{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UVD4XXL3YCJ3EOROIXWLIZLXPW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b2b31427e46cfcb5ffd3fba42ad394622c3cb463a47f901e1c350d9556cd8e99","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T15:22:10Z","title_canon_sha256":"f84b664b66a725495175e7850528bb41c1f9bd7fbf6c678521539b1b91fdb79a"},"schema_version":"1.0","source":{"id":"2503.05505","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05505","created_at":"2026-07-05T11:00:05Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05505v2","created_at":"2026-07-05T11:00:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05505","created_at":"2026-07-05T11:00:05Z"},{"alias_kind":"pith_short_12","alias_value":"UVD4XXL3YCJ3","created_at":"2026-07-05T11:00:05Z"},{"alias_kind":"pith_short_16","alias_value":"UVD4XXL3YCJ3EORO","created_at":"2026-07-05T11:00:05Z"},{"alias_kind":"pith_short_8","alias_value":"UVD4XXL3","created_at":"2026-07-05T11:00:05Z"}],"graph_snapshots":[{"event_id":"sha256:083eac06432354550b8333c424362fbdf80d1bf95a0eed2d6071716ff6df41d0","target":"graph","created_at":"2026-07-05T11:00:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.05505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hongru Lin, Junya Tang, Li Li, Yusong Ke, Yuting Ruan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T15:22:10Z","title":"Correctness Coverage Evaluation for Medical Multiple-Choice Question Answering Based on the Enhanced Conformal Prediction Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05505","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:413abdc52a86c0763ddc360f7eb2de468427f319edf4356011ad1df9642b6368","target":"record","created_at":"2026-07-05T11:00:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b2b31427e46cfcb5ffd3fba42ad394622c3cb463a47f901e1c350d9556cd8e99","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-07T15:22:10Z","title_canon_sha256":"f84b664b66a725495175e7850528bb41c1f9bd7fbf6c678521539b1b91fdb79a"},"schema_version":"1.0","source":{"id":"2503.05505","kind":"arxiv","version":2}},"canonical_sha256":"a547cbdd7bc093b23a2e45ecb465777db5cf0331548dc12bba70fdae24cbca57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a547cbdd7bc093b23a2e45ecb465777db5cf0331548dc12bba70fdae24cbca57","first_computed_at":"2026-07-05T11:00:05.256845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:05.256845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R3FdO8yRTQcrcBbT/89MX0dhC5fh4VXvokdctkNwINNOYzRceFTb6sCsKXB3b3aDL9IFJCVWdEXtjqWBioBYCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:05.257355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.05505","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:413abdc52a86c0763ddc360f7eb2de468427f319edf4356011ad1df9642b6368","sha256:083eac06432354550b8333c424362fbdf80d1bf95a0eed2d6071716ff6df41d0"],"state_sha256":"59178a73ef5b50830c01f7c6b16fd178a14707bea01840e7a11f9c2d36a516d4"}