{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WUVDLOGMNX3XCDW6EEVM7ZHEPF","short_pith_number":"pith:WUVDLOGM","schema_version":"1.0","canonical_sha256":"b52a35b8cc6df7710ede212acfe4e4795439b57aca0ab72fe105ba2c9e22778b","source":{"kind":"arxiv","id":"2506.00612","version":3},"attestation_state":"computed","paper":{"title":"Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Minghui Chen, Running Yang, Wenlong Deng, Xiaoxiao Li, Yuyin Zhou","submitted_at":"2025-05-31T15:51:09Z","abstract_excerpt":"Clinical tasks such as diagnosis and treatment require strong decision-making abilities, highlighting the importance of rigorous evaluation benchmarks to assess the reliability of large language models (LLMs). In this work, we introduce a knowledge-guided data augmentation framework that enhances the difficulty of clinical multiple-choice question (MCQ) datasets by generating distractors (i.e., incorrect choices that are similar to the correct one and may confuse existing LLMs). Using our KG-based pipeline, the generated choices are both clinically plausible and deliberately misleading. Our ap"},"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":"2506.00612","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T15:51:09Z","cross_cats_sorted":[],"title_canon_sha256":"570f7d2f5af253ff7bc1c09ab040881f2ceec8d5e43fb329d56889b2dd2d0696","abstract_canon_sha256":"8e1f0031ab198be163e01bc08c61b7915981d7648b0a1a52729fdf79402e4162"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:28.262973Z","signature_b64":"ou8YdvCh/uuSOHkNWvjaVZqsN1yVEm4g7DQjffemyz9IXkE/0Ke/q/9rzsODh40RLOj52ZPcUQBCPs4jm5SYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b52a35b8cc6df7710ede212acfe4e4795439b57aca0ab72fe105ba2c9e22778b","last_reissued_at":"2026-07-05T11:31:28.262489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:28.262489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Minghui Chen, Running Yang, Wenlong Deng, Xiaoxiao Li, Yuyin Zhou","submitted_at":"2025-05-31T15:51:09Z","abstract_excerpt":"Clinical tasks such as diagnosis and treatment require strong decision-making abilities, highlighting the importance of rigorous evaluation benchmarks to assess the reliability of large language models (LLMs). In this work, we introduce a knowledge-guided data augmentation framework that enhances the difficulty of clinical multiple-choice question (MCQ) datasets by generating distractors (i.e., incorrect choices that are similar to the correct one and may confuse existing LLMs). Using our KG-based pipeline, the generated choices are both clinically plausible and deliberately misleading. Our ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00612","kind":"arxiv","version":3},"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/2506.00612/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":"2506.00612","created_at":"2026-07-05T11:31:28.262549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00612v3","created_at":"2026-07-05T11:31:28.262549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00612","created_at":"2026-07-05T11:31:28.262549+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUVDLOGMNX3X","created_at":"2026-07-05T11:31:28.262549+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUVDLOGMNX3XCDW6","created_at":"2026-07-05T11:31:28.262549+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUVDLOGM","created_at":"2026-07-05T11:31:28.262549+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/WUVDLOGMNX3XCDW6EEVM7ZHEPF","json":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF.json","graph_json":"https://pith.science/api/pith-number/WUVDLOGMNX3XCDW6EEVM7ZHEPF/graph.json","events_json":"https://pith.science/api/pith-number/WUVDLOGMNX3XCDW6EEVM7ZHEPF/events.json","paper":"https://pith.science/paper/WUVDLOGM"},"agent_actions":{"view_html":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF","download_json":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF.json","view_paper":"https://pith.science/paper/WUVDLOGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00612&json=true","fetch_graph":"https://pith.science/api/pith-number/WUVDLOGMNX3XCDW6EEVM7ZHEPF/graph.json","fetch_events":"https://pith.science/api/pith-number/WUVDLOGMNX3XCDW6EEVM7ZHEPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/action/storage_attestation","attest_author":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/action/author_attestation","sign_citation":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/action/citation_signature","submit_replication":"https://pith.science/pith/WUVDLOGMNX3XCDW6EEVM7ZHEPF/action/replication_record"}},"created_at":"2026-07-05T11:31:28.262549+00:00","updated_at":"2026-07-05T11:31:28.262549+00:00"}