{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FAF5LGIRTZAL57KTJLYPD2TYR5","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":"ecc74d43fc91aea1c1eaff522f3224acf8e9c22f807cf61cf281a3b2b4e9c654","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:20:16Z","title_canon_sha256":"000c3d689c4dd24749af4a38eeba9101a31e6369aa895498ea7732926269de29"},"schema_version":"1.0","source":{"id":"2412.09529","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09529","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09529v3","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09529","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_12","alias_value":"FAF5LGIRTZAL","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_16","alias_value":"FAF5LGIRTZAL57KT","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_8","alias_value":"FAF5LGIR","created_at":"2026-07-05T10:45:58Z"}],"graph_snapshots":[{"event_id":"sha256:8abf6e9ae4f65a799b55b38203bee97c40c8ae9d6fbe169c30f042738232f758","target":"graph","created_at":"2026-07-05T10:45:58Z","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/2412.09529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce RadA-BenchPlat, an evaluation platform that benchmarks the performance of large language models (LLMs) act as agent cores in radiology environments using 2,200 radiologist-verified synthetic patient records covering six anatomical regions, five imaging modalities, and 2,200 disease scenarios, resulting in 24,200 question-answer pairs that simulate diverse clinical situations. The platform also defines ten categories of tools for agent-driven task solving and evaluates seven leading LLMs, revealing that while models like Claude-3.7-Sonnet can achieve a 67.1% task completion rate in","authors_text":"Chaoyi Wu, Lisong Dai, Pengcheng Qiu, Qiaoyu Zheng, Weidi Xie, Yanfeng Wang, Ya Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:20:16Z","title":"How Well Can Modern LLMs Act as Agent Cores in Radiology Environments?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09529","kind":"arxiv","version":3},"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:a8191b6244be0962e3f40feffa85c90605d16f5f70136e0470723c53738c458b","target":"record","created_at":"2026-07-05T10:45:58Z","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":"ecc74d43fc91aea1c1eaff522f3224acf8e9c22f807cf61cf281a3b2b4e9c654","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:20:16Z","title_canon_sha256":"000c3d689c4dd24749af4a38eeba9101a31e6369aa895498ea7732926269de29"},"schema_version":"1.0","source":{"id":"2412.09529","kind":"arxiv","version":3}},"canonical_sha256":"280bd599119e40befd534af0f1ea788f797d83897eb050c5d4b190ef5855e66f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"280bd599119e40befd534af0f1ea788f797d83897eb050c5d4b190ef5855e66f","first_computed_at":"2026-07-05T10:45:58.271291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:58.271291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FTCV6ewhFQ9GAfY4MujT94uDXfeK0bFk0PEC74hAhRJZl/wd7cXldtGcBbi3mM4A7gtpfXp+QL6aOSktYo/7BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:58.271798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09529","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8191b6244be0962e3f40feffa85c90605d16f5f70136e0470723c53738c458b","sha256:8abf6e9ae4f65a799b55b38203bee97c40c8ae9d6fbe169c30f042738232f758"],"state_sha256":"be6fd1f881c4f6887f1de53eaeca883f551b9b28c05bd3f191b5f13b0dda15f2"}