{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YDFMTRVWX4J2PLMK4YXNZTVDHF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5fdc485bd2eeda1e12d9e3c6193db1f111f44f38a2d177c7848bf4d575821c94","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-04T18:28:03Z","title_canon_sha256":"0f06b480559264abda2149188dbd6b39509111833f1efc0bd4a2cf4eaf420ebd"},"schema_version":"1.0","source":{"id":"2508.02808","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02808","created_at":"2026-07-05T11:48:31Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02808v1","created_at":"2026-07-05T11:48:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02808","created_at":"2026-07-05T11:48:31Z"},{"alias_kind":"pith_short_12","alias_value":"YDFMTRVWX4J2","created_at":"2026-07-05T11:48:31Z"},{"alias_kind":"pith_short_16","alias_value":"YDFMTRVWX4J2PLMK","created_at":"2026-07-05T11:48:31Z"},{"alias_kind":"pith_short_8","alias_value":"YDFMTRVW","created_at":"2026-07-05T11:48:31Z"}],"graph_snapshots":[{"event_id":"sha256:09be5b67eb38462b9461f093628f2b3ba9726378297fac2939b20ad713e8ae78","target":"graph","created_at":"2026-07-05T11:48:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.02808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Radiological imaging is central to diagnosis, treatment planning, and clinical decision-making. Vision-language foundation models have spurred interest in automated radiology report generation (RRG), but safe deployment requires reliable clinical evaluation of generated reports. Existing metrics often rely on surface-level similarity or behave as black boxes, lacking interpretability. We introduce ICARE (Interpretable and Clinically-grounded Agent-based Report Evaluation), an interpretable evaluation framework leveraging large language model agents and dynamic multiple-choice question answerin","authors_text":"Daniel Alexander Alber, Daniel Freedman, Danielle Rigau, Diana Ruan, Eric Karl Oermann, Kang Zhang, Kyunghyun Cho, Motaz Nashawaty, Radhika Dua, Siddhant Dogra, Young Joon (Fred) Kwon","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-04T18:28:03Z","title":"Clinically Grounded Agent-based Report Evaluation: An Interpretable Metric for Radiology Report Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02808","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ad55b5f982b180b3969bfd4a0c0e6a08c12f16a631ded6de6c6245d01aca3bb4","target":"record","created_at":"2026-07-05T11:48:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5fdc485bd2eeda1e12d9e3c6193db1f111f44f38a2d177c7848bf4d575821c94","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-04T18:28:03Z","title_canon_sha256":"0f06b480559264abda2149188dbd6b39509111833f1efc0bd4a2cf4eaf420ebd"},"schema_version":"1.0","source":{"id":"2508.02808","kind":"arxiv","version":1}},"canonical_sha256":"c0cac9c6b6bf13a7ad8ae62edccea3397c84eca4603c06ef8949ae05e271a068","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0cac9c6b6bf13a7ad8ae62edccea3397c84eca4603c06ef8949ae05e271a068","first_computed_at":"2026-07-05T11:48:31.295908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:31.295908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+QVsoLfwcP6b+rFxQFUiggv1JRu8BYoqn7UgrTmS12qjdndBpH+0Y5Yu2qsq5kjLwihevM4FT/VXDBhQmz4uBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:31.296567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02808","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad55b5f982b180b3969bfd4a0c0e6a08c12f16a631ded6de6c6245d01aca3bb4","sha256:09be5b67eb38462b9461f093628f2b3ba9726378297fac2939b20ad713e8ae78"],"state_sha256":"b3fe7cfcf71a32bd37f859aff9972340f171419754c65702981411dbad97d0b0"}