{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N6SXX4EZU3O6VCYEPOWHPWDBB3","short_pith_number":"pith:N6SXX4EZ","schema_version":"1.0","canonical_sha256":"6fa57bf099a6ddea8b047bac77d8610efd8238aa62fb8c63c0c4ec5ac68ab527","source":{"kind":"arxiv","id":"2405.20613","version":2},"attestation_state":"computed","paper":{"title":"FineRadScore: A Radiology Report Line-by-Line Evaluation Technique Generating Corrections with Severity Scores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alyssa Huang, Eduardo Pontes Reis, Kay Wu, Oishi Banerjee, Pranav Rajpurkar","submitted_at":"2024-05-31T04:05:09Z","abstract_excerpt":"The current gold standard for evaluating generated chest x-ray (CXR) reports is through radiologist annotations. However, this process can be extremely time-consuming and costly, especially when evaluating large numbers of reports. In this work, we present FineRadScore, a Large Language Model (LLM)-based automated evaluation metric for generated CXR reports. Given a candidate report and a ground-truth report, FineRadScore gives the minimum number of line-by-line corrections required to go from the candidate to the ground-truth report. Additionally, FineRadScore provides an error severity ratin"},"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":"2405.20613","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-31T04:05:09Z","cross_cats_sorted":[],"title_canon_sha256":"be49fdd0240d38eeb9b45907d961f9fce4596de2a4d9675188940ed14a204f8f","abstract_canon_sha256":"ba8d7664f8e830ee50d1054108011ea446d0763b5941f4c0b33b734776fec8b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:14.066534Z","signature_b64":"Loqjyf7NTprp9V9DLdWIyKxvk4qWuThrS4PVcr0fEKf5J+AeTh5R/vWWGfFeS5ce1ZjqqroDsHhC5UR2C3GOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fa57bf099a6ddea8b047bac77d8610efd8238aa62fb8c63c0c4ec5ac68ab527","last_reissued_at":"2026-07-05T08:54:14.066021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:14.066021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineRadScore: A Radiology Report Line-by-Line Evaluation Technique Generating Corrections with Severity Scores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alyssa Huang, Eduardo Pontes Reis, Kay Wu, Oishi Banerjee, Pranav Rajpurkar","submitted_at":"2024-05-31T04:05:09Z","abstract_excerpt":"The current gold standard for evaluating generated chest x-ray (CXR) reports is through radiologist annotations. However, this process can be extremely time-consuming and costly, especially when evaluating large numbers of reports. In this work, we present FineRadScore, a Large Language Model (LLM)-based automated evaluation metric for generated CXR reports. Given a candidate report and a ground-truth report, FineRadScore gives the minimum number of line-by-line corrections required to go from the candidate to the ground-truth report. Additionally, FineRadScore provides an error severity ratin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20613","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/2405.20613/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":"2405.20613","created_at":"2026-07-05T08:54:14.066089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20613v2","created_at":"2026-07-05T08:54:14.066089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20613","created_at":"2026-07-05T08:54:14.066089+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6SXX4EZU3O6","created_at":"2026-07-05T08:54:14.066089+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6SXX4EZU3O6VCYE","created_at":"2026-07-05T08:54:14.066089+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6SXX4EZ","created_at":"2026-07-05T08:54:14.066089+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/N6SXX4EZU3O6VCYEPOWHPWDBB3","json":"https://pith.science/pith/N6SXX4EZU3O6VCYEPOWHPWDBB3.json","graph_json":"https://pith.science/api/pith-number/N6SXX4EZU3O6VCYEPOWHPWDBB3/graph.json","events_json":"https://pith.science/api/pith-number/N6SXX4EZU3O6VCYEPOWHPWDBB3/events.json","paper":"https://pith.science/paper/N6SXX4EZ"},"agent_actions":{"view_html":"https://pith.science/pith/N6SXX4EZU3O6VCYEPOWHPWDBB3","download_json":"https://pith.science/pith/N6SXX4EZU3O6VCYEPOWHPWDBB3.json","view_paper":"https://pith.science/paper/N6SXX4EZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20613&json=true","fetch_graph":"https://pith.science/api/pith-number/N6SXX4EZU3O6VCYEPOWHPWDBB3/graph.json","fetch_events":"https://pith.science/api/pith-number/N6SXX4EZU3O6VCYEPOWHPWDBB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6SXX4EZU3O6VCYEPOWHPWDBB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6SXX4EZU3O6VCYEPOWHPWDBB3/action/storage_attestation","attest_author":"https://pith.science/pith/N6SXX4EZU3O6VCYEPOWHPWDBB3/action/author_attestation","sign_citation":"https://pith.science/pith/N6SXX4EZU3O6VCYEPOWHPWDBB3/action/citation_signature","submit_replication":"https://pith.science/pith/N6SXX4EZU3O6VCYEPOWHPWDBB3/action/replication_record"}},"created_at":"2026-07-05T08:54:14.066089+00:00","updated_at":"2026-07-05T08:54:14.066089+00:00"}