{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TDBCV6ZH2OR2EBCLITP63O53BQ","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":"666f621903fe85024858c7f72612c2958590a67d418df58fac3fd5ba12081d94","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T05:23:46Z","title_canon_sha256":"45e32e1249b0491c2564a729f29cc55e37fe2f144568fc51b280bd9af6cb6bfa"},"schema_version":"1.0","source":{"id":"2606.24155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24155","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24155v1","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24155","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_12","alias_value":"TDBCV6ZH2OR2","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_16","alias_value":"TDBCV6ZH2OR2EBCL","created_at":"2026-06-24T01:14:43Z"},{"alias_kind":"pith_short_8","alias_value":"TDBCV6ZH","created_at":"2026-06-24T01:14:43Z"}],"graph_snapshots":[{"event_id":"sha256:fb0943a76add2e5b392903e93a3accc4f35956bdf49fa6211fb2c8e761636b57","target":"graph","created_at":"2026-06-24T01:14:43Z","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/2606.24155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing medical AI benchmarks lack process visibility, atomic skill evaluation, and integrated hallucination detection. We introduce MedBench v5, a redesigned benchmark for clinical multimodal models (language, vision-language, and agent systems) that moves from static QA to dynamic, process-oriented evaluation. MedBench v5 features: (1) a dual-dimensional framework combining Clinical Cognitive Responsiveness (14 sub-dimensions) and Medical Atomic Skills (4 agent environments), covering 63 tasks; (2) three switchable information-flow stressors (omission, contradiction, evidence delay) for fac","authors_text":"and Xu Jie, Bian Mouxiao, Chen Jiangyuan, Chen Ruiyao, Ding Jinru, Gao Zhuangzhi, Han Bin, Jiang Chuchu, Liu Meiling, Lu Lu, Lu Renjie, Pang Wenrao, Peng xinwei, Ren Sijie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T05:23:46Z","title":"MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24155","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":"sha256:9dc435f407097c233afc78e10e4c27a8c81327fb5f6a0e5d22f330eb093aff70","target":"record","created_at":"2026-06-24T01:14:43Z","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":"666f621903fe85024858c7f72612c2958590a67d418df58fac3fd5ba12081d94","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T05:23:46Z","title_canon_sha256":"45e32e1249b0491c2564a729f29cc55e37fe2f144568fc51b280bd9af6cb6bfa"},"schema_version":"1.0","source":{"id":"2606.24155","kind":"arxiv","version":1}},"canonical_sha256":"98c22afb27d3a3a2044b44dfedbbbb0c1949e917db438fd98705f4b8274578cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98c22afb27d3a3a2044b44dfedbbbb0c1949e917db438fd98705f4b8274578cf","first_computed_at":"2026-06-24T01:14:43.078918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:43.078918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v8xTH93M05jlB957XW9SPxljxyorUi5BwKCPOdGU4RRookX7L9Uo3dXA0nAMihU66f9gsjqbwFZ9S1mPav1oCQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:43.079788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dc435f407097c233afc78e10e4c27a8c81327fb5f6a0e5d22f330eb093aff70","sha256:fb0943a76add2e5b392903e93a3accc4f35956bdf49fa6211fb2c8e761636b57"],"state_sha256":"709ccad02963294b067d0db89dffddec4aa53a83d763c74e9ce9449d00a5dcc0"}