{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EACNUH3RMLKK4SIERHLHMFPI7E","short_pith_number":"pith:EACNUH3R","schema_version":"1.0","canonical_sha256":"2004da1f7162d4ae490489d67615e8f923a0df0b4e06740402a023f459384273","source":{"kind":"arxiv","id":"2210.07586","version":4},"attestation_state":"computed","paper":{"title":"Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hyunjae Kim, Jaehyo Yoo, Jaewoo Kang, Seunghyun Yoon","submitted_at":"2022-10-14T07:36:44Z","abstract_excerpt":"Most weakly supervised named entity recognition (NER) models rely on domain-specific dictionaries provided by experts. This approach is infeasible in many domains where dictionaries do not exist. While a phrase retrieval model was used to construct pseudo-dictionaries with entities retrieved from Wikipedia automatically in a recent study, these dictionaries often have limited coverage because the retriever is likely to retrieve popular entities rather than rare ones. In this study, we present a novel framework, HighGEN, that generates NER datasets with high-coverage pseudo-dictionaries. Specif"},"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":"2210.07586","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T07:36:44Z","cross_cats_sorted":[],"title_canon_sha256":"c4bc652a84576a523b0c10a690fa5e7787fd9814f009045e50b47870a9715c47","abstract_canon_sha256":"d94484df1ff0519ae9134432a29a32bacb3a70753a42701a1eb7f22764b2f6b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:12.022356Z","signature_b64":"hWwXLcDxwPVnbw6W58sJhqaDDJWaTLR9DcAg7KLu/uW0AbUE6BSZNXEOwX2Z8eUXICUV7rrOTa//EXnBoy0uBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2004da1f7162d4ae490489d67615e8f923a0df0b4e06740402a023f459384273","last_reissued_at":"2026-07-05T06:16:12.021833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:12.021833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Creation of Named Entity Recognition Datasets by Querying Phrase Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hyunjae Kim, Jaehyo Yoo, Jaewoo Kang, Seunghyun Yoon","submitted_at":"2022-10-14T07:36:44Z","abstract_excerpt":"Most weakly supervised named entity recognition (NER) models rely on domain-specific dictionaries provided by experts. This approach is infeasible in many domains where dictionaries do not exist. While a phrase retrieval model was used to construct pseudo-dictionaries with entities retrieved from Wikipedia automatically in a recent study, these dictionaries often have limited coverage because the retriever is likely to retrieve popular entities rather than rare ones. In this study, we present a novel framework, HighGEN, that generates NER datasets with high-coverage pseudo-dictionaries. Specif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07586","kind":"arxiv","version":4},"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/2210.07586/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.07586","created_at":"2026-07-05T06:16:12.021894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07586v4","created_at":"2026-07-05T06:16:12.021894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07586","created_at":"2026-07-05T06:16:12.021894+00:00"},{"alias_kind":"pith_short_12","alias_value":"EACNUH3RMLKK","created_at":"2026-07-05T06:16:12.021894+00:00"},{"alias_kind":"pith_short_16","alias_value":"EACNUH3RMLKK4SIE","created_at":"2026-07-05T06:16:12.021894+00:00"},{"alias_kind":"pith_short_8","alias_value":"EACNUH3R","created_at":"2026-07-05T06:16:12.021894+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/EACNUH3RMLKK4SIERHLHMFPI7E","json":"https://pith.science/pith/EACNUH3RMLKK4SIERHLHMFPI7E.json","graph_json":"https://pith.science/api/pith-number/EACNUH3RMLKK4SIERHLHMFPI7E/graph.json","events_json":"https://pith.science/api/pith-number/EACNUH3RMLKK4SIERHLHMFPI7E/events.json","paper":"https://pith.science/paper/EACNUH3R"},"agent_actions":{"view_html":"https://pith.science/pith/EACNUH3RMLKK4SIERHLHMFPI7E","download_json":"https://pith.science/pith/EACNUH3RMLKK4SIERHLHMFPI7E.json","view_paper":"https://pith.science/paper/EACNUH3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07586&json=true","fetch_graph":"https://pith.science/api/pith-number/EACNUH3RMLKK4SIERHLHMFPI7E/graph.json","fetch_events":"https://pith.science/api/pith-number/EACNUH3RMLKK4SIERHLHMFPI7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EACNUH3RMLKK4SIERHLHMFPI7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EACNUH3RMLKK4SIERHLHMFPI7E/action/storage_attestation","attest_author":"https://pith.science/pith/EACNUH3RMLKK4SIERHLHMFPI7E/action/author_attestation","sign_citation":"https://pith.science/pith/EACNUH3RMLKK4SIERHLHMFPI7E/action/citation_signature","submit_replication":"https://pith.science/pith/EACNUH3RMLKK4SIERHLHMFPI7E/action/replication_record"}},"created_at":"2026-07-05T06:16:12.021894+00:00","updated_at":"2026-07-05T06:16:12.021894+00:00"}