{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WJIXVSPOZO2TUBF4WPY4DZTDTW","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":"688e97685641bf3a79598e2258c608221d276acde5a00f24fecc990d974bd7e8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T06:33:23Z","title_canon_sha256":"23873cc5e0774a99b2af85a0560055a5631cdb01540c3524efc8239cf55890b5"},"schema_version":"1.0","source":{"id":"2502.14302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14302","created_at":"2026-07-05T10:17:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14302v1","created_at":"2026-07-05T10:17:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14302","created_at":"2026-07-05T10:17:24Z"},{"alias_kind":"pith_short_12","alias_value":"WJIXVSPOZO2T","created_at":"2026-07-05T10:17:24Z"},{"alias_kind":"pith_short_16","alias_value":"WJIXVSPOZO2TUBF4","created_at":"2026-07-05T10:17:24Z"},{"alias_kind":"pith_short_8","alias_value":"WJIXVSPO","created_at":"2026-07-05T10:17:24Z"}],"graph_snapshots":[{"event_id":"sha256:0240acb5a047d225e1c630127632cc2f194cc4de24d3994edb9467e38ddbfb40","target":"graph","created_at":"2026-07-05T10:17:24Z","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/2502.14302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advancements in Large Language Models (LLMs) and their increasing use in medical question-answering necessitate rigorous evaluation of their reliability. A critical challenge lies in hallucination, where models generate plausible yet factually incorrect outputs. In the medical domain, this poses serious risks to patient safety and clinical decision-making. To address this, we introduce MedHallu, the first benchmark specifically designed for medical hallucination detection. MedHallu comprises 10,000 high-quality question-answer pairs derived from PubMedQA, with hallucinated answers systematical","authors_text":"Jiawei Xu, Junyuan Hong, Kaidi Xu, Shrey Pandit, Tianlong Chen, Ying Ding, Zhangyang Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T06:33:23Z","title":"MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14302","kind":"arxiv","version":1},"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":"sha256:11dd3315c6e72a8cc75e87fca1735ccc649ae0d90b2455386bff4c1876df9029","target":"record","created_at":"2026-07-05T10:17:24Z","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":"688e97685641bf3a79598e2258c608221d276acde5a00f24fecc990d974bd7e8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T06:33:23Z","title_canon_sha256":"23873cc5e0774a99b2af85a0560055a5631cdb01540c3524efc8239cf55890b5"},"schema_version":"1.0","source":{"id":"2502.14302","kind":"arxiv","version":1}},"canonical_sha256":"b2517ac9eecbb53a04bcb3f1c1e6639dbabf4b078dfde3eb32e2e042c0af4e0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2517ac9eecbb53a04bcb3f1c1e6639dbabf4b078dfde3eb32e2e042c0af4e0e","first_computed_at":"2026-07-05T10:17:24.148766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:24.148766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"516ZoY2Xcbr7RTtmYrQEvC2OAM+rX9lYS1UtOdkRf4vD28bvcBao+xinWEKMJJguW1ByoSvODhl+ol7dOSBZAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:24.149362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11dd3315c6e72a8cc75e87fca1735ccc649ae0d90b2455386bff4c1876df9029","sha256:0240acb5a047d225e1c630127632cc2f194cc4de24d3994edb9467e38ddbfb40"],"state_sha256":"79a27c1d2643c10998d324a5fb1ee59f5a3fdb1754b4737365213a43ba50bae5"}