{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DXUNH54B7MQ3O4YAOCH7NO67OY","short_pith_number":"pith:DXUNH54B","schema_version":"1.0","canonical_sha256":"1de8d3f781fb21b77300708ff6bbdf7608a444d03d2058a5fd6bacb630c88251","source":{"kind":"arxiv","id":"2312.08078","version":5},"attestation_state":"computed","paper":{"title":"Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Jingyang Lin, Linlin Shen, Wenting Chen, Xiang Li, Yixuan Yuan","submitted_at":"2023-12-13T11:47:28Z","abstract_excerpt":"To address these issues, we propose a novel Adaptive patch-word Matching (AdaMatch) model to correlate chest X-ray (CXR) image regions with words in medical reports and apply it to CXR-report generation to provide explainability for the generation process. AdaMatch exploits the fine-grained relation between adaptive patches and words to provide explanations of specific image regions with corresponding words. To capture the abnormal regions of varying sizes and positions, we introduce the Adaptive Patch extraction (AdaPatch) module to acquire the adaptive patches for these regions adaptively. I"},"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":"2312.08078","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T11:47:28Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ac8c47a95bda57174355df7585f55a750c937a8abec2534fc520677e65c2df4a","abstract_canon_sha256":"cd69e69c5a6f89aa4103ab1a07be82ee978800924d0129198d13ad3e4eb43961"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:15.738862Z","signature_b64":"V+XN/qlJqWbUyEWA9WT+vkSMF2Ogr/wH6u16iqT5OjDJ8R/hYrRImoZ5YTfWGq2wkZugarLIe8GsG4NMqiy/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1de8d3f781fb21b77300708ff6bbdf7608a444d03d2058a5fd6bacb630c88251","last_reissued_at":"2026-07-05T08:56:15.738413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:15.738413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiebo Luo, Jingyang Lin, Linlin Shen, Wenting Chen, Xiang Li, Yixuan Yuan","submitted_at":"2023-12-13T11:47:28Z","abstract_excerpt":"To address these issues, we propose a novel Adaptive patch-word Matching (AdaMatch) model to correlate chest X-ray (CXR) image regions with words in medical reports and apply it to CXR-report generation to provide explainability for the generation process. AdaMatch exploits the fine-grained relation between adaptive patches and words to provide explanations of specific image regions with corresponding words. To capture the abnormal regions of varying sizes and positions, we introduce the Adaptive Patch extraction (AdaPatch) module to acquire the adaptive patches for these regions adaptively. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08078","kind":"arxiv","version":5},"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/2312.08078/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":"2312.08078","created_at":"2026-07-05T08:56:15.738469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08078v5","created_at":"2026-07-05T08:56:15.738469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08078","created_at":"2026-07-05T08:56:15.738469+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXUNH54B7MQ3","created_at":"2026-07-05T08:56:15.738469+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXUNH54B7MQ3O4YA","created_at":"2026-07-05T08:56:15.738469+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXUNH54B","created_at":"2026-07-05T08:56:15.738469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27559","citing_title":"RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXUNH54B7MQ3O4YAOCH7NO67OY","json":"https://pith.science/pith/DXUNH54B7MQ3O4YAOCH7NO67OY.json","graph_json":"https://pith.science/api/pith-number/DXUNH54B7MQ3O4YAOCH7NO67OY/graph.json","events_json":"https://pith.science/api/pith-number/DXUNH54B7MQ3O4YAOCH7NO67OY/events.json","paper":"https://pith.science/paper/DXUNH54B"},"agent_actions":{"view_html":"https://pith.science/pith/DXUNH54B7MQ3O4YAOCH7NO67OY","download_json":"https://pith.science/pith/DXUNH54B7MQ3O4YAOCH7NO67OY.json","view_paper":"https://pith.science/paper/DXUNH54B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08078&json=true","fetch_graph":"https://pith.science/api/pith-number/DXUNH54B7MQ3O4YAOCH7NO67OY/graph.json","fetch_events":"https://pith.science/api/pith-number/DXUNH54B7MQ3O4YAOCH7NO67OY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXUNH54B7MQ3O4YAOCH7NO67OY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXUNH54B7MQ3O4YAOCH7NO67OY/action/storage_attestation","attest_author":"https://pith.science/pith/DXUNH54B7MQ3O4YAOCH7NO67OY/action/author_attestation","sign_citation":"https://pith.science/pith/DXUNH54B7MQ3O4YAOCH7NO67OY/action/citation_signature","submit_replication":"https://pith.science/pith/DXUNH54B7MQ3O4YAOCH7NO67OY/action/replication_record"}},"created_at":"2026-07-05T08:56:15.738469+00:00","updated_at":"2026-07-05T08:56:15.738469+00:00"}