{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2ZYEN7YMHXTAKQFLI64NA2VCGY","short_pith_number":"pith:2ZYEN7YM","schema_version":"1.0","canonical_sha256":"d67046ff0c3de60540ab47b8d06aa236130dfe37936f79926c2de248d55f3cce","source":{"kind":"arxiv","id":"2407.15268","version":2},"attestation_state":"computed","paper":{"title":"Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyan Xiong, James Zhao, Liwen Sun, Megan Han","submitted_at":"2024-07-21T21:04:28Z","abstract_excerpt":"Multimodal foundation models hold significant potential for automating radiology report generation, thereby assisting clinicians in diagnosing cardiac diseases. However, generated reports often suffer from serious factual inaccuracy. In this paper, we introduce a fact-aware multimodal retrieval-augmented pipeline in generating accurate radiology reports (FactMM-RAG). We first leverage RadGraph to mine factual report pairs, then integrate factual knowledge to train a universal multimodal retriever. Given a radiology image, our retriever can identify high-quality reference reports to augment mul"},"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":"2407.15268","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-21T21:04:28Z","cross_cats_sorted":[],"title_canon_sha256":"3788af1be305fa0d3aec4966859c68d10130698fb344cb888e051c2fca676110","abstract_canon_sha256":"7a7d5f24a402378be327ae720c391d8569b2dcc3a7cca565f1957475d8802b89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:08.335456Z","signature_b64":"CXyDBi9pMYzJmdAdiqV5y5bzIyBDvJSKDk9HXF7tOk5BjIjkost2VYEeIO7SNIbqOqzhK3ugpXia7HoA93uxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d67046ff0c3de60540ab47b8d06aa236130dfe37936f79926c2de248d55f3cce","last_reissued_at":"2026-07-05T10:10:08.334909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:08.334909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyan Xiong, James Zhao, Liwen Sun, Megan Han","submitted_at":"2024-07-21T21:04:28Z","abstract_excerpt":"Multimodal foundation models hold significant potential for automating radiology report generation, thereby assisting clinicians in diagnosing cardiac diseases. However, generated reports often suffer from serious factual inaccuracy. In this paper, we introduce a fact-aware multimodal retrieval-augmented pipeline in generating accurate radiology reports (FactMM-RAG). We first leverage RadGraph to mine factual report pairs, then integrate factual knowledge to train a universal multimodal retriever. Given a radiology image, our retriever can identify high-quality reference reports to augment mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15268","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/2407.15268/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":"2407.15268","created_at":"2026-07-05T10:10:08.334966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15268v2","created_at":"2026-07-05T10:10:08.334966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15268","created_at":"2026-07-05T10:10:08.334966+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZYEN7YMHXTA","created_at":"2026-07-05T10:10:08.334966+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZYEN7YMHXTAKQFL","created_at":"2026-07-05T10:10:08.334966+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZYEN7YM","created_at":"2026-07-05T10:10:08.334966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01440","citing_title":"FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2504.07415","citing_title":"RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZYEN7YMHXTAKQFLI64NA2VCGY","json":"https://pith.science/pith/2ZYEN7YMHXTAKQFLI64NA2VCGY.json","graph_json":"https://pith.science/api/pith-number/2ZYEN7YMHXTAKQFLI64NA2VCGY/graph.json","events_json":"https://pith.science/api/pith-number/2ZYEN7YMHXTAKQFLI64NA2VCGY/events.json","paper":"https://pith.science/paper/2ZYEN7YM"},"agent_actions":{"view_html":"https://pith.science/pith/2ZYEN7YMHXTAKQFLI64NA2VCGY","download_json":"https://pith.science/pith/2ZYEN7YMHXTAKQFLI64NA2VCGY.json","view_paper":"https://pith.science/paper/2ZYEN7YM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15268&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZYEN7YMHXTAKQFLI64NA2VCGY/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZYEN7YMHXTAKQFLI64NA2VCGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZYEN7YMHXTAKQFLI64NA2VCGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZYEN7YMHXTAKQFLI64NA2VCGY/action/storage_attestation","attest_author":"https://pith.science/pith/2ZYEN7YMHXTAKQFLI64NA2VCGY/action/author_attestation","sign_citation":"https://pith.science/pith/2ZYEN7YMHXTAKQFLI64NA2VCGY/action/citation_signature","submit_replication":"https://pith.science/pith/2ZYEN7YMHXTAKQFLI64NA2VCGY/action/replication_record"}},"created_at":"2026-07-05T10:10:08.334966+00:00","updated_at":"2026-07-05T10:10:08.334966+00:00"}