{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7XEZO4ZA5LQ3PD7NJ2DDKFU26S","short_pith_number":"pith:7XEZO4ZA","schema_version":"1.0","canonical_sha256":"fdc9977320eae1b78fed4e8635169af4894fb0b13399d4229750f03c1c26860f","source":{"kind":"arxiv","id":"2607.01103","version":1},"attestation_state":"computed","paper":{"title":"Clinician-Level Agreement Without Clinical Caution: LLM Evaluator Limits in Medical AI Benchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Baumann, Finn Fassbender, Ip Chi Wang, Johanna Reimer, Lukas Goede, Markus Hobert, Martje Pauly, Rebecca Herzog, Ronald B\\\"ock, Sebastian Fudickar, Sebastian L\\\"ons, Theresa Paulus, Thorsten Langer, William Philipp","submitted_at":"2026-07-01T15:55:31Z","abstract_excerpt":"Open-response evaluation provides stronger clinical validity than multiple-choice benchmarks but creates a scoring bottleneck that motivates automated LLM-asa-Judge approaches. Whether such evaluators replicate clinical calibration and caution, however, remains untested. We introduce MedQADE, the first standardised open-response clinical benchmark for German, a major clinical language lacking native evaluation infrastructure, comprising 3,800 items annotated by ten practising physicians and nine Large Language Model (LLM) evaluators. The top-performing evaluator model, Gemini 3 Flash, reached "},"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":"2607.01103","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T15:55:31Z","cross_cats_sorted":[],"title_canon_sha256":"77a83bc3f909e0f427bfd538ee7fea4b7ad9b58e0eec44e8317159f95f8c3d28","abstract_canon_sha256":"ca7a77642d207f6e775e94a1cf34da34ca665a48d815abbff0a0765705a07f50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:29.144437Z","signature_b64":"d81le4WGAPIU6ZRzDlxVunt2DKy4bF2UYIbz5Rvs8n7a7ICY7upT164mS3imekZ2WPKSjflsVaUB/vi/BcJPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdc9977320eae1b78fed4e8635169af4894fb0b13399d4229750f03c1c26860f","last_reissued_at":"2026-07-02T01:18:29.144063Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:29.144063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clinician-Level Agreement Without Clinical Caution: LLM Evaluator Limits in Medical AI Benchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Baumann, Finn Fassbender, Ip Chi Wang, Johanna Reimer, Lukas Goede, Markus Hobert, Martje Pauly, Rebecca Herzog, Ronald B\\\"ock, Sebastian Fudickar, Sebastian L\\\"ons, Theresa Paulus, Thorsten Langer, William Philipp","submitted_at":"2026-07-01T15:55:31Z","abstract_excerpt":"Open-response evaluation provides stronger clinical validity than multiple-choice benchmarks but creates a scoring bottleneck that motivates automated LLM-asa-Judge approaches. Whether such evaluators replicate clinical calibration and caution, however, remains untested. We introduce MedQADE, the first standardised open-response clinical benchmark for German, a major clinical language lacking native evaluation infrastructure, comprising 3,800 items annotated by ten practising physicians and nine Large Language Model (LLM) evaluators. The top-performing evaluator model, Gemini 3 Flash, reached "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01103","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/2607.01103/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":"2607.01103","created_at":"2026-07-02T01:18:29.144127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01103v1","created_at":"2026-07-02T01:18:29.144127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01103","created_at":"2026-07-02T01:18:29.144127+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XEZO4ZA5LQ3","created_at":"2026-07-02T01:18:29.144127+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XEZO4ZA5LQ3PD7N","created_at":"2026-07-02T01:18:29.144127+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XEZO4ZA","created_at":"2026-07-02T01:18:29.144127+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/7XEZO4ZA5LQ3PD7NJ2DDKFU26S","json":"https://pith.science/pith/7XEZO4ZA5LQ3PD7NJ2DDKFU26S.json","graph_json":"https://pith.science/api/pith-number/7XEZO4ZA5LQ3PD7NJ2DDKFU26S/graph.json","events_json":"https://pith.science/api/pith-number/7XEZO4ZA5LQ3PD7NJ2DDKFU26S/events.json","paper":"https://pith.science/paper/7XEZO4ZA"},"agent_actions":{"view_html":"https://pith.science/pith/7XEZO4ZA5LQ3PD7NJ2DDKFU26S","download_json":"https://pith.science/pith/7XEZO4ZA5LQ3PD7NJ2DDKFU26S.json","view_paper":"https://pith.science/paper/7XEZO4ZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01103&json=true","fetch_graph":"https://pith.science/api/pith-number/7XEZO4ZA5LQ3PD7NJ2DDKFU26S/graph.json","fetch_events":"https://pith.science/api/pith-number/7XEZO4ZA5LQ3PD7NJ2DDKFU26S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XEZO4ZA5LQ3PD7NJ2DDKFU26S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XEZO4ZA5LQ3PD7NJ2DDKFU26S/action/storage_attestation","attest_author":"https://pith.science/pith/7XEZO4ZA5LQ3PD7NJ2DDKFU26S/action/author_attestation","sign_citation":"https://pith.science/pith/7XEZO4ZA5LQ3PD7NJ2DDKFU26S/action/citation_signature","submit_replication":"https://pith.science/pith/7XEZO4ZA5LQ3PD7NJ2DDKFU26S/action/replication_record"}},"created_at":"2026-07-02T01:18:29.144127+00:00","updated_at":"2026-07-02T01:18:29.144127+00:00"}