{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CDYEUOYCUMVSCPTXKB5RZPGBBA","short_pith_number":"pith:CDYEUOYC","schema_version":"1.0","canonical_sha256":"10f04a3b02a32b213e77507b1cbcc1082368bf37afe61d9b2622817336036d4c","source":{"kind":"arxiv","id":"2404.17778","version":1},"attestation_state":"computed","paper":{"title":"MRScore: Evaluating Radiology Report Generation with LLM-based Reward System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Wang, Lingqiao Liu, Luping Zhou, Xinyu Liang, Yingshu Li, Yunyi Liu, Zhanyu Wang","submitted_at":"2024-04-27T04:42:45Z","abstract_excerpt":"In recent years, automated radiology report generation has experienced significant growth. This paper introduces MRScore, an automatic evaluation metric tailored for radiology report generation by leveraging Large Language Models (LLMs). Conventional NLG (natural language generation) metrics like BLEU are inadequate for accurately assessing the generated radiology reports, as systematically demonstrated by our observations within this paper. To address this challenge, we collaborated with radiologists to develop a framework that guides LLMs for radiology report evaluation, ensuring alignment w"},"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":"2404.17778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T04:42:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"693417df782fa0c871078b446dffa6c80b15f2f27bda8580a28c3cd4505b7287","abstract_canon_sha256":"3c6799e8a25c115465142b0184f1fe646b1ff1942d45afa774d306427a396704"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:53.995057Z","signature_b64":"3EbwaipGEADafZ0vnWAIES61pn2fSodNt/QKAw2RDaSJUSq+6MHPP/CYbqkvAPTDxtrqAIk6HrETU4T0MEbQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10f04a3b02a32b213e77507b1cbcc1082368bf37afe61d9b2622817336036d4c","last_reissued_at":"2026-07-05T08:12:53.994510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:53.994510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MRScore: Evaluating Radiology Report Generation with LLM-based Reward System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Wang, Lingqiao Liu, Luping Zhou, Xinyu Liang, Yingshu Li, Yunyi Liu, Zhanyu Wang","submitted_at":"2024-04-27T04:42:45Z","abstract_excerpt":"In recent years, automated radiology report generation has experienced significant growth. This paper introduces MRScore, an automatic evaluation metric tailored for radiology report generation by leveraging Large Language Models (LLMs). Conventional NLG (natural language generation) metrics like BLEU are inadequate for accurately assessing the generated radiology reports, as systematically demonstrated by our observations within this paper. To address this challenge, we collaborated with radiologists to develop a framework that guides LLMs for radiology report evaluation, ensuring alignment w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17778","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/2404.17778/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":"2404.17778","created_at":"2026-07-05T08:12:53.994568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17778v1","created_at":"2026-07-05T08:12:53.994568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17778","created_at":"2026-07-05T08:12:53.994568+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDYEUOYCUMVS","created_at":"2026-07-05T08:12:53.994568+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDYEUOYCUMVSCPTX","created_at":"2026-07-05T08:12:53.994568+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDYEUOYC","created_at":"2026-07-05T08:12:53.994568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04067","citing_title":"Automated Medical Report Generation for ECG Data: Bridging Medical Text and Signal Processing with Deep Learning","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDYEUOYCUMVSCPTXKB5RZPGBBA","json":"https://pith.science/pith/CDYEUOYCUMVSCPTXKB5RZPGBBA.json","graph_json":"https://pith.science/api/pith-number/CDYEUOYCUMVSCPTXKB5RZPGBBA/graph.json","events_json":"https://pith.science/api/pith-number/CDYEUOYCUMVSCPTXKB5RZPGBBA/events.json","paper":"https://pith.science/paper/CDYEUOYC"},"agent_actions":{"view_html":"https://pith.science/pith/CDYEUOYCUMVSCPTXKB5RZPGBBA","download_json":"https://pith.science/pith/CDYEUOYCUMVSCPTXKB5RZPGBBA.json","view_paper":"https://pith.science/paper/CDYEUOYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17778&json=true","fetch_graph":"https://pith.science/api/pith-number/CDYEUOYCUMVSCPTXKB5RZPGBBA/graph.json","fetch_events":"https://pith.science/api/pith-number/CDYEUOYCUMVSCPTXKB5RZPGBBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDYEUOYCUMVSCPTXKB5RZPGBBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDYEUOYCUMVSCPTXKB5RZPGBBA/action/storage_attestation","attest_author":"https://pith.science/pith/CDYEUOYCUMVSCPTXKB5RZPGBBA/action/author_attestation","sign_citation":"https://pith.science/pith/CDYEUOYCUMVSCPTXKB5RZPGBBA/action/citation_signature","submit_replication":"https://pith.science/pith/CDYEUOYCUMVSCPTXKB5RZPGBBA/action/replication_record"}},"created_at":"2026-07-05T08:12:53.994568+00:00","updated_at":"2026-07-05T08:12:53.994568+00:00"}