{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PTMYVQCOOIQNHXXSL32QR725N4","short_pith_number":"pith:PTMYVQCO","schema_version":"1.0","canonical_sha256":"7cd98ac04e7220d3def25ef508ff5d6f0db255ebe5a2d8b5cd42cd6f211d3400","source":{"kind":"arxiv","id":"2508.15464","version":1},"attestation_state":"computed","paper":{"title":"RadReason: Radiology Report Evaluation Metric with Reasons and Sub-Scores","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, Yingshu Li, Yunyi Liu","submitted_at":"2025-08-21T11:34:30Z","abstract_excerpt":"Evaluating automatically generated radiology reports remains a fundamental challenge due to the lack of clinically grounded, interpretable, and fine-grained metrics. Existing methods either produce coarse overall scores or rely on opaque black-box models, limiting their usefulness in real-world clinical workflows. We introduce RadReason, a novel evaluation framework for radiology reports that not only outputs fine-grained sub-scores across six clinically defined error types, but also produces human-readable justifications that explain the rationale behind each score. Our method builds on Group"},"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":"2508.15464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T11:34:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4cdf20eae5cf4c8adf89c4a776d4d645b86b38008521cda56266851e7272ffa","abstract_canon_sha256":"4ba1d62fcf67ba2f86b676b1e93c86675d0d9c3389d8f4b362017d372505e0df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:12.731725Z","signature_b64":"f231Go+cXTHGK80nGvUlPhqzttm8g3qWWrOauhoygcT/kIw8+/K9yx6RJalairsxx81fOW0ERwaNlMvWxSPvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cd98ac04e7220d3def25ef508ff5d6f0db255ebe5a2d8b5cd42cd6f211d3400","last_reissued_at":"2026-07-05T11:57:12.731177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:12.731177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RadReason: Radiology Report Evaluation Metric with Reasons and Sub-Scores","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, Yingshu Li, Yunyi Liu","submitted_at":"2025-08-21T11:34:30Z","abstract_excerpt":"Evaluating automatically generated radiology reports remains a fundamental challenge due to the lack of clinically grounded, interpretable, and fine-grained metrics. Existing methods either produce coarse overall scores or rely on opaque black-box models, limiting their usefulness in real-world clinical workflows. We introduce RadReason, a novel evaluation framework for radiology reports that not only outputs fine-grained sub-scores across six clinically defined error types, but also produces human-readable justifications that explain the rationale behind each score. Our method builds on Group"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15464","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/2508.15464/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":"2508.15464","created_at":"2026-07-05T11:57:12.731238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15464v1","created_at":"2026-07-05T11:57:12.731238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15464","created_at":"2026-07-05T11:57:12.731238+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTMYVQCOOIQN","created_at":"2026-07-05T11:57:12.731238+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTMYVQCOOIQNHXXS","created_at":"2026-07-05T11:57:12.731238+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTMYVQCO","created_at":"2026-07-05T11:57:12.731238+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/PTMYVQCOOIQNHXXSL32QR725N4","json":"https://pith.science/pith/PTMYVQCOOIQNHXXSL32QR725N4.json","graph_json":"https://pith.science/api/pith-number/PTMYVQCOOIQNHXXSL32QR725N4/graph.json","events_json":"https://pith.science/api/pith-number/PTMYVQCOOIQNHXXSL32QR725N4/events.json","paper":"https://pith.science/paper/PTMYVQCO"},"agent_actions":{"view_html":"https://pith.science/pith/PTMYVQCOOIQNHXXSL32QR725N4","download_json":"https://pith.science/pith/PTMYVQCOOIQNHXXSL32QR725N4.json","view_paper":"https://pith.science/paper/PTMYVQCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15464&json=true","fetch_graph":"https://pith.science/api/pith-number/PTMYVQCOOIQNHXXSL32QR725N4/graph.json","fetch_events":"https://pith.science/api/pith-number/PTMYVQCOOIQNHXXSL32QR725N4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTMYVQCOOIQNHXXSL32QR725N4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTMYVQCOOIQNHXXSL32QR725N4/action/storage_attestation","attest_author":"https://pith.science/pith/PTMYVQCOOIQNHXXSL32QR725N4/action/author_attestation","sign_citation":"https://pith.science/pith/PTMYVQCOOIQNHXXSL32QR725N4/action/citation_signature","submit_replication":"https://pith.science/pith/PTMYVQCOOIQNHXXSL32QR725N4/action/replication_record"}},"created_at":"2026-07-05T11:57:12.731238+00:00","updated_at":"2026-07-05T11:57:12.731238+00:00"}