{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3AFUIEM2T3GRDSTM2OQFGD4XKU","short_pith_number":"pith:3AFUIEM2","schema_version":"1.0","canonical_sha256":"d80b44119a9ecd11ca6cd3a0530f9755167421d7f5a0c6c15bd85da5b78f8a9a","source":{"kind":"arxiv","id":"2306.11345","version":1},"attestation_state":"computed","paper":{"title":"KiUT: Knowledge-injected U-Transformer for Radiology Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Shaoting Zhang, Xiaofan Zhang, Zhongzhen Huang","submitted_at":"2023-06-20T07:27:28Z","abstract_excerpt":"Radiology report generation aims to automatically generate a clinically accurate and coherent paragraph from the X-ray image, which could relieve radiologists from the heavy burden of report writing. Although various image caption methods have shown remarkable performance in the natural image field, generating accurate reports for medical images requires knowledge of multiple modalities, including vision, language, and medical terminology. We propose a Knowledge-injected U-Transformer (KiUT) to learn multi-level visual representation and adaptively distill the information with contextual and c"},"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":"2306.11345","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-20T07:27:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4ba3f41f0fc4e4cd1c6890bc39f60ae05ed89e22c75754886263fb7284f926d7","abstract_canon_sha256":"3630edb4bd84e17f64bdcdc14f264d05f8a8c215b53f68446c8b5639a7eb7f66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:22:18.702632Z","signature_b64":"ooprNeiMYN4vK9Ti6YtZo9sxqNxZO1Aa1AALMpemzTEQN6zq67z//iBiLZiFYSUNb6yCK2/Jvj3oOplAkNk1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d80b44119a9ecd11ca6cd3a0530f9755167421d7f5a0c6c15bd85da5b78f8a9a","last_reissued_at":"2026-07-05T06:22:18.702218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:22:18.702218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KiUT: Knowledge-injected U-Transformer for Radiology Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Shaoting Zhang, Xiaofan Zhang, Zhongzhen Huang","submitted_at":"2023-06-20T07:27:28Z","abstract_excerpt":"Radiology report generation aims to automatically generate a clinically accurate and coherent paragraph from the X-ray image, which could relieve radiologists from the heavy burden of report writing. Although various image caption methods have shown remarkable performance in the natural image field, generating accurate reports for medical images requires knowledge of multiple modalities, including vision, language, and medical terminology. We propose a Knowledge-injected U-Transformer (KiUT) to learn multi-level visual representation and adaptively distill the information with contextual and c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11345","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/2306.11345/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":"2306.11345","created_at":"2026-07-05T06:22:18.702277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11345v1","created_at":"2026-07-05T06:22:18.702277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11345","created_at":"2026-07-05T06:22:18.702277+00:00"},{"alias_kind":"pith_short_12","alias_value":"3AFUIEM2T3GR","created_at":"2026-07-05T06:22:18.702277+00:00"},{"alias_kind":"pith_short_16","alias_value":"3AFUIEM2T3GRDSTM","created_at":"2026-07-05T06:22:18.702277+00:00"},{"alias_kind":"pith_short_8","alias_value":"3AFUIEM2","created_at":"2026-07-05T06:22:18.702277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02502","citing_title":"An Explainable Vision-Language Model Framework with Adaptive PID-Tversky Loss for Lumbar Spinal Stenosis Diagnosis","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3AFUIEM2T3GRDSTM2OQFGD4XKU","json":"https://pith.science/pith/3AFUIEM2T3GRDSTM2OQFGD4XKU.json","graph_json":"https://pith.science/api/pith-number/3AFUIEM2T3GRDSTM2OQFGD4XKU/graph.json","events_json":"https://pith.science/api/pith-number/3AFUIEM2T3GRDSTM2OQFGD4XKU/events.json","paper":"https://pith.science/paper/3AFUIEM2"},"agent_actions":{"view_html":"https://pith.science/pith/3AFUIEM2T3GRDSTM2OQFGD4XKU","download_json":"https://pith.science/pith/3AFUIEM2T3GRDSTM2OQFGD4XKU.json","view_paper":"https://pith.science/paper/3AFUIEM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11345&json=true","fetch_graph":"https://pith.science/api/pith-number/3AFUIEM2T3GRDSTM2OQFGD4XKU/graph.json","fetch_events":"https://pith.science/api/pith-number/3AFUIEM2T3GRDSTM2OQFGD4XKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3AFUIEM2T3GRDSTM2OQFGD4XKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3AFUIEM2T3GRDSTM2OQFGD4XKU/action/storage_attestation","attest_author":"https://pith.science/pith/3AFUIEM2T3GRDSTM2OQFGD4XKU/action/author_attestation","sign_citation":"https://pith.science/pith/3AFUIEM2T3GRDSTM2OQFGD4XKU/action/citation_signature","submit_replication":"https://pith.science/pith/3AFUIEM2T3GRDSTM2OQFGD4XKU/action/replication_record"}},"created_at":"2026-07-05T06:22:18.702277+00:00","updated_at":"2026-07-05T06:22:18.702277+00:00"}