{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JACOBFSNN7OMKQJUFBWQLKQMP6","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":"b687248ce0c9eeb36c5c115c0fd4bca40297b7488a1ba652bcb3b52ce6a28cdc","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-26T18:38:25Z","title_canon_sha256":"84a8f191ca042b220116f45fd95a23bf64f30a5c411e2b0f1881da2fd04ed3c4"},"schema_version":"1.0","source":{"id":"2603.25821","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.25821","created_at":"2026-07-22T00:22:33Z"},{"alias_kind":"arxiv_version","alias_value":"2603.25821v2","created_at":"2026-07-22T00:22:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.25821","created_at":"2026-07-22T00:22:33Z"},{"alias_kind":"pith_short_12","alias_value":"JACOBFSNN7OM","created_at":"2026-07-22T00:22:33Z"},{"alias_kind":"pith_short_16","alias_value":"JACOBFSNN7OMKQJU","created_at":"2026-07-22T00:22:33Z"},{"alias_kind":"pith_short_8","alias_value":"JACOBFSN","created_at":"2026-07-22T00:22:33Z"}],"graph_snapshots":[{"event_id":"sha256:36881c77e8a2512994f0ee377a93928806a444e32a2293eb29c7ae0a71f1cc46","target":"graph","created_at":"2026-07-22T00:22:33Z","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/2603.25821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Doctorina MedBench, a comprehensive evaluation framework for agent-based medical AI based on the simulation of realistic physician-patient interactions. Unlike traditional medical benchmarks that rely on solving standardized test questions, the proposed approach models a multi-step clinical dialogue in which either a physician or an AI system must collect medical history, analyze attached materials (including laboratory reports, images, and medical documents), formulate differential diagnoses, and provide personalized recommendations. System performance is evaluated using the D.O.T.","authors_text":"Anna Kozlova, Hanna Plotnitskaya, Pavel Satalkin, Sergey Parfenyuk, Stanislau Salavei","cross_cats":["cs.AI","cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-26T18:38:25Z","title":"Doctorina MedBench-ICD10: A Dialogue-Based Benchmark and Evaluation Framework for Agent-Based Medical AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.25821","kind":"arxiv","version":2},"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":"sha256:8ba0456863978783a6f5d5b5d41018d4f73af085ca81c2adcff3375b7f74b348","target":"record","created_at":"2026-07-22T00:22:33Z","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":"b687248ce0c9eeb36c5c115c0fd4bca40297b7488a1ba652bcb3b52ce6a28cdc","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-26T18:38:25Z","title_canon_sha256":"84a8f191ca042b220116f45fd95a23bf64f30a5c411e2b0f1881da2fd04ed3c4"},"schema_version":"1.0","source":{"id":"2603.25821","kind":"arxiv","version":2}},"canonical_sha256":"4804e0964d6fdcc54134286d05aa0c7f8b5fece8e95087413ed5186226f74134","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4804e0964d6fdcc54134286d05aa0c7f8b5fece8e95087413ed5186226f74134","first_computed_at":"2026-07-22T00:22:33.914366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:33.914366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3aJGxDHSjztXZvTYgHOkohzHl1GKOwv3qGAyeGHUpc1hQO6a+WdKCMa+rP3MmfeHDK9wCv8uhUNWu4eo/hP/BA==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:33.915242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.25821","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ba0456863978783a6f5d5b5d41018d4f73af085ca81c2adcff3375b7f74b348","sha256:36881c77e8a2512994f0ee377a93928806a444e32a2293eb29c7ae0a71f1cc46"],"state_sha256":"8b39834ab58c47ddb9544133bfb51d64ce00bbd8fc480cd00edb20a3b04322bb"}