea3e59f0b08758d133c568bbf5a712d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T10:45:23Z","title_canon_sha256":"d148a0d611e403b5d8989a32bd058bf0765efa47e1fc2f054888b097fa22703b"},"schema_version":"1.0","source":{"id":"1702.02363","kind":"arxiv","version":2}},"canonical_sha256":"9cdeefe82aec1ddd7176f9d6b5619a7602763c7cd45858fbf35953c4eb5d1f84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cdeefe82aec1ddd7176f9d6b5619a7602763c7cd45858fbf35953c4eb5d1f84","first_computed_at":"2026-05-18T00:51:02.717241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:02.717241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HhrzStvQo1N3K7Wcuuxebc6hl79VFajUxwRJlH9PEsBvXbZlts/JIi8XcsMF+oaL95qhXNV+6tuViYw3q8BwDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:02.717698Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.02363","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2827c605908fbe84eceb3b78ba3a9ccdea3fb3dae5bc6e572be0d673cda6602b","sha256:61a86404852928bb3a196541d0c65ef9a4714ce0eb1b01c4ed6fbdd4d316d251"],"state_sha256":"3290a8bd0977722ccfa8a3eee462365ac1dec33724daf840b04ecb5fadfd042d"}