{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TDBCV6ZH2OR2EBCLITP63O53BQ","short_pith_number":"pith:TDBCV6ZH","schema_version":"1.0","canonical_sha256":"98c22afb27d3a3a2044b44dfedbbbb0c1949e917db438fd98705f4b8274578cf","source":{"kind":"arxiv","id":"2606.24155","version":1},"attestation_state":"computed","paper":{"title":"MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2026-06-23T05:23:46Z","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"},"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":"2606.24155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T05:23:46Z","cross_cats_sorted":[],"title_canon_sha256":"45e32e1249b0491c2564a729f29cc55e37fe2f144568fc51b280bd9af6cb6bfa","abstract_canon_sha256":"666f621903fe85024858c7f72612c2958590a67d418df58fac3fd5ba12081d94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:43.079788Z","signature_b64":"v8xTH93M05jlB957XW9SPxljxyorUi5BwKCPOdGU4RRookX7L9Uo3dXA0nAMihU66f9gsjqbwFZ9S1mPav1oCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98c22afb27d3a3a2044b44dfedbbbb0c1949e917db438fd98705f4b8274578cf","last_reissued_at":"2026-06-24T01:14:43.078918Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:43.078918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","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","submitted_at":"2026-06-23T05:23:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24155","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/2606.24155/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":"2606.24155","created_at":"2026-06-24T01:14:43.079076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24155v1","created_at":"2026-06-24T01:14:43.079076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24155","created_at":"2026-06-24T01:14:43.079076+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDBCV6ZH2OR2","created_at":"2026-06-24T01:14:43.079076+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDBCV6ZH2OR2EBCL","created_at":"2026-06-24T01:14:43.079076+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDBCV6ZH","created_at":"2026-06-24T01:14:43.079076+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/TDBCV6ZH2OR2EBCLITP63O53BQ","json":"https://pith.science/pith/TDBCV6ZH2OR2EBCLITP63O53BQ.json","graph_json":"https://pith.science/api/pith-number/TDBCV6ZH2OR2EBCLITP63O53BQ/graph.json","events_json":"https://pith.science/api/pith-number/TDBCV6ZH2OR2EBCLITP63O53BQ/events.json","paper":"https://pith.science/paper/TDBCV6ZH"},"agent_actions":{"view_html":"https://pith.science/pith/TDBCV6ZH2OR2EBCLITP63O53BQ","download_json":"https://pith.science/pith/TDBCV6ZH2OR2EBCLITP63O53BQ.json","view_paper":"https://pith.science/paper/TDBCV6ZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24155&json=true","fetch_graph":"https://pith.science/api/pith-number/TDBCV6ZH2OR2EBCLITP63O53BQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TDBCV6ZH2OR2EBCLITP63O53BQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDBCV6ZH2OR2EBCLITP63O53BQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDBCV6ZH2OR2EBCLITP63O53BQ/action/storage_attestation","attest_author":"https://pith.science/pith/TDBCV6ZH2OR2EBCLITP63O53BQ/action/author_attestation","sign_citation":"https://pith.science/pith/TDBCV6ZH2OR2EBCLITP63O53BQ/action/citation_signature","submit_replication":"https://pith.science/pith/TDBCV6ZH2OR2EBCLITP63O53BQ/action/replication_record"}},"created_at":"2026-06-24T01:14:43.079076+00:00","updated_at":"2026-06-24T01:14:43.079076+00:00"}