{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:54UREK34UEWLFQXUHOJUVD5ZI2","short_pith_number":"pith:54UREK34","schema_version":"1.0","canonical_sha256":"ef29122b7ca12cb2c2f43b934a8fb9469589b4ae9d72e92bb5f52eee879adc44","source":{"kind":"arxiv","id":"2608.08494","version":1},"attestation_state":"computed","paper":{"title":"Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wang, Qiang Hu, Qiang Li, Qimei Wang, Yingjie Guo, Yuxuan Luo, Zhiwei Wang","submitted_at":"2026-08-09T05:29:42Z","abstract_excerpt":"Despite significant advances in Medical Report Generation (MRG), the reliability remains constrained by the prevalence of factual errors. While Direct Preference Optimization (DPO) has emerged as a promising post-training paradigm to enhance the performance of Supervised Fine-Tuned (SFT) MRG models, existing DPO-based MRG methods typically adopt a naive preference construction that directly pairs model-generated reports with ground truth reports. This strategy inadvertently entangles critical clinical findings with clinically irrelevant linguistic characteristics, and fundamentally lacks expli"},"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":"2608.08494","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-09T05:29:42Z","cross_cats_sorted":[],"title_canon_sha256":"c9ff9aaed03a7fd3494badbde4300ae412b0844f86ac90e57413da0012a7c4ec","abstract_canon_sha256":"576a9fee60d9078ffe063504312aaf7bd5990319adc72686c39769cddbf78bbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:47.267094Z","signature_b64":"Xuy5ALWkOJCyyJzVNpXyIiK/mh6AlQnPPZUd9edn4gm9JjSlx2ypuvG4H0tjBUKzLAhAwyF+UFk0eOfPH3j3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef29122b7ca12cb2c2f43b934a8fb9469589b4ae9d72e92bb5f52eee879adc44","last_reissued_at":"2026-08-11T01:22:47.264768Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:47.264768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wang, Qiang Hu, Qiang Li, Qimei Wang, Yingjie Guo, Yuxuan Luo, Zhiwei Wang","submitted_at":"2026-08-09T05:29:42Z","abstract_excerpt":"Despite significant advances in Medical Report Generation (MRG), the reliability remains constrained by the prevalence of factual errors. While Direct Preference Optimization (DPO) has emerged as a promising post-training paradigm to enhance the performance of Supervised Fine-Tuned (SFT) MRG models, existing DPO-based MRG methods typically adopt a naive preference construction that directly pairs model-generated reports with ground truth reports. This strategy inadvertently entangles critical clinical findings with clinically irrelevant linguistic characteristics, and fundamentally lacks expli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08494","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/2608.08494/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":"2608.08494","created_at":"2026-08-11T01:22:47.265496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08494v1","created_at":"2026-08-11T01:22:47.265496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08494","created_at":"2026-08-11T01:22:47.265496+00:00"},{"alias_kind":"pith_short_12","alias_value":"54UREK34UEWL","created_at":"2026-08-11T01:22:47.265496+00:00"},{"alias_kind":"pith_short_16","alias_value":"54UREK34UEWLFQXU","created_at":"2026-08-11T01:22:47.265496+00:00"},{"alias_kind":"pith_short_8","alias_value":"54UREK34","created_at":"2026-08-11T01:22:47.265496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54UREK34UEWLFQXUHOJUVD5ZI2","json":"https://pith.science/pith/54UREK34UEWLFQXUHOJUVD5ZI2.json","graph_json":"https://pith.science/api/pith-number/54UREK34UEWLFQXUHOJUVD5ZI2/graph.json","events_json":"https://pith.science/api/pith-number/54UREK34UEWLFQXUHOJUVD5ZI2/events.json","paper":"https://pith.science/paper/54UREK34"},"agent_actions":{"view_html":"https://pith.science/pith/54UREK34UEWLFQXUHOJUVD5ZI2","download_json":"https://pith.science/pith/54UREK34UEWLFQXUHOJUVD5ZI2.json","view_paper":"https://pith.science/paper/54UREK34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08494&json=true","fetch_graph":"https://pith.science/api/pith-number/54UREK34UEWLFQXUHOJUVD5ZI2/graph.json","fetch_events":"https://pith.science/api/pith-number/54UREK34UEWLFQXUHOJUVD5ZI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54UREK34UEWLFQXUHOJUVD5ZI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54UREK34UEWLFQXUHOJUVD5ZI2/action/storage_attestation","attest_author":"https://pith.science/pith/54UREK34UEWLFQXUHOJUVD5ZI2/action/author_attestation","sign_citation":"https://pith.science/pith/54UREK34UEWLFQXUHOJUVD5ZI2/action/citation_signature","submit_replication":"https://pith.science/pith/54UREK34UEWLFQXUHOJUVD5ZI2/action/replication_record"}},"created_at":"2026-08-11T01:22:47.265496+00:00","updated_at":"2026-08-11T01:22:47.265496+00:00"}