{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TI7Y5L2HZMOH5U3UCSGIJ3QCIO","short_pith_number":"pith:TI7Y5L2H","schema_version":"1.0","canonical_sha256":"9a3f8eaf47cb1c7ed374148c84ee0243aef5f3a91154e251d146404cbbae4b32","source":{"kind":"arxiv","id":"2507.07568","version":1},"attestation_state":"computed","paper":{"title":"Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"stat.ME","authors_text":"Chang Yao, Guoyan Liang, Jingyuan Chen, Qin Zhou, Sai Wu, Wang Zhe, Xindi Li","submitted_at":"2025-07-10T09:13:10Z","abstract_excerpt":"Automated radiology report generation is essential for improving diagnostic efficiency and reducing the workload of medical professionals. However, existing methods face significant challenges, such as disease class imbalance and insufficient cross-modal fusion. To address these issues, we propose the learnable Retrieval Enhanced Visual-Text Alignment and Fusion (REVTAF) framework, which effectively tackles both class imbalance and visual-text fusion in report generation. REVTAF incorporates two core components: (1) a Learnable Retrieval Enhancer (LRE) that utilizes semantic hierarchies from h"},"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":"2507.07568","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-07-10T09:13:10Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"3505e0342770c1d4a0b6298c2093fdb96573f06c9815452ed27244227a7b870b","abstract_canon_sha256":"d513defe6080479a48b4b06607681476d50a5d2efc4b948233f04f157a9d5f83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:01.027375Z","signature_b64":"kyxss3cZY1V3mKGUpU0LVv7N6fiQZdAz5y57ae0CCnZBVBAy8Ks3Ra1x9G+wB1xv6190Tir6eN/rmvP48iyaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a3f8eaf47cb1c7ed374148c84ee0243aef5f3a91154e251d146404cbbae4b32","last_reissued_at":"2026-07-05T11:35:01.026875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:01.026875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"stat.ME","authors_text":"Chang Yao, Guoyan Liang, Jingyuan Chen, Qin Zhou, Sai Wu, Wang Zhe, Xindi Li","submitted_at":"2025-07-10T09:13:10Z","abstract_excerpt":"Automated radiology report generation is essential for improving diagnostic efficiency and reducing the workload of medical professionals. However, existing methods face significant challenges, such as disease class imbalance and insufficient cross-modal fusion. To address these issues, we propose the learnable Retrieval Enhanced Visual-Text Alignment and Fusion (REVTAF) framework, which effectively tackles both class imbalance and visual-text fusion in report generation. REVTAF incorporates two core components: (1) a Learnable Retrieval Enhancer (LRE) that utilizes semantic hierarchies from h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07568","kind":"arxiv","version":1},"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/2507.07568/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":"2507.07568","created_at":"2026-07-05T11:35:01.026944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07568v1","created_at":"2026-07-05T11:35:01.026944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07568","created_at":"2026-07-05T11:35:01.026944+00:00"},{"alias_kind":"pith_short_12","alias_value":"TI7Y5L2HZMOH","created_at":"2026-07-05T11:35:01.026944+00:00"},{"alias_kind":"pith_short_16","alias_value":"TI7Y5L2HZMOH5U3U","created_at":"2026-07-05T11:35:01.026944+00:00"},{"alias_kind":"pith_short_8","alias_value":"TI7Y5L2H","created_at":"2026-07-05T11:35:01.026944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"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":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TI7Y5L2HZMOH5U3UCSGIJ3QCIO","json":"https://pith.science/pith/TI7Y5L2HZMOH5U3UCSGIJ3QCIO.json","graph_json":"https://pith.science/api/pith-number/TI7Y5L2HZMOH5U3UCSGIJ3QCIO/graph.json","events_json":"https://pith.science/api/pith-number/TI7Y5L2HZMOH5U3UCSGIJ3QCIO/events.json","paper":"https://pith.science/paper/TI7Y5L2H"},"agent_actions":{"view_html":"https://pith.science/pith/TI7Y5L2HZMOH5U3UCSGIJ3QCIO","download_json":"https://pith.science/pith/TI7Y5L2HZMOH5U3UCSGIJ3QCIO.json","view_paper":"https://pith.science/paper/TI7Y5L2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07568&json=true","fetch_graph":"https://pith.science/api/pith-number/TI7Y5L2HZMOH5U3UCSGIJ3QCIO/graph.json","fetch_events":"https://pith.science/api/pith-number/TI7Y5L2HZMOH5U3UCSGIJ3QCIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TI7Y5L2HZMOH5U3UCSGIJ3QCIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TI7Y5L2HZMOH5U3UCSGIJ3QCIO/action/storage_attestation","attest_author":"https://pith.science/pith/TI7Y5L2HZMOH5U3UCSGIJ3QCIO/action/author_attestation","sign_citation":"https://pith.science/pith/TI7Y5L2HZMOH5U3UCSGIJ3QCIO/action/citation_signature","submit_replication":"https://pith.science/pith/TI7Y5L2HZMOH5U3UCSGIJ3QCIO/action/replication_record"}},"created_at":"2026-07-05T11:35:01.026944+00:00","updated_at":"2026-07-05T11:35:01.026944+00:00"}