{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:22SL37BHHRDBZCPLVHUYZ5MBIL","short_pith_number":"pith:22SL37BH","schema_version":"1.0","canonical_sha256":"d6a4bdfc273c461c89eba9e98cf58142fb0591dfb5843c86b3abbe573b4986a0","source":{"kind":"arxiv","id":"2304.07396","version":2},"attestation_state":"computed","paper":{"title":"Improving Patient Pre-screening for Clinical Trials: Assisting Physicians with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Daniel Kapitan, Danny M. den Hamer, Perry Schoor, Tobias B. Polak","submitted_at":"2023-04-14T21:19:46Z","abstract_excerpt":"Physicians considering clinical trials for their patients are met with the laborious process of checking many text based eligibility criteria. Large Language Models (LLMs) have shown to perform well for clinical information extraction and clinical reasoning, including medical tests, but not yet in real-world scenarios. This paper investigates the use of InstructGPT to assist physicians in determining eligibility for clinical trials based on a patient's summarised medical profile. Using a prompting strategy combining one-shot, selection-inference and chain-of-thought techniques, we investigate "},"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":"2304.07396","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-14T21:19:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7e6136c41104bde73b7a942d272e8bda8e9f3e85a96f98f2edb59617188a8210","abstract_canon_sha256":"33dbbccbf8d22c36bedf377d44f66b5e4368e6dd55884726fc20b60d507391e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:01.710178Z","signature_b64":"Uuc+JOUR3YwDJAd7vzIjZhLZpCTiywSV1m1E4mCaIxwU2T8sxIyp5+AHr6F0AqyTYrng73ubsiBq1jpKtuBMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6a4bdfc273c461c89eba9e98cf58142fb0591dfb5843c86b3abbe573b4986a0","last_reissued_at":"2026-07-05T06:26:01.709683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:01.709683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Patient Pre-screening for Clinical Trials: Assisting Physicians with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Daniel Kapitan, Danny M. den Hamer, Perry Schoor, Tobias B. Polak","submitted_at":"2023-04-14T21:19:46Z","abstract_excerpt":"Physicians considering clinical trials for their patients are met with the laborious process of checking many text based eligibility criteria. Large Language Models (LLMs) have shown to perform well for clinical information extraction and clinical reasoning, including medical tests, but not yet in real-world scenarios. This paper investigates the use of InstructGPT to assist physicians in determining eligibility for clinical trials based on a patient's summarised medical profile. Using a prompting strategy combining one-shot, selection-inference and chain-of-thought techniques, we investigate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.07396","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.07396/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":"2304.07396","created_at":"2026-07-05T06:26:01.709741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.07396v2","created_at":"2026-07-05T06:26:01.709741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.07396","created_at":"2026-07-05T06:26:01.709741+00:00"},{"alias_kind":"pith_short_12","alias_value":"22SL37BHHRDB","created_at":"2026-07-05T06:26:01.709741+00:00"},{"alias_kind":"pith_short_16","alias_value":"22SL37BHHRDBZCPL","created_at":"2026-07-05T06:26:01.709741+00:00"},{"alias_kind":"pith_short_8","alias_value":"22SL37BH","created_at":"2026-07-05T06:26:01.709741+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28044","citing_title":"A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05740","citing_title":"RECOVER: Designing a Large Language Model-based Remote Patient Monitoring System for Postoperative Gastrointestinal Cancer Care","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/22SL37BHHRDBZCPLVHUYZ5MBIL","json":"https://pith.science/pith/22SL37BHHRDBZCPLVHUYZ5MBIL.json","graph_json":"https://pith.science/api/pith-number/22SL37BHHRDBZCPLVHUYZ5MBIL/graph.json","events_json":"https://pith.science/api/pith-number/22SL37BHHRDBZCPLVHUYZ5MBIL/events.json","paper":"https://pith.science/paper/22SL37BH"},"agent_actions":{"view_html":"https://pith.science/pith/22SL37BHHRDBZCPLVHUYZ5MBIL","download_json":"https://pith.science/pith/22SL37BHHRDBZCPLVHUYZ5MBIL.json","view_paper":"https://pith.science/paper/22SL37BH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.07396&json=true","fetch_graph":"https://pith.science/api/pith-number/22SL37BHHRDBZCPLVHUYZ5MBIL/graph.json","fetch_events":"https://pith.science/api/pith-number/22SL37BHHRDBZCPLVHUYZ5MBIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22SL37BHHRDBZCPLVHUYZ5MBIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22SL37BHHRDBZCPLVHUYZ5MBIL/action/storage_attestation","attest_author":"https://pith.science/pith/22SL37BHHRDBZCPLVHUYZ5MBIL/action/author_attestation","sign_citation":"https://pith.science/pith/22SL37BHHRDBZCPLVHUYZ5MBIL/action/citation_signature","submit_replication":"https://pith.science/pith/22SL37BHHRDBZCPLVHUYZ5MBIL/action/replication_record"}},"created_at":"2026-07-05T06:26:01.709741+00:00","updated_at":"2026-07-05T06:26:01.709741+00:00"}