{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KAM75S3R3ZXF6DFO6KYSR2H2LL","short_pith_number":"pith:KAM75S3R","schema_version":"1.0","canonical_sha256":"5019fecb71de6e5f0caef2b128e8fa5ae0d92b3f5c720a6f693f72e12ebe9692","source":{"kind":"arxiv","id":"2502.19634","version":2},"attestation_state":"computed","paper":{"title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Che Liu, Chen Chen, Cheng Ouyang, Daniel Rueckert, Fenglin Liu, Hongwei Bran Li, Jiayuan Zhu, Jiazhen Pan, Junde Wu","submitted_at":"2025-02-26T23:57:34Z","abstract_excerpt":"Reasoning is a critical frontier for advancing medical image analysis, where transparency and trustworthiness play a central role in both clinician trust and regulatory approval. Although Medical Visual Language Models (VLMs) show promise for radiological tasks, most existing VLMs merely produce final answers without revealing the underlying reasoning. To address this gap, we introduce MedVLM-R1, a medical VLM that explicitly generates natural language reasoning to enhance transparency and trustworthiness. Instead of relying on supervised fine-tuning (SFT), which often suffers from overfitting"},"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":"2502.19634","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-26T23:57:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7638f9bb6b70d24ef474fb2030cbb0a5a71b38cfd5325bdf6d9879804110efe2","abstract_canon_sha256":"359f09599b10e2389496860723b7017f16f4ba355ebfc8279a4d6b7b3105aad9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:42.771215Z","signature_b64":"TqzhA4hQc+srrC9f8Qgg5a8NatUb6/hvIkiw+6StBjETFE7iiZh0by/sIgwCqXPBkurSWLV2rx3/3ot0aSbRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5019fecb71de6e5f0caef2b128e8fa5ae0d92b3f5c720a6f693f72e12ebe9692","last_reissued_at":"2026-07-05T10:34:42.770459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:42.770459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Che Liu, Chen Chen, Cheng Ouyang, Daniel Rueckert, Fenglin Liu, Hongwei Bran Li, Jiayuan Zhu, Jiazhen Pan, Junde Wu","submitted_at":"2025-02-26T23:57:34Z","abstract_excerpt":"Reasoning is a critical frontier for advancing medical image analysis, where transparency and trustworthiness play a central role in both clinician trust and regulatory approval. Although Medical Visual Language Models (VLMs) show promise for radiological tasks, most existing VLMs merely produce final answers without revealing the underlying reasoning. To address this gap, we introduce MedVLM-R1, a medical VLM that explicitly generates natural language reasoning to enhance transparency and trustworthiness. Instead of relying on supervised fine-tuning (SFT), which often suffers from overfitting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19634","kind":"arxiv","version":2},"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/2502.19634/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":"2502.19634","created_at":"2026-07-05T10:34:42.770572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19634v2","created_at":"2026-07-05T10:34:42.770572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19634","created_at":"2026-07-05T10:34:42.770572+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAM75S3R3ZXF","created_at":"2026-07-05T10:34:42.770572+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAM75S3R3ZXF6DFO","created_at":"2026-07-05T10:34:42.770572+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAM75S3R","created_at":"2026-07-05T10:34:42.770572+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19950","citing_title":"Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05744","citing_title":"PlanBench-V: A Spatial Planning Map Benchmark for Vision-Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03693","citing_title":"Does Language Shift Break Medical Vision-Language Models? Indonesian Radiology Visual Question Answering Case Study","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28164","citing_title":"EchoSonar-R: A Multi-View Reasoning-Enabled Model for Disease Classification and Report Generation in Echocardiography","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07542","citing_title":"DIYHealth Suite: Dataset, Model, and Benchmark for Health Management at Home","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21652","citing_title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28388","citing_title":"Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2502.07143","citing_title":"Ask Patients with Patience: Enabling LLMs for Human-Centric Medical Dialogue with Grounded Reasoning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14062","citing_title":"FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21652","citing_title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15951","citing_title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19630","citing_title":"Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning","ref_index":25,"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":11,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06856","citing_title":"Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16796","citing_title":"RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04225","citing_title":"Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2512.22278","citing_title":"FETAL-GAUGE: A Benchmark for Assessing Vision-Language Models in Fetal Ultrasound","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14044","citing_title":"Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":154,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":258,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10761","citing_title":"RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21138","citing_title":"Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13756","citing_title":"MedRCube: A Multidimensional Framework for Fine-Grained and In-Depth Evaluation of MLLMs in Medical Imaging","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAM75S3R3ZXF6DFO6KYSR2H2LL","json":"https://pith.science/pith/KAM75S3R3ZXF6DFO6KYSR2H2LL.json","graph_json":"https://pith.science/api/pith-number/KAM75S3R3ZXF6DFO6KYSR2H2LL/graph.json","events_json":"https://pith.science/api/pith-number/KAM75S3R3ZXF6DFO6KYSR2H2LL/events.json","paper":"https://pith.science/paper/KAM75S3R"},"agent_actions":{"view_html":"https://pith.science/pith/KAM75S3R3ZXF6DFO6KYSR2H2LL","download_json":"https://pith.science/pith/KAM75S3R3ZXF6DFO6KYSR2H2LL.json","view_paper":"https://pith.science/paper/KAM75S3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19634&json=true","fetch_graph":"https://pith.science/api/pith-number/KAM75S3R3ZXF6DFO6KYSR2H2LL/graph.json","fetch_events":"https://pith.science/api/pith-number/KAM75S3R3ZXF6DFO6KYSR2H2LL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAM75S3R3ZXF6DFO6KYSR2H2LL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAM75S3R3ZXF6DFO6KYSR2H2LL/action/storage_attestation","attest_author":"https://pith.science/pith/KAM75S3R3ZXF6DFO6KYSR2H2LL/action/author_attestation","sign_citation":"https://pith.science/pith/KAM75S3R3ZXF6DFO6KYSR2H2LL/action/citation_signature","submit_replication":"https://pith.science/pith/KAM75S3R3ZXF6DFO6KYSR2H2LL/action/replication_record"}},"created_at":"2026-07-05T10:34:42.770572+00:00","updated_at":"2026-07-05T10:34:42.770572+00:00"}