{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LA526ICRLRCGJHXYUUPFGJMFPQ","short_pith_number":"pith:LA526ICR","schema_version":"1.0","canonical_sha256":"583baf20515c44649ef8a51e5325857c081a8f1dfb42859852bd11015f0a2594","source":{"kind":"arxiv","id":"1911.06915","version":1},"attestation_state":"computed","paper":{"title":"Evaluating robustness of language models for chief complaint extraction from patient-generated text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caleb Goodwin, Daniel S. Zisook, Ian M. Finn, Ilya Valmianski, Naqi Khan","submitted_at":"2019-11-15T23:37:41Z","abstract_excerpt":"Automated classification of chief complaints from patient-generated text is a critical first step in developing scalable platforms to triage patients without human intervention. In this work, we evaluate several approaches to chief complaint classification using a novel Chief Complaint (CC) Dataset that contains ~200,000 patient-generated reasons-for-visit entries mapped to a set of 795 discrete chief complaints. We examine the use of several fine-tuned bidirectional transformer (BERT) models trained on both unrelated texts as well as on the CC dataset. We contrast this performance with a TF-I"},"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":"1911.06915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-15T23:37:41Z","cross_cats_sorted":[],"title_canon_sha256":"4963ecabaf1486cf4a136244a6e2e4260ecb213565f6125f9ee6875ca658c6d0","abstract_canon_sha256":"83aaa61398800deaa3368cb0ddb5a182fd26324e672e679c34b2ec8fd7b6888b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:40.657744Z","signature_b64":"3Df5HNCcBermgIf3BG7lDnvI9fZdKvnZvx0rIGZq3l+RPEiNK+7pl2aA3D6O1houU28BpTZ4nUeXQmmAdUs0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"583baf20515c44649ef8a51e5325857c081a8f1dfb42859852bd11015f0a2594","last_reissued_at":"2026-07-05T00:19:40.657176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:40.657176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating robustness of language models for chief complaint extraction from patient-generated text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caleb Goodwin, Daniel S. Zisook, Ian M. Finn, Ilya Valmianski, Naqi Khan","submitted_at":"2019-11-15T23:37:41Z","abstract_excerpt":"Automated classification of chief complaints from patient-generated text is a critical first step in developing scalable platforms to triage patients without human intervention. In this work, we evaluate several approaches to chief complaint classification using a novel Chief Complaint (CC) Dataset that contains ~200,000 patient-generated reasons-for-visit entries mapped to a set of 795 discrete chief complaints. We examine the use of several fine-tuned bidirectional transformer (BERT) models trained on both unrelated texts as well as on the CC dataset. We contrast this performance with a TF-I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06915","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/1911.06915/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":"1911.06915","created_at":"2026-07-05T00:19:40.657266+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.06915v1","created_at":"2026-07-05T00:19:40.657266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06915","created_at":"2026-07-05T00:19:40.657266+00:00"},{"alias_kind":"pith_short_12","alias_value":"LA526ICRLRCG","created_at":"2026-07-05T00:19:40.657266+00:00"},{"alias_kind":"pith_short_16","alias_value":"LA526ICRLRCGJHXY","created_at":"2026-07-05T00:19:40.657266+00:00"},{"alias_kind":"pith_short_8","alias_value":"LA526ICR","created_at":"2026-07-05T00:19:40.657266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01899","citing_title":"Weakly Supervised Medical Entity Extraction and Linking for Chief Complaints","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LA526ICRLRCGJHXYUUPFGJMFPQ","json":"https://pith.science/pith/LA526ICRLRCGJHXYUUPFGJMFPQ.json","graph_json":"https://pith.science/api/pith-number/LA526ICRLRCGJHXYUUPFGJMFPQ/graph.json","events_json":"https://pith.science/api/pith-number/LA526ICRLRCGJHXYUUPFGJMFPQ/events.json","paper":"https://pith.science/paper/LA526ICR"},"agent_actions":{"view_html":"https://pith.science/pith/LA526ICRLRCGJHXYUUPFGJMFPQ","download_json":"https://pith.science/pith/LA526ICRLRCGJHXYUUPFGJMFPQ.json","view_paper":"https://pith.science/paper/LA526ICR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.06915&json=true","fetch_graph":"https://pith.science/api/pith-number/LA526ICRLRCGJHXYUUPFGJMFPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LA526ICRLRCGJHXYUUPFGJMFPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LA526ICRLRCGJHXYUUPFGJMFPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LA526ICRLRCGJHXYUUPFGJMFPQ/action/storage_attestation","attest_author":"https://pith.science/pith/LA526ICRLRCGJHXYUUPFGJMFPQ/action/author_attestation","sign_citation":"https://pith.science/pith/LA526ICRLRCGJHXYUUPFGJMFPQ/action/citation_signature","submit_replication":"https://pith.science/pith/LA526ICRLRCGJHXYUUPFGJMFPQ/action/replication_record"}},"created_at":"2026-07-05T00:19:40.657266+00:00","updated_at":"2026-07-05T00:19:40.657266+00:00"}