{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RBGSLSF3SOYB4JEWJGGGXHBG4K","short_pith_number":"pith:RBGSLSF3","schema_version":"1.0","canonical_sha256":"884d25c8bb93b01e2496498c6b9c26e29ead7f1d98e450b95ca6eb33444d2dd6","source":{"kind":"arxiv","id":"2606.19950","version":1},"attestation_state":"computed","paper":{"title":"Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingdi Chen, Ming Kong, Qiang Long, Qiang Zhu, Tian Liang, Yucheng Wang, Yuetian Du","submitted_at":"2026-06-18T08:49:11Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) show great potential in medical tasks, but their elicited confidence often misaligns with actual accuracy, potentially leading to misdiagnosis or overlooking correct advice. This study presents the first comprehensive analysis of the relationship between accuracy and confidence in medical MLLMs. It proposes a novel method that combines Multi-Strategy Fusion-Based Interrogation (MS-FBI) with auxiliary expert LLM assessment, aiming to improve confidence calibration in Medical Visual Question Answering (VQA). Experiments demonstrate that our method reduces"},"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":"2606.19950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T08:49:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ee340a25b5240642266717da3c78acf36ab17fce9678f7465efdca4566a120a3","abstract_canon_sha256":"6e504aa54ca0a658ac977520efc3b8a5c20176394c91234781bf9ae9d07c0b50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:59.005461Z","signature_b64":"ePmqHwlyXuD6fMPlJopdxUjFJ/rO2KC76Kx8/5ctXW3h1QukJ+3AJBRXsp2Qt6ExxAL4D2lySnNceozqei2wCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"884d25c8bb93b01e2496498c6b9c26e29ead7f1d98e450b95ca6eb33444d2dd6","last_reissued_at":"2026-06-19T16:12:59.005032Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:59.005032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bingdi Chen, Ming Kong, Qiang Long, Qiang Zhu, Tian Liang, Yucheng Wang, Yuetian Du","submitted_at":"2026-06-18T08:49:11Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) show great potential in medical tasks, but their elicited confidence often misaligns with actual accuracy, potentially leading to misdiagnosis or overlooking correct advice. This study presents the first comprehensive analysis of the relationship between accuracy and confidence in medical MLLMs. It proposes a novel method that combines Multi-Strategy Fusion-Based Interrogation (MS-FBI) with auxiliary expert LLM assessment, aiming to improve confidence calibration in Medical Visual Question Answering (VQA). Experiments demonstrate that our method reduces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19950","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/2606.19950/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":"2606.19950","created_at":"2026-06-19T16:12:59.005101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19950v1","created_at":"2026-06-19T16:12:59.005101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19950","created_at":"2026-06-19T16:12:59.005101+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBGSLSF3SOYB","created_at":"2026-06-19T16:12:59.005101+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBGSLSF3SOYB4JEW","created_at":"2026-06-19T16:12:59.005101+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBGSLSF3","created_at":"2026-06-19T16:12:59.005101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBGSLSF3SOYB4JEWJGGGXHBG4K","json":"https://pith.science/pith/RBGSLSF3SOYB4JEWJGGGXHBG4K.json","graph_json":"https://pith.science/api/pith-number/RBGSLSF3SOYB4JEWJGGGXHBG4K/graph.json","events_json":"https://pith.science/api/pith-number/RBGSLSF3SOYB4JEWJGGGXHBG4K/events.json","paper":"https://pith.science/paper/RBGSLSF3"},"agent_actions":{"view_html":"https://pith.science/pith/RBGSLSF3SOYB4JEWJGGGXHBG4K","download_json":"https://pith.science/pith/RBGSLSF3SOYB4JEWJGGGXHBG4K.json","view_paper":"https://pith.science/paper/RBGSLSF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19950&json=true","fetch_graph":"https://pith.science/api/pith-number/RBGSLSF3SOYB4JEWJGGGXHBG4K/graph.json","fetch_events":"https://pith.science/api/pith-number/RBGSLSF3SOYB4JEWJGGGXHBG4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBGSLSF3SOYB4JEWJGGGXHBG4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBGSLSF3SOYB4JEWJGGGXHBG4K/action/storage_attestation","attest_author":"https://pith.science/pith/RBGSLSF3SOYB4JEWJGGGXHBG4K/action/author_attestation","sign_citation":"https://pith.science/pith/RBGSLSF3SOYB4JEWJGGGXHBG4K/action/citation_signature","submit_replication":"https://pith.science/pith/RBGSLSF3SOYB4JEWJGGGXHBG4K/action/replication_record"}},"created_at":"2026-06-19T16:12:59.005101+00:00","updated_at":"2026-06-19T16:12:59.005101+00:00"}