{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UVD4XXL3YCJ3EOROIXWLIZLXPW","short_pith_number":"pith:UVD4XXL3","schema_version":"1.0","canonical_sha256":"a547cbdd7bc093b23a2e45ecb465777db5cf0331548dc12bba70fdae24cbca57","source":{"kind":"arxiv","id":"2503.05505","version":2},"attestation_state":"computed","paper":{"title":"Correctness Coverage Evaluation for Medical Multiple-Choice Question Answering Based on the Enhanced Conformal Prediction Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongru Lin, Junya Tang, Li Li, Yusong Ke, Yuting Ruan","submitted_at":"2025-03-07T15:22:10Z","abstract_excerpt":"Large language models (LLMs) are increasingly adopted in medical question-answering (QA) scenarios. However, LLMs can generate hallucinations and nonfactual information, undermining their trustworthiness in high-stakes medical tasks. Conformal Prediction (CP) provides a statistically rigorous framework for marginal (average) coverage guarantees but has limited exploration in medical QA. This paper proposes an enhanced CP framework for medical multiple-choice question-answering (MCQA) tasks. By associating the non-conformance score with the frequency score of correct options and leveraging self"},"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":"2503.05505","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T15:22:10Z","cross_cats_sorted":[],"title_canon_sha256":"f84b664b66a725495175e7850528bb41c1f9bd7fbf6c678521539b1b91fdb79a","abstract_canon_sha256":"b2b31427e46cfcb5ffd3fba42ad394622c3cb463a47f901e1c350d9556cd8e99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:05.257355Z","signature_b64":"R3FdO8yRTQcrcBbT/89MX0dhC5fh4VXvokdctkNwINNOYzRceFTb6sCsKXB3b3aDL9IFJCVWdEXtjqWBioBYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a547cbdd7bc093b23a2e45ecb465777db5cf0331548dc12bba70fdae24cbca57","last_reissued_at":"2026-07-05T11:00:05.256845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:05.256845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correctness Coverage Evaluation for Medical Multiple-Choice Question Answering Based on the Enhanced Conformal Prediction Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongru Lin, Junya Tang, Li Li, Yusong Ke, Yuting Ruan","submitted_at":"2025-03-07T15:22:10Z","abstract_excerpt":"Large language models (LLMs) are increasingly adopted in medical question-answering (QA) scenarios. However, LLMs can generate hallucinations and nonfactual information, undermining their trustworthiness in high-stakes medical tasks. Conformal Prediction (CP) provides a statistically rigorous framework for marginal (average) coverage guarantees but has limited exploration in medical QA. This paper proposes an enhanced CP framework for medical multiple-choice question-answering (MCQA) tasks. By associating the non-conformance score with the frequency score of correct options and leveraging self"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05505","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/2503.05505/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":"2503.05505","created_at":"2026-07-05T11:00:05.256905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.05505v2","created_at":"2026-07-05T11:00:05.256905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05505","created_at":"2026-07-05T11:00:05.256905+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVD4XXL3YCJ3","created_at":"2026-07-05T11:00:05.256905+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVD4XXL3YCJ3EORO","created_at":"2026-07-05T11:00:05.256905+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVD4XXL3","created_at":"2026-07-05T11:00:05.256905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.17671","citing_title":"Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UVD4XXL3YCJ3EOROIXWLIZLXPW","json":"https://pith.science/pith/UVD4XXL3YCJ3EOROIXWLIZLXPW.json","graph_json":"https://pith.science/api/pith-number/UVD4XXL3YCJ3EOROIXWLIZLXPW/graph.json","events_json":"https://pith.science/api/pith-number/UVD4XXL3YCJ3EOROIXWLIZLXPW/events.json","paper":"https://pith.science/paper/UVD4XXL3"},"agent_actions":{"view_html":"https://pith.science/pith/UVD4XXL3YCJ3EOROIXWLIZLXPW","download_json":"https://pith.science/pith/UVD4XXL3YCJ3EOROIXWLIZLXPW.json","view_paper":"https://pith.science/paper/UVD4XXL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.05505&json=true","fetch_graph":"https://pith.science/api/pith-number/UVD4XXL3YCJ3EOROIXWLIZLXPW/graph.json","fetch_events":"https://pith.science/api/pith-number/UVD4XXL3YCJ3EOROIXWLIZLXPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVD4XXL3YCJ3EOROIXWLIZLXPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVD4XXL3YCJ3EOROIXWLIZLXPW/action/storage_attestation","attest_author":"https://pith.science/pith/UVD4XXL3YCJ3EOROIXWLIZLXPW/action/author_attestation","sign_citation":"https://pith.science/pith/UVD4XXL3YCJ3EOROIXWLIZLXPW/action/citation_signature","submit_replication":"https://pith.science/pith/UVD4XXL3YCJ3EOROIXWLIZLXPW/action/replication_record"}},"created_at":"2026-07-05T11:00:05.256905+00:00","updated_at":"2026-07-05T11:00:05.256905+00:00"}