{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QBOA65PVR6BHGPU6GVACI6YRJ6","short_pith_number":"pith:QBOA65PV","schema_version":"1.0","canonical_sha256":"805c0f75f58f82733e9e3540247b114fbe1ddf1390365ec68c62175626f4d187","source":{"kind":"arxiv","id":"2403.06728","version":2},"attestation_state":"computed","paper":{"title":"Multimodal Large Language Model driven Radiology Report Generation with Clinical Knowledge Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Meng Wei, Miaojing Shi, Oluwatosin Alabi, Tianyu Cen, Tom Vercauteren, Zijie Yue","submitted_at":"2024-03-11T13:47:11Z","abstract_excerpt":"Radiology report generation (RRG) has attracted significant attention due to its potential to reduce the workload of radiologists. The performance of current RRG approaches remains unsatisfactory against clinical standards. This paper introduces a novel RRG method, MLLM-RRG, that integrates multimodal large language models (MLLMs) with various types of clinical knowledge to generate accurate and comprehensive chest X-ray reports. Our method first designs a referring anatomical feature extractor that leverages anatomical knowledge to analyze different regions of the chest X-ray image and extrac"},"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":"2403.06728","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T13:47:11Z","cross_cats_sorted":[],"title_canon_sha256":"3cb17eca4e91e36f8f04be09572d22392a70bb193c2f54fac0c5825483a55882","abstract_canon_sha256":"5510921dc08f281bd0052f7844e8f8906cc2fb778b26ff2d22428127e975272a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:06.680313Z","signature_b64":"4LzBGaxOutW4IU2v23SXBK5TdZii3OdeVgg9z7/P2pLZUFVqrCr0gwqPEQ1UUn/SY4QTFi9NIFPXgCKziJqqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"805c0f75f58f82733e9e3540247b114fbe1ddf1390365ec68c62175626f4d187","last_reissued_at":"2026-06-30T00:15:06.679803Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:06.679803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Large Language Model driven Radiology Report Generation with Clinical Knowledge Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Meng Wei, Miaojing Shi, Oluwatosin Alabi, Tianyu Cen, Tom Vercauteren, Zijie Yue","submitted_at":"2024-03-11T13:47:11Z","abstract_excerpt":"Radiology report generation (RRG) has attracted significant attention due to its potential to reduce the workload of radiologists. The performance of current RRG approaches remains unsatisfactory against clinical standards. This paper introduces a novel RRG method, MLLM-RRG, that integrates multimodal large language models (MLLMs) with various types of clinical knowledge to generate accurate and comprehensive chest X-ray reports. Our method first designs a referring anatomical feature extractor that leverages anatomical knowledge to analyze different regions of the chest X-ray image and extrac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06728","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/2403.06728/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":"2403.06728","created_at":"2026-06-30T00:15:06.679868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06728v2","created_at":"2026-06-30T00:15:06.679868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06728","created_at":"2026-06-30T00:15:06.679868+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBOA65PVR6BH","created_at":"2026-06-30T00:15:06.679868+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBOA65PVR6BHGPU6","created_at":"2026-06-30T00:15:06.679868+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBOA65PV","created_at":"2026-06-30T00:15:06.679868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.25546","citing_title":"Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2408.16213","citing_title":"M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2603.16876","citing_title":"Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation","ref_index":148,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09584","citing_title":"CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13598","citing_title":"Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBOA65PVR6BHGPU6GVACI6YRJ6","json":"https://pith.science/pith/QBOA65PVR6BHGPU6GVACI6YRJ6.json","graph_json":"https://pith.science/api/pith-number/QBOA65PVR6BHGPU6GVACI6YRJ6/graph.json","events_json":"https://pith.science/api/pith-number/QBOA65PVR6BHGPU6GVACI6YRJ6/events.json","paper":"https://pith.science/paper/QBOA65PV"},"agent_actions":{"view_html":"https://pith.science/pith/QBOA65PVR6BHGPU6GVACI6YRJ6","download_json":"https://pith.science/pith/QBOA65PVR6BHGPU6GVACI6YRJ6.json","view_paper":"https://pith.science/paper/QBOA65PV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06728&json=true","fetch_graph":"https://pith.science/api/pith-number/QBOA65PVR6BHGPU6GVACI6YRJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/QBOA65PVR6BHGPU6GVACI6YRJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBOA65PVR6BHGPU6GVACI6YRJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBOA65PVR6BHGPU6GVACI6YRJ6/action/storage_attestation","attest_author":"https://pith.science/pith/QBOA65PVR6BHGPU6GVACI6YRJ6/action/author_attestation","sign_citation":"https://pith.science/pith/QBOA65PVR6BHGPU6GVACI6YRJ6/action/citation_signature","submit_replication":"https://pith.science/pith/QBOA65PVR6BHGPU6GVACI6YRJ6/action/replication_record"}},"created_at":"2026-06-30T00:15:06.679868+00:00","updated_at":"2026-06-30T00:15:06.679868+00:00"}