{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4BGYCO2GR5VL2ACQO7LNALZIMO","short_pith_number":"pith:4BGYCO2G","schema_version":"1.0","canonical_sha256":"e04d813b468f6abd005077d6d02f2863ac61b7f7b4d31eb546f0ce34f050952a","source":{"kind":"arxiv","id":"2403.16158","version":1},"attestation_state":"computed","paper":{"title":"Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaeyoung Oh, Dongjun Jang, Hyopil Shin, Jean Seo, Jiseung Hong, Minseok Kim, Sumin Park, Sungjoo Byun","submitted_at":"2024-03-24T13:51:05Z","abstract_excerpt":"Named Entity Recognition (NER) plays a pivotal role in medical Natural Language Processing (NLP). Yet, there has not been an open-source medical NER dataset specifically for the Korean language. To address this, we utilized ChatGPT to assist in constructing the KBMC (Korean Bio-Medical Corpus), which we are now presenting to the public. With the KBMC dataset, we noticed an impressive 20% increase in medical NER performance compared to models trained on general Korean NER datasets. This research underscores the significant benefits and importance of using specialized tools and datasets, like Ch"},"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":"2403.16158","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-24T13:51:05Z","cross_cats_sorted":[],"title_canon_sha256":"ef116ed46a42125f5029938fd830ffc47c51d1656c2aafd0438a81d57b672fb6","abstract_canon_sha256":"a7b7139a97b6d5ed175f2a3a5fd191051416045ca93f8374c1c863f7de911a3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:11.319485Z","signature_b64":"1nu0lDVe+8KLyQJjUtCH2D3CwfQvsfWBldVonHbDWC7datWtDLOIBK7P/18QBy4M/CH41xPIgDNEeKU/sJbQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e04d813b468f6abd005077d6d02f2863ac61b7f7b4d31eb546f0ce34f050952a","last_reissued_at":"2026-07-05T08:00:11.319101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:11.319101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaeyoung Oh, Dongjun Jang, Hyopil Shin, Jean Seo, Jiseung Hong, Minseok Kim, Sumin Park, Sungjoo Byun","submitted_at":"2024-03-24T13:51:05Z","abstract_excerpt":"Named Entity Recognition (NER) plays a pivotal role in medical Natural Language Processing (NLP). Yet, there has not been an open-source medical NER dataset specifically for the Korean language. To address this, we utilized ChatGPT to assist in constructing the KBMC (Korean Bio-Medical Corpus), which we are now presenting to the public. With the KBMC dataset, we noticed an impressive 20% increase in medical NER performance compared to models trained on general Korean NER datasets. This research underscores the significant benefits and importance of using specialized tools and datasets, like Ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16158","kind":"arxiv","version":1},"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/2403.16158/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":"2403.16158","created_at":"2026-07-05T08:00:11.319156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16158v1","created_at":"2026-07-05T08:00:11.319156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16158","created_at":"2026-07-05T08:00:11.319156+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BGYCO2GR5VL","created_at":"2026-07-05T08:00:11.319156+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BGYCO2GR5VL2ACQ","created_at":"2026-07-05T08:00:11.319156+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BGYCO2G","created_at":"2026-07-05T08:00:11.319156+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/4BGYCO2GR5VL2ACQO7LNALZIMO","json":"https://pith.science/pith/4BGYCO2GR5VL2ACQO7LNALZIMO.json","graph_json":"https://pith.science/api/pith-number/4BGYCO2GR5VL2ACQO7LNALZIMO/graph.json","events_json":"https://pith.science/api/pith-number/4BGYCO2GR5VL2ACQO7LNALZIMO/events.json","paper":"https://pith.science/paper/4BGYCO2G"},"agent_actions":{"view_html":"https://pith.science/pith/4BGYCO2GR5VL2ACQO7LNALZIMO","download_json":"https://pith.science/pith/4BGYCO2GR5VL2ACQO7LNALZIMO.json","view_paper":"https://pith.science/paper/4BGYCO2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16158&json=true","fetch_graph":"https://pith.science/api/pith-number/4BGYCO2GR5VL2ACQO7LNALZIMO/graph.json","fetch_events":"https://pith.science/api/pith-number/4BGYCO2GR5VL2ACQO7LNALZIMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BGYCO2GR5VL2ACQO7LNALZIMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BGYCO2GR5VL2ACQO7LNALZIMO/action/storage_attestation","attest_author":"https://pith.science/pith/4BGYCO2GR5VL2ACQO7LNALZIMO/action/author_attestation","sign_citation":"https://pith.science/pith/4BGYCO2GR5VL2ACQO7LNALZIMO/action/citation_signature","submit_replication":"https://pith.science/pith/4BGYCO2GR5VL2ACQO7LNALZIMO/action/replication_record"}},"created_at":"2026-07-05T08:00:11.319156+00:00","updated_at":"2026-07-05T08:00:11.319156+00:00"}