{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PPCZJQ2AF3RGKUQPFFSDBPWUTQ","short_pith_number":"pith:PPCZJQ2A","schema_version":"1.0","canonical_sha256":"7bc594c3402ee265520f296430bed49c1445bd9adf8a3e874b691f7318194de8","source":{"kind":"arxiv","id":"2606.31608","version":1},"attestation_state":"computed","paper":{"title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abin Roy, Afthab Salam Kanniyan, Ajmal M., Jawadh Abdul Kabeer, Jerin James, Preslav Nakov, Zhuohan Xie","submitted_at":"2026-06-30T12:56:42Z","abstract_excerpt":"Large Language Models (LLMs) achieve strong results on many medical benchmarks, but their clinical reasoning remains difficult to evaluate reliably. A central risk is an evaluation illusion: fluent and well-structured explanations can appear clinically convincing even when the final diagnosis is incorrect. We introduce CLExEval, a human-in-the-loop framework for evaluating LLM clinical reasoning under progressive information masking. CLExEval combines 5,600 expert-physician annotations with 200 clinical reasoning traces derived from 40 rare diagnostic cases. Our analysis identifies three recur"},"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":"2606.31608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T12:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"1375ef3bbd355403ae2a92978dd8b9543a6ad5a82f89c88acbbd0b4cae90af90","abstract_canon_sha256":"8ab4b1f5e447f14f639de8a573798cdf3025404d3f4650d34b8249edb3b922ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:09.070107Z","signature_b64":"a0ithBHA7QogV3vco2C6PNj1iqMnvfQAOFAMvDKy42jdk0ZoEeykD+YFvdKORduFzgUQTVvnUSVovyyJhX6TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bc594c3402ee265520f296430bed49c1445bd9adf8a3e874b691f7318194de8","last_reissued_at":"2026-07-01T01:18:09.069609Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:09.069609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abin Roy, Afthab Salam Kanniyan, Ajmal M., Jawadh Abdul Kabeer, Jerin James, Preslav Nakov, Zhuohan Xie","submitted_at":"2026-06-30T12:56:42Z","abstract_excerpt":"Large Language Models (LLMs) achieve strong results on many medical benchmarks, but their clinical reasoning remains difficult to evaluate reliably. A central risk is an evaluation illusion: fluent and well-structured explanations can appear clinically convincing even when the final diagnosis is incorrect. We introduce CLExEval, a human-in-the-loop framework for evaluating LLM clinical reasoning under progressive information masking. CLExEval combines 5,600 expert-physician annotations with 200 clinical reasoning traces derived from 40 rare diagnostic cases. Our analysis identifies three recur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31608","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/2606.31608/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":"2606.31608","created_at":"2026-07-01T01:18:09.069664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31608v1","created_at":"2026-07-01T01:18:09.069664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31608","created_at":"2026-07-01T01:18:09.069664+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPCZJQ2AF3RG","created_at":"2026-07-01T01:18:09.069664+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPCZJQ2AF3RGKUQP","created_at":"2026-07-01T01:18:09.069664+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPCZJQ2A","created_at":"2026-07-01T01:18:09.069664+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/PPCZJQ2AF3RGKUQPFFSDBPWUTQ","json":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ.json","graph_json":"https://pith.science/api/pith-number/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/graph.json","events_json":"https://pith.science/api/pith-number/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/events.json","paper":"https://pith.science/paper/PPCZJQ2A"},"agent_actions":{"view_html":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ","download_json":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ.json","view_paper":"https://pith.science/paper/PPCZJQ2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31608&json=true","fetch_graph":"https://pith.science/api/pith-number/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/action/storage_attestation","attest_author":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/action/author_attestation","sign_citation":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/action/citation_signature","submit_replication":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/action/replication_record"}},"created_at":"2026-07-01T01:18:09.069664+00:00","updated_at":"2026-07-01T01:18:09.069664+00:00"}