{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G5QDK62SZNNJAGC26QJSWZGOTT","short_pith_number":"pith:G5QDK62S","schema_version":"1.0","canonical_sha256":"3760357b52cb5a90185af4132b64ce9cc7c69893d187a5f0fa0b185b76dc7216","source":{"kind":"arxiv","id":"2403.04890","version":4},"attestation_state":"computed","paper":{"title":"Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dinesh Raghu, Ganesh Ramakrishnan, Kshitij Sharad Jadhav, Ojas Gramopadhye, Prateek Chanda, Sachindra Joshi, Saeel Sandeep Nachane, Yatin Nandwani","submitted_at":"2024-03-07T20:48:40Z","abstract_excerpt":"In this paper, we propose a modified version of the MedQA-USMLE dataset, named MEDQA-OPEN, which contains open-ended medical questions without options to mimic clinical scenarios, along with clinician-approved reasoned answers. Additionally, we implement a prompt driven by Chain of Thought (CoT) reasoning, CLINICR, to mirror the prospective process of incremental reasoning, reaching a correct response to medical questions. We empirically demonstrate how CLINICR outperforms the state-of-the-art 5-shot CoT-based prompt (Li\\'evin et al., 2022). We also present an approach that mirrors real-life c"},"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":"2403.04890","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T20:48:40Z","cross_cats_sorted":[],"title_canon_sha256":"eb033a9508177c65587b6d5e26d17cd3ffa9204ee0629d36be3297e219f6abd0","abstract_canon_sha256":"cd5439901f459f0aed5a7e79cfea012995f7b7dcb5207e63baf055535cfdd19d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:18.432351Z","signature_b64":"0l0uBZ9f5Eq3H8K5ED/2uNsZz6B1rRsbBJJDt0ukdtC4eq74gjRB+k87oF6aLnsU9tKm7t3l+mhOkzDV3OAsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3760357b52cb5a90185af4132b64ce9cc7c69893d187a5f0fa0b185b76dc7216","last_reissued_at":"2026-06-24T01:14:18.431890Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:18.431890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dinesh Raghu, Ganesh Ramakrishnan, Kshitij Sharad Jadhav, Ojas Gramopadhye, Prateek Chanda, Sachindra Joshi, Saeel Sandeep Nachane, Yatin Nandwani","submitted_at":"2024-03-07T20:48:40Z","abstract_excerpt":"In this paper, we propose a modified version of the MedQA-USMLE dataset, named MEDQA-OPEN, which contains open-ended medical questions without options to mimic clinical scenarios, along with clinician-approved reasoned answers. Additionally, we implement a prompt driven by Chain of Thought (CoT) reasoning, CLINICR, to mirror the prospective process of incremental reasoning, reaching a correct response to medical questions. We empirically demonstrate how CLINICR outperforms the state-of-the-art 5-shot CoT-based prompt (Li\\'evin et al., 2022). We also present an approach that mirrors real-life c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04890","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/2403.04890/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":"2403.04890","created_at":"2026-06-24T01:14:18.431946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.04890v4","created_at":"2026-06-24T01:14:18.431946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04890","created_at":"2026-06-24T01:14:18.431946+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5QDK62SZNNJ","created_at":"2026-06-24T01:14:18.431946+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5QDK62SZNNJAGC2","created_at":"2026-06-24T01:14:18.431946+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5QDK62S","created_at":"2026-06-24T01:14:18.431946+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2507.20917","citing_title":"MediQAl: A French Medical Question Answering Dataset for Knowledge and Reasoning Evaluation","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2405.07960","citing_title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5QDK62SZNNJAGC26QJSWZGOTT","json":"https://pith.science/pith/G5QDK62SZNNJAGC26QJSWZGOTT.json","graph_json":"https://pith.science/api/pith-number/G5QDK62SZNNJAGC26QJSWZGOTT/graph.json","events_json":"https://pith.science/api/pith-number/G5QDK62SZNNJAGC26QJSWZGOTT/events.json","paper":"https://pith.science/paper/G5QDK62S"},"agent_actions":{"view_html":"https://pith.science/pith/G5QDK62SZNNJAGC26QJSWZGOTT","download_json":"https://pith.science/pith/G5QDK62SZNNJAGC26QJSWZGOTT.json","view_paper":"https://pith.science/paper/G5QDK62S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.04890&json=true","fetch_graph":"https://pith.science/api/pith-number/G5QDK62SZNNJAGC26QJSWZGOTT/graph.json","fetch_events":"https://pith.science/api/pith-number/G5QDK62SZNNJAGC26QJSWZGOTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5QDK62SZNNJAGC26QJSWZGOTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5QDK62SZNNJAGC26QJSWZGOTT/action/storage_attestation","attest_author":"https://pith.science/pith/G5QDK62SZNNJAGC26QJSWZGOTT/action/author_attestation","sign_citation":"https://pith.science/pith/G5QDK62SZNNJAGC26QJSWZGOTT/action/citation_signature","submit_replication":"https://pith.science/pith/G5QDK62SZNNJAGC26QJSWZGOTT/action/replication_record"}},"created_at":"2026-06-24T01:14:18.431946+00:00","updated_at":"2026-06-24T01:14:18.431946+00:00"}