{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:42LMUBKFSVZAS4TDEFJDV57MHB","short_pith_number":"pith:42LMUBKF","schema_version":"1.0","canonical_sha256":"e696ca0545957209726321523af7ec386b4e50a47900a34448a96204ce64894d","source":{"kind":"arxiv","id":"2412.00056","version":1},"attestation_state":"computed","paper":{"title":"Improving Medical Diagnostics with Vision-Language Models: Convex Hull-Based Uncertainty Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ferhat Ozgur Catak, Murat Kuzlu, Taylor Patrick","submitted_at":"2024-11-24T17:49:48Z","abstract_excerpt":"In recent years, vision-language models (VLMs) have been applied to various fields, including healthcare, education, finance, and manufacturing, with remarkable performance. However, concerns remain regarding VLMs' consistency and uncertainty, particularly in critical applications such as healthcare, which demand a high level of trust and reliability. This paper proposes a novel approach to evaluate uncertainty in VLMs' responses using a convex hull approach on a healthcare application for Visual Question Answering (VQA). LLM-CXR model is selected as the medical VLM utilized to generate respon"},"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":"2412.00056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-24T17:49:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de09f9df66d6d61bad23625d7cbec3e535c73069a9ca1c7ccb03179ab10c2168","abstract_canon_sha256":"6d68b46c56f469b5d968f58c88584e376c56850dd87906fcb2c75764cd577fa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:35.435426Z","signature_b64":"ViBcEciY3sZqkxnW+wUyFgyoUnmHI52EF9g0++pHXzMXkFEmWoFjI419WWpu3ZP5mds9Xy2KJiexYwbflvp7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e696ca0545957209726321523af7ec386b4e50a47900a34448a96204ce64894d","last_reissued_at":"2026-07-05T09:42:35.434897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:35.434897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Medical Diagnostics with Vision-Language Models: Convex Hull-Based Uncertainty Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ferhat Ozgur Catak, Murat Kuzlu, Taylor Patrick","submitted_at":"2024-11-24T17:49:48Z","abstract_excerpt":"In recent years, vision-language models (VLMs) have been applied to various fields, including healthcare, education, finance, and manufacturing, with remarkable performance. However, concerns remain regarding VLMs' consistency and uncertainty, particularly in critical applications such as healthcare, which demand a high level of trust and reliability. This paper proposes a novel approach to evaluate uncertainty in VLMs' responses using a convex hull approach on a healthcare application for Visual Question Answering (VQA). LLM-CXR model is selected as the medical VLM utilized to generate respon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00056","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/2412.00056/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":"2412.00056","created_at":"2026-07-05T09:42:35.434956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00056v1","created_at":"2026-07-05T09:42:35.434956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00056","created_at":"2026-07-05T09:42:35.434956+00:00"},{"alias_kind":"pith_short_12","alias_value":"42LMUBKFSVZA","created_at":"2026-07-05T09:42:35.434956+00:00"},{"alias_kind":"pith_short_16","alias_value":"42LMUBKFSVZAS4TD","created_at":"2026-07-05T09:42:35.434956+00:00"},{"alias_kind":"pith_short_8","alias_value":"42LMUBKF","created_at":"2026-07-05T09:42:35.434956+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24492","citing_title":"Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42LMUBKFSVZAS4TDEFJDV57MHB","json":"https://pith.science/pith/42LMUBKFSVZAS4TDEFJDV57MHB.json","graph_json":"https://pith.science/api/pith-number/42LMUBKFSVZAS4TDEFJDV57MHB/graph.json","events_json":"https://pith.science/api/pith-number/42LMUBKFSVZAS4TDEFJDV57MHB/events.json","paper":"https://pith.science/paper/42LMUBKF"},"agent_actions":{"view_html":"https://pith.science/pith/42LMUBKFSVZAS4TDEFJDV57MHB","download_json":"https://pith.science/pith/42LMUBKFSVZAS4TDEFJDV57MHB.json","view_paper":"https://pith.science/paper/42LMUBKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00056&json=true","fetch_graph":"https://pith.science/api/pith-number/42LMUBKFSVZAS4TDEFJDV57MHB/graph.json","fetch_events":"https://pith.science/api/pith-number/42LMUBKFSVZAS4TDEFJDV57MHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42LMUBKFSVZAS4TDEFJDV57MHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42LMUBKFSVZAS4TDEFJDV57MHB/action/storage_attestation","attest_author":"https://pith.science/pith/42LMUBKFSVZAS4TDEFJDV57MHB/action/author_attestation","sign_citation":"https://pith.science/pith/42LMUBKFSVZAS4TDEFJDV57MHB/action/citation_signature","submit_replication":"https://pith.science/pith/42LMUBKFSVZAS4TDEFJDV57MHB/action/replication_record"}},"created_at":"2026-07-05T09:42:35.434956+00:00","updated_at":"2026-07-05T09:42:35.434956+00:00"}