{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TTPO72BK5QO524LW7HLLKYM2OY","short_pith_number":"pith:TTPO72BK","schema_version":"1.0","canonical_sha256":"9cdeefe82aec1ddd7176f9d6b5619a7602763c7cd45858fbf35953c4eb5d1f84","source":{"kind":"arxiv","id":"1702.02363","version":2},"attestation_state":"computed","paper":{"title":"Automatically Annotated Turkish Corpus for Named Entity Recognition and Text Categorization using Large-Scale Gazetteers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caglar Tirkaz, Eray Yildiz, H. Bahadir Sahin, Mustafa Tolga Eren, Ozan Sonmez","submitted_at":"2017-02-08T10:45:23Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1702.02363","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-08T10:45:23Z","cross_cats_sorted":[],"title_canon_sha256":"d148a0d611e403b5d8989a32bd058bf0765efa47e1fc2f054888b097fa22703b","abstract_canon_sha256":"a849156ec3542022f2a4a98ac5dfe1a36ea3e59f0b08758d133c568bbf5a712d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:02.717698Z","signature_b64":"HhrzStvQo1N3K7Wcuuxebc6hl79VFajUxwRJlH9PEsBvXbZlts/JIi8XcsMF+oaL95qhXNV+6tuViYw3q8BwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cdeefe82aec1ddd7176f9d6b5619a7602763c7cd45858fbf35953c4eb5d1f84","last_reissued_at":"2026-05-18T00:51:02.717241Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:02.717241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatically Annotated Turkish Corpus for Named Entity Recognition and Text Categorization using Large-Scale Gazetteers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caglar Tirkaz, Eray Yildiz, H. Bahadir Sahin, Mustafa Tolga Eren, Ozan Sonmez","submitted_at":"2017-02-08T10:45:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02363","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1702.02363","created_at":"2026-05-18T00:51:02.717310+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.02363v2","created_at":"2026-05-18T00:51:02.717310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02363","created_at":"2026-05-18T00:51:02.717310+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTPO72BK5QO5","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTPO72BK5QO524LW","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTPO72BK","created_at":"2026-05-18T12:31:46.661854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTPO72BK5QO524LW7HLLKYM2OY","json":"https://pith.science/pith/TTPO72BK5QO524LW7HLLKYM2OY.json","graph_json":"https://pith.science/api/pith-number/TTPO72BK5QO524LW7HLLKYM2OY/graph.json","events_json":"https://pith.science/api/pith-number/TTPO72BK5QO524LW7HLLKYM2OY/events.json","paper":"https://pith.science/paper/TTPO72BK"},"agent_actions":{"view_html":"https://pith.science/pith/TTPO72BK5QO524LW7HLLKYM2OY","download_json":"https://pith.science/pith/TTPO72BK5QO524LW7HLLKYM2OY.json","view_paper":"https://pith.science/paper/TTPO72BK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.02363&json=true","fetch_graph":"https://pith.science/api/pith-number/TTPO72BK5QO524LW7HLLKYM2OY/graph.json","fetch_events":"https://pith.science/api/pith-number/TTPO72BK5QO524LW7HLLKYM2OY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTPO72BK5QO524LW7HLLKYM2OY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTPO72BK5QO524LW7HLLKYM2OY/action/storage_attestation","attest_author":"https://pith.science/pith/TTPO72BK5QO524LW7HLLKYM2OY/action/author_attestation","sign_citation":"https://pith.science/pith/TTPO72BK5QO524LW7HLLKYM2OY/action/citation_signature","submit_replication":"https://pith.science/pith/TTPO72BK5QO524LW7HLLKYM2OY/action/replication_record"}},"created_at":"2026-05-18T00:51:02.717310+00:00","updated_at":"2026-05-18T00:51:02.717310+00:00"}