{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DWHJCWDWULDPLXUHDFVSS4N2IU","short_pith_number":"pith:DWHJCWDW","schema_version":"1.0","canonical_sha256":"1d8e915876a2c6f5de87196b2971ba45129b3069e6f480caa84e39e4051048fb","source":{"kind":"arxiv","id":"2407.02730","version":1},"attestation_state":"computed","paper":{"title":"MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changchang Yin, Fenglin Liu, Ping Zhang, Zishan Gu","submitted_at":"2024-07-03T00:59:03Z","abstract_excerpt":"Large Vision Language Models (LVLMs) have recently achieved superior performance in various tasks on natural image and text data, which inspires a large amount of studies for LVLMs fine-tuning and training. Despite their advancements, there has been scant research on the robustness of these models against hallucination when fine-tuned on smaller datasets. In this study, we introduce a new benchmark dataset, the Medical Visual Hallucination Test (MedVH), to evaluate the hallucination of domain-specific LVLMs. MedVH comprises five tasks to evaluate hallucinations in LVLMs within the medical cont"},"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":"2407.02730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T00:59:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55c97e1d5da1279fd8ac3350bc4b9f2034d3ecddea7c1f56f1e5d6389bdbb4fb","abstract_canon_sha256":"19680be443518da17c63ccce2cf90eaa7ffba61ff44ba66c004f51bed6181547"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:40.692658Z","signature_b64":"0hN+DqjInPbzYwGfqplW9WU90BSTEy+kMKuSLezNdZPTZ8SU0v3Jw34bTTZAdXb331aZGoPkshBrNt4pimCTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d8e915876a2c6f5de87196b2971ba45129b3069e6f480caa84e39e4051048fb","last_reissued_at":"2026-07-05T08:39:40.692182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:40.692182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changchang Yin, Fenglin Liu, Ping Zhang, Zishan Gu","submitted_at":"2024-07-03T00:59:03Z","abstract_excerpt":"Large Vision Language Models (LVLMs) have recently achieved superior performance in various tasks on natural image and text data, which inspires a large amount of studies for LVLMs fine-tuning and training. Despite their advancements, there has been scant research on the robustness of these models against hallucination when fine-tuned on smaller datasets. In this study, we introduce a new benchmark dataset, the Medical Visual Hallucination Test (MedVH), to evaluate the hallucination of domain-specific LVLMs. MedVH comprises five tasks to evaluate hallucinations in LVLMs within the medical cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02730","kind":"arxiv","version":1},"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/2407.02730/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":"2407.02730","created_at":"2026-07-05T08:39:40.692240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02730v1","created_at":"2026-07-05T08:39:40.692240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02730","created_at":"2026-07-05T08:39:40.692240+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWHJCWDWULDP","created_at":"2026-07-05T08:39:40.692240+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWHJCWDWULDPLXUH","created_at":"2026-07-05T08:39:40.692240+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWHJCWDW","created_at":"2026-07-05T08:39:40.692240+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07919","citing_title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20469","citing_title":"HalluCXR: Benchmarking and Mitigating Hallucinations in Medical Vision-Language Models for Chest Radiograph Interpretation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07919","citing_title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWHJCWDWULDPLXUHDFVSS4N2IU","json":"https://pith.science/pith/DWHJCWDWULDPLXUHDFVSS4N2IU.json","graph_json":"https://pith.science/api/pith-number/DWHJCWDWULDPLXUHDFVSS4N2IU/graph.json","events_json":"https://pith.science/api/pith-number/DWHJCWDWULDPLXUHDFVSS4N2IU/events.json","paper":"https://pith.science/paper/DWHJCWDW"},"agent_actions":{"view_html":"https://pith.science/pith/DWHJCWDWULDPLXUHDFVSS4N2IU","download_json":"https://pith.science/pith/DWHJCWDWULDPLXUHDFVSS4N2IU.json","view_paper":"https://pith.science/paper/DWHJCWDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02730&json=true","fetch_graph":"https://pith.science/api/pith-number/DWHJCWDWULDPLXUHDFVSS4N2IU/graph.json","fetch_events":"https://pith.science/api/pith-number/DWHJCWDWULDPLXUHDFVSS4N2IU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWHJCWDWULDPLXUHDFVSS4N2IU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWHJCWDWULDPLXUHDFVSS4N2IU/action/storage_attestation","attest_author":"https://pith.science/pith/DWHJCWDWULDPLXUHDFVSS4N2IU/action/author_attestation","sign_citation":"https://pith.science/pith/DWHJCWDWULDPLXUHDFVSS4N2IU/action/citation_signature","submit_replication":"https://pith.science/pith/DWHJCWDWULDPLXUHDFVSS4N2IU/action/replication_record"}},"created_at":"2026-07-05T08:39:40.692240+00:00","updated_at":"2026-07-05T08:39:40.692240+00:00"}