{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HZUTTGM25COFMI7SWAH4VTFVAE","short_pith_number":"pith:HZUTTGM2","schema_version":"1.0","canonical_sha256":"3e6939999ae89c5623f2b00fcaccb5012c513d8af9d8bbcbbbf6224fb2883dd9","source":{"kind":"arxiv","id":"2411.00299","version":2},"attestation_state":"computed","paper":{"title":"RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Julian Acosta, L. John Fahrner, Oishi Banerjee, Pranav Rajpurkar, Serena Zhang, Sraavya Sambara","submitted_at":"2024-11-01T01:38:42Z","abstract_excerpt":"Generating accurate radiology reports from medical images is a clinically important but challenging task. While current Vision Language Models (VLMs) show promise, they are prone to generating hallucinations, potentially compromising patient care. We introduce RadFlag, a black-box method to enhance the accuracy of radiology report generation. Our method uses a sampling-based flagging technique to find hallucinatory generations that should be removed. We first sample multiple reports at varying temperatures and then use a Large Language Model (LLM) to identify claims that are not consistently s"},"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":"2411.00299","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T01:38:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f1f0ef6fec16a9954e3bef87ab29d12323a7e9b251d48ac1c10f93a815163559","abstract_canon_sha256":"291a6262ada173dde73c498e0ca875c835f0a4e058555f2162998751959f33d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:15.727849Z","signature_b64":"siiPGkYWAQcWFifY5XMHeqWklcJFlO7AgjOBPh2tfGh6BtROB3jxwB8ssESB6BYzzwOk0WJuP2bkGwRyRca5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e6939999ae89c5623f2b00fcaccb5012c513d8af9d8bbcbbbf6224fb2883dd9","last_reissued_at":"2026-07-05T09:36:15.727297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:15.727297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Julian Acosta, L. John Fahrner, Oishi Banerjee, Pranav Rajpurkar, Serena Zhang, Sraavya Sambara","submitted_at":"2024-11-01T01:38:42Z","abstract_excerpt":"Generating accurate radiology reports from medical images is a clinically important but challenging task. While current Vision Language Models (VLMs) show promise, they are prone to generating hallucinations, potentially compromising patient care. We introduce RadFlag, a black-box method to enhance the accuracy of radiology report generation. Our method uses a sampling-based flagging technique to find hallucinatory generations that should be removed. We first sample multiple reports at varying temperatures and then use a Large Language Model (LLM) to identify claims that are not consistently s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00299","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/2411.00299/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":"2411.00299","created_at":"2026-07-05T09:36:15.727366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00299v2","created_at":"2026-07-05T09:36:15.727366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00299","created_at":"2026-07-05T09:36:15.727366+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZUTTGM25COF","created_at":"2026-07-05T09:36:15.727366+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZUTTGM25COFMI7S","created_at":"2026-07-05T09:36:15.727366+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZUTTGM2","created_at":"2026-07-05T09:36:15.727366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18609","citing_title":"Hallucination Detection and Correction in Medical VLMs via Counter-Evidence Verification","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31407","citing_title":"Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20772","citing_title":"VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20772","citing_title":"VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02543","citing_title":"Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03476","citing_title":"CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZUTTGM25COFMI7SWAH4VTFVAE","json":"https://pith.science/pith/HZUTTGM25COFMI7SWAH4VTFVAE.json","graph_json":"https://pith.science/api/pith-number/HZUTTGM25COFMI7SWAH4VTFVAE/graph.json","events_json":"https://pith.science/api/pith-number/HZUTTGM25COFMI7SWAH4VTFVAE/events.json","paper":"https://pith.science/paper/HZUTTGM2"},"agent_actions":{"view_html":"https://pith.science/pith/HZUTTGM25COFMI7SWAH4VTFVAE","download_json":"https://pith.science/pith/HZUTTGM25COFMI7SWAH4VTFVAE.json","view_paper":"https://pith.science/paper/HZUTTGM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00299&json=true","fetch_graph":"https://pith.science/api/pith-number/HZUTTGM25COFMI7SWAH4VTFVAE/graph.json","fetch_events":"https://pith.science/api/pith-number/HZUTTGM25COFMI7SWAH4VTFVAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZUTTGM25COFMI7SWAH4VTFVAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZUTTGM25COFMI7SWAH4VTFVAE/action/storage_attestation","attest_author":"https://pith.science/pith/HZUTTGM25COFMI7SWAH4VTFVAE/action/author_attestation","sign_citation":"https://pith.science/pith/HZUTTGM25COFMI7SWAH4VTFVAE/action/citation_signature","submit_replication":"https://pith.science/pith/HZUTTGM25COFMI7SWAH4VTFVAE/action/replication_record"}},"created_at":"2026-07-05T09:36:15.727366+00:00","updated_at":"2026-07-05T09:36:15.727366+00:00"}