{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RN4ZWNL3FYGYNUESZIDMDW5AWV","short_pith_number":"pith:RN4ZWNL3","schema_version":"1.0","canonical_sha256":"8b799b357b2e0d86d092ca06c1dba0b55baa647959659a8d4468f469c287ecae","source":{"kind":"arxiv","id":"2505.08838","version":2},"attestation_state":"computed","paper":{"title":"Ultrasound Report Generation with Multimodal Large Language Models for Standardized Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Baoliang Zhao, Chi Hong Wong, Faqin Lv, Liang Yao, Pak Kin Wong, Peixuan Ge, Peng Zhang, Tongkun Su, Ying Hu, Yu Sun, Zenan Wang","submitted_at":"2025-05-13T08:27:01Z","abstract_excerpt":"Ultrasound (US) report generation is a challenging task due to the variability of US images, operator dependence, and the need for standardized text. Unlike X-ray and CT, US imaging lacks consistent datasets, making automation difficult. In this study, we propose a unified framework for multi-organ and multilingual US report generation, integrating fragment-based multilingual training and leveraging the standardized nature of US reports. By aligning modular text fragments with diverse imaging data and curating a bilingual English-Chinese dataset, the method achieves consistent and clinically a"},"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":"2505.08838","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2025-05-13T08:27:01Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"570c01995fc14959976ed56f0d656a72cd36e44712021e244e4fe82d340bf19f","abstract_canon_sha256":"f0c2f9c1250147531f1511b4579012a815fc1962837da098f8974fbb6d552bb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:51.401632Z","signature_b64":"mQMHA9NG3W+uhcLLQYf1r0gn4HFywWBLSbpyfwFpZ02GbRmZD1xJID+hUt9swZFyfSU+FW/k8rGb4UOZwPpQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b799b357b2e0d86d092ca06c1dba0b55baa647959659a8d4468f469c287ecae","last_reissued_at":"2026-07-05T11:04:51.401070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:51.401070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ultrasound Report Generation with Multimodal Large Language Models for Standardized Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Baoliang Zhao, Chi Hong Wong, Faqin Lv, Liang Yao, Pak Kin Wong, Peixuan Ge, Peng Zhang, Tongkun Su, Ying Hu, Yu Sun, Zenan Wang","submitted_at":"2025-05-13T08:27:01Z","abstract_excerpt":"Ultrasound (US) report generation is a challenging task due to the variability of US images, operator dependence, and the need for standardized text. Unlike X-ray and CT, US imaging lacks consistent datasets, making automation difficult. In this study, we propose a unified framework for multi-organ and multilingual US report generation, integrating fragment-based multilingual training and leveraging the standardized nature of US reports. By aligning modular text fragments with diverse imaging data and curating a bilingual English-Chinese dataset, the method achieves consistent and clinically a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08838","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/2505.08838/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":"2505.08838","created_at":"2026-07-05T11:04:51.401132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08838v2","created_at":"2026-07-05T11:04:51.401132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08838","created_at":"2026-07-05T11:04:51.401132+00:00"},{"alias_kind":"pith_short_12","alias_value":"RN4ZWNL3FYGY","created_at":"2026-07-05T11:04:51.401132+00:00"},{"alias_kind":"pith_short_16","alias_value":"RN4ZWNL3FYGYNUES","created_at":"2026-07-05T11:04:51.401132+00:00"},{"alias_kind":"pith_short_8","alias_value":"RN4ZWNL3","created_at":"2026-07-05T11:04:51.401132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19319","citing_title":"MedVQA-TREE: A Multimodal Reasoning and Retrieval Framework for Sarcopenia Prediction","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RN4ZWNL3FYGYNUESZIDMDW5AWV","json":"https://pith.science/pith/RN4ZWNL3FYGYNUESZIDMDW5AWV.json","graph_json":"https://pith.science/api/pith-number/RN4ZWNL3FYGYNUESZIDMDW5AWV/graph.json","events_json":"https://pith.science/api/pith-number/RN4ZWNL3FYGYNUESZIDMDW5AWV/events.json","paper":"https://pith.science/paper/RN4ZWNL3"},"agent_actions":{"view_html":"https://pith.science/pith/RN4ZWNL3FYGYNUESZIDMDW5AWV","download_json":"https://pith.science/pith/RN4ZWNL3FYGYNUESZIDMDW5AWV.json","view_paper":"https://pith.science/paper/RN4ZWNL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08838&json=true","fetch_graph":"https://pith.science/api/pith-number/RN4ZWNL3FYGYNUESZIDMDW5AWV/graph.json","fetch_events":"https://pith.science/api/pith-number/RN4ZWNL3FYGYNUESZIDMDW5AWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RN4ZWNL3FYGYNUESZIDMDW5AWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RN4ZWNL3FYGYNUESZIDMDW5AWV/action/storage_attestation","attest_author":"https://pith.science/pith/RN4ZWNL3FYGYNUESZIDMDW5AWV/action/author_attestation","sign_citation":"https://pith.science/pith/RN4ZWNL3FYGYNUESZIDMDW5AWV/action/citation_signature","submit_replication":"https://pith.science/pith/RN4ZWNL3FYGYNUESZIDMDW5AWV/action/replication_record"}},"created_at":"2026-07-05T11:04:51.401132+00:00","updated_at":"2026-07-05T11:04:51.401132+00:00"}