{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FFO3UGVTH45XBWAQEEQFKMXK52","short_pith_number":"pith:FFO3UGVT","schema_version":"1.0","canonical_sha256":"295dba1ab33f3b70d81021205532eaeeb78f7460ed2e16f952455ab91b5d0835","source":{"kind":"arxiv","id":"2406.19280","version":4},"attestation_state":"computed","paper":{"title":"HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anningzhe Gao, Benyou Wang, Chi Gui, Guangjun Yu, Guiming Hardy Chen, Junying Chen, Ke Ji, Ruifei Zhang, Ruyi Ouyang, Shunian Chen, Xiang Wan, Xidong Wang, Zhenyang Cai","submitted_at":"2024-06-27T15:50:41Z","abstract_excerpt":"The rapid development of multimodal large language models (MLLMs), such as GPT-4V, has led to significant advancements. However, these models still face challenges in medical multimodal capabilities due to limitations in the quantity and quality of medical vision-text data, stemming from data privacy concerns and high annotation costs. While pioneering approaches utilize PubMed's large-scale, de-identified medical image-text pairs to address these limitations, they still fall short due to inherent data noise. To tackle this, we refined medical image-text pairs from PubMed and employed MLLMs (G"},"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":"2406.19280","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-27T15:50:41Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"81083a38e648bfe434003d4fe7a849de3e152b6016dde37040f8ddf2ccaaba0c","abstract_canon_sha256":"89f51ba95642da89d3591652eca00d8797a269d81dad84eb0ea9d12838b403ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:04.659405Z","signature_b64":"Egnp6FbeKL6anXkXfp6krL4vp84EtMW8U2UYCB/YDX2X77NWkjaCuEw2PwNpm89hEvTP3HJ7berYHcIiD+DVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"295dba1ab33f3b70d81021205532eaeeb78f7460ed2e16f952455ab91b5d0835","last_reissued_at":"2026-07-05T09:13:04.658886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:04.658886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anningzhe Gao, Benyou Wang, Chi Gui, Guangjun Yu, Guiming Hardy Chen, Junying Chen, Ke Ji, Ruifei Zhang, Ruyi Ouyang, Shunian Chen, Xiang Wan, Xidong Wang, Zhenyang Cai","submitted_at":"2024-06-27T15:50:41Z","abstract_excerpt":"The rapid development of multimodal large language models (MLLMs), such as GPT-4V, has led to significant advancements. However, these models still face challenges in medical multimodal capabilities due to limitations in the quantity and quality of medical vision-text data, stemming from data privacy concerns and high annotation costs. While pioneering approaches utilize PubMed's large-scale, de-identified medical image-text pairs to address these limitations, they still fall short due to inherent data noise. To tackle this, we refined medical image-text pairs from PubMed and employed MLLMs (G"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19280","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/2406.19280/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":"2406.19280","created_at":"2026-07-05T09:13:04.658945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19280v4","created_at":"2026-07-05T09:13:04.658945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19280","created_at":"2026-07-05T09:13:04.658945+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFO3UGVTH45X","created_at":"2026-07-05T09:13:04.658945+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFO3UGVTH45XBWAQ","created_at":"2026-07-05T09:13:04.658945+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFO3UGVT","created_at":"2026-07-05T09:13:04.658945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05310","citing_title":"Evaluating and Understanding Model Editing for Medical Vision Language Models","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25375","citing_title":"Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01908","citing_title":"Towards Real-World Ultrasound Understanding: Large Vision-Language Models from Multi-Image Examinations with Long-Form Reports","ref_index":5,"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":77,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25375","citing_title":"Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01049","citing_title":"Beyond Captions: Context-Grounded Reconstruction for Biomedical Multimodal Continued Pretraining","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27500","citing_title":"Aloe-Vision: Robust Vision-Language Models for Healthcare","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31599","citing_title":"Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07542","citing_title":"DIYHealth Suite: Dataset, Model, and Benchmark for Health Management at Home","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28422","citing_title":"VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00602","citing_title":"ASAP: Advancing Medical Volumetric Representation Learning with Anatomy-aware Semantically-adaptive Pre-training","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20277","citing_title":"Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15561","citing_title":"RoiMAM: Region-of-Interest Medical Attention Model for Efficient Vision-Language Understanding","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05831","citing_title":"HeartcareGPT: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11989","citing_title":"Thought Graph Traversal for Test-time Scaling in Chest X-ray VLLMs","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03054","citing_title":"IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21950","citing_title":"MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14403","citing_title":"DermAgent: A Self-Reflective Agentic System for Dermatological Image Analysis with Multi-Tool Reasoning and Traceable Decision-Making","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24649","citing_title":"MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09679","citing_title":"DeepTumorVQA: A Hierarchical 3D CT Benchmark for Stage-Wise Evaluation of Medical VLMs and Tool-Augmented Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10286","citing_title":"AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10286","citing_title":"AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06537","citing_title":"MedHorizon: Towards Long-context Medical Video Understanding in the Wild","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07128","citing_title":"A Utility-preserving De-identification Pipeline for Cross-hospital Radiology Data Sharing","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFO3UGVTH45XBWAQEEQFKMXK52","json":"https://pith.science/pith/FFO3UGVTH45XBWAQEEQFKMXK52.json","graph_json":"https://pith.science/api/pith-number/FFO3UGVTH45XBWAQEEQFKMXK52/graph.json","events_json":"https://pith.science/api/pith-number/FFO3UGVTH45XBWAQEEQFKMXK52/events.json","paper":"https://pith.science/paper/FFO3UGVT"},"agent_actions":{"view_html":"https://pith.science/pith/FFO3UGVTH45XBWAQEEQFKMXK52","download_json":"https://pith.science/pith/FFO3UGVTH45XBWAQEEQFKMXK52.json","view_paper":"https://pith.science/paper/FFO3UGVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19280&json=true","fetch_graph":"https://pith.science/api/pith-number/FFO3UGVTH45XBWAQEEQFKMXK52/graph.json","fetch_events":"https://pith.science/api/pith-number/FFO3UGVTH45XBWAQEEQFKMXK52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFO3UGVTH45XBWAQEEQFKMXK52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFO3UGVTH45XBWAQEEQFKMXK52/action/storage_attestation","attest_author":"https://pith.science/pith/FFO3UGVTH45XBWAQEEQFKMXK52/action/author_attestation","sign_citation":"https://pith.science/pith/FFO3UGVTH45XBWAQEEQFKMXK52/action/citation_signature","submit_replication":"https://pith.science/pith/FFO3UGVTH45XBWAQEEQFKMXK52/action/replication_record"}},"created_at":"2026-07-05T09:13:04.658945+00:00","updated_at":"2026-07-05T09:13:04.658945+00:00"}