{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZVNQROORH57VEKPKPF5QVP2T2C","short_pith_number":"pith:ZVNQROOR","schema_version":"1.0","canonical_sha256":"cd5b08b9d13f7f5229ea797b0abf53d08cdbb9fa4b0b5033c73a7d6645ddb8cc","source":{"kind":"arxiv","id":"2412.06141","version":4},"attestation_state":"computed","paper":{"title":"MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hongtu Zhu, Huaxiu Yao, Kangyu Zhu, Peng Xia, Sheng Wang, Yun Li","submitted_at":"2024-12-09T01:50:39Z","abstract_excerpt":"The advancement of Large Vision-Language Models (LVLMs) has propelled their application in the medical field. However, Medical LVLMs (Med-LVLMs) encounter factuality challenges due to modality misalignment, where the models prioritize textual knowledge over visual input, leading to hallucinations that contradict information in medical images. Previous attempts to enhance modality alignment in Med-LVLMs through preference optimization have inadequately mitigated clinical relevance in preference data, making these samples easily distinguishable and reducing alignment effectiveness. To address th"},"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":"2412.06141","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T01:50:39Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7a3523155d07825cae9350d7f4054ace76beb1e058a9f858bafadaed47b9001c","abstract_canon_sha256":"515e7f9b7cceaad6900f2cb168738f2ed1014f8a968bc1dd2aef65bc31dc0e19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:41.067480Z","signature_b64":"Lk3PTNn6S8qNwUF7uR07bcrXuElG9FsD1eN/HEdH3JEcC8SHTCyTbltKU9qSk4v8jOYIH0rKKzV3sRBBgmlGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd5b08b9d13f7f5229ea797b0abf53d08cdbb9fa4b0b5033c73a7d6645ddb8cc","last_reissued_at":"2026-07-05T11:15:41.066952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:41.066952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hongtu Zhu, Huaxiu Yao, Kangyu Zhu, Peng Xia, Sheng Wang, Yun Li","submitted_at":"2024-12-09T01:50:39Z","abstract_excerpt":"The advancement of Large Vision-Language Models (LVLMs) has propelled their application in the medical field. However, Medical LVLMs (Med-LVLMs) encounter factuality challenges due to modality misalignment, where the models prioritize textual knowledge over visual input, leading to hallucinations that contradict information in medical images. Previous attempts to enhance modality alignment in Med-LVLMs through preference optimization have inadequately mitigated clinical relevance in preference data, making these samples easily distinguishable and reducing alignment effectiveness. To address th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06141","kind":"arxiv","version":4},"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/2412.06141/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":"2412.06141","created_at":"2026-07-05T11:15:41.067023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06141v4","created_at":"2026-07-05T11:15:41.067023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06141","created_at":"2026-07-05T11:15:41.067023+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVNQROORH57V","created_at":"2026-07-05T11:15:41.067023+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVNQROORH57VEKPK","created_at":"2026-07-05T11:15:41.067023+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVNQROOR","created_at":"2026-07-05T11:15:41.067023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26283","citing_title":"MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12590","citing_title":"Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11740","citing_title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","ref_index":224,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06379","citing_title":"EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26283","citing_title":"MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26283","citing_title":"MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26283","citing_title":"MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZVNQROORH57VEKPKPF5QVP2T2C","json":"https://pith.science/pith/ZVNQROORH57VEKPKPF5QVP2T2C.json","graph_json":"https://pith.science/api/pith-number/ZVNQROORH57VEKPKPF5QVP2T2C/graph.json","events_json":"https://pith.science/api/pith-number/ZVNQROORH57VEKPKPF5QVP2T2C/events.json","paper":"https://pith.science/paper/ZVNQROOR"},"agent_actions":{"view_html":"https://pith.science/pith/ZVNQROORH57VEKPKPF5QVP2T2C","download_json":"https://pith.science/pith/ZVNQROORH57VEKPKPF5QVP2T2C.json","view_paper":"https://pith.science/paper/ZVNQROOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06141&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVNQROORH57VEKPKPF5QVP2T2C/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVNQROORH57VEKPKPF5QVP2T2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVNQROORH57VEKPKPF5QVP2T2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVNQROORH57VEKPKPF5QVP2T2C/action/storage_attestation","attest_author":"https://pith.science/pith/ZVNQROORH57VEKPKPF5QVP2T2C/action/author_attestation","sign_citation":"https://pith.science/pith/ZVNQROORH57VEKPKPF5QVP2T2C/action/citation_signature","submit_replication":"https://pith.science/pith/ZVNQROORH57VEKPKPF5QVP2T2C/action/replication_record"}},"created_at":"2026-07-05T11:15:41.067023+00:00","updated_at":"2026-07-05T11:15:41.067023+00:00"}