{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4IM2UBJ5KCQCMXTANSJNDR4WYO","short_pith_number":"pith:4IM2UBJ5","schema_version":"1.0","canonical_sha256":"e219aa053d50a0265e606c92d1c796c3a3c7f32be384f5cd2d7b807108acd121","source":{"kind":"arxiv","id":"2408.16208","version":1},"attestation_state":"computed","paper":{"title":"ReXamine-Global: A Framework for Uncovering Inconsistencies in Radiology Report Generation Metrics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Adil Zia, Agustina Saenz, Alain S. Abi-Ghanem, Cibele Luna, Dominic Buensalido, Frederic Jonske, Helen Kavnoudias, Heng-sheng Chao, Johannes Haubold, Kay Wu, Khaled Al-Surimi, Lars Heiliger, Moon Kim, Nour El Ghawi, Oishi Banerjee, Patricia Castillo, Pranav Rajpurkar, Rayyan A. Daghistani, Warren Clements, Yuh-Min Chen","submitted_at":"2024-08-29T02:03:05Z","abstract_excerpt":"Given the rapidly expanding capabilities of generative AI models for radiology, there is a need for robust metrics that can accurately measure the quality of AI-generated radiology reports across diverse hospitals. We develop ReXamine-Global, a LLM-powered, multi-site framework that tests metrics across different writing styles and patient populations, exposing gaps in their generalization. First, our method tests whether a metric is undesirably sensitive to reporting style, providing different scores depending on whether AI-generated reports are stylistically similar to ground-truth reports o"},"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":"2408.16208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-29T02:03:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e80fe4a55a1a4e2af7be4102f45829039a26319d33c38d432dd039d14a676cdd","abstract_canon_sha256":"18ef241549ecb5f59290f6518964006776aa7c47a1c0eaa8a929d1c0b34218be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:27.797215Z","signature_b64":"M0pkI30BeDsHwAy+4vR6wO4fVtCWN/SjufzolTmn/k8sReXnhl+MMb3gf6tStzchZRPMri0x1jyizJquC3/XDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e219aa053d50a0265e606c92d1c796c3a3c7f32be384f5cd2d7b807108acd121","last_reissued_at":"2026-07-05T09:00:27.796759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:27.796759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReXamine-Global: A Framework for Uncovering Inconsistencies in Radiology Report Generation Metrics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Adil Zia, Agustina Saenz, Alain S. Abi-Ghanem, Cibele Luna, Dominic Buensalido, Frederic Jonske, Helen Kavnoudias, Heng-sheng Chao, Johannes Haubold, Kay Wu, Khaled Al-Surimi, Lars Heiliger, Moon Kim, Nour El Ghawi, Oishi Banerjee, Patricia Castillo, Pranav Rajpurkar, Rayyan A. Daghistani, Warren Clements, Yuh-Min Chen","submitted_at":"2024-08-29T02:03:05Z","abstract_excerpt":"Given the rapidly expanding capabilities of generative AI models for radiology, there is a need for robust metrics that can accurately measure the quality of AI-generated radiology reports across diverse hospitals. We develop ReXamine-Global, a LLM-powered, multi-site framework that tests metrics across different writing styles and patient populations, exposing gaps in their generalization. First, our method tests whether a metric is undesirably sensitive to reporting style, providing different scores depending on whether AI-generated reports are stylistically similar to ground-truth reports o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16208","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/2408.16208/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":"2408.16208","created_at":"2026-07-05T09:00:27.796823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16208v1","created_at":"2026-07-05T09:00:27.796823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16208","created_at":"2026-07-05T09:00:27.796823+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IM2UBJ5KCQC","created_at":"2026-07-05T09:00:27.796823+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IM2UBJ5KCQCMXTA","created_at":"2026-07-05T09:00:27.796823+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IM2UBJ5","created_at":"2026-07-05T09:00:27.796823+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/4IM2UBJ5KCQCMXTANSJNDR4WYO","json":"https://pith.science/pith/4IM2UBJ5KCQCMXTANSJNDR4WYO.json","graph_json":"https://pith.science/api/pith-number/4IM2UBJ5KCQCMXTANSJNDR4WYO/graph.json","events_json":"https://pith.science/api/pith-number/4IM2UBJ5KCQCMXTANSJNDR4WYO/events.json","paper":"https://pith.science/paper/4IM2UBJ5"},"agent_actions":{"view_html":"https://pith.science/pith/4IM2UBJ5KCQCMXTANSJNDR4WYO","download_json":"https://pith.science/pith/4IM2UBJ5KCQCMXTANSJNDR4WYO.json","view_paper":"https://pith.science/paper/4IM2UBJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16208&json=true","fetch_graph":"https://pith.science/api/pith-number/4IM2UBJ5KCQCMXTANSJNDR4WYO/graph.json","fetch_events":"https://pith.science/api/pith-number/4IM2UBJ5KCQCMXTANSJNDR4WYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IM2UBJ5KCQCMXTANSJNDR4WYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IM2UBJ5KCQCMXTANSJNDR4WYO/action/storage_attestation","attest_author":"https://pith.science/pith/4IM2UBJ5KCQCMXTANSJNDR4WYO/action/author_attestation","sign_citation":"https://pith.science/pith/4IM2UBJ5KCQCMXTANSJNDR4WYO/action/citation_signature","submit_replication":"https://pith.science/pith/4IM2UBJ5KCQCMXTANSJNDR4WYO/action/replication_record"}},"created_at":"2026-07-05T09:00:27.796823+00:00","updated_at":"2026-07-05T09:00:27.796823+00:00"}