{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7XEZO4ZA5LQ3PD7NJ2DDKFU26S","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":"ca7a77642d207f6e775e94a1cf34da34ca665a48d815abbff0a0765705a07f50","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T15:55:31Z","title_canon_sha256":"77a83bc3f909e0f427bfd538ee7fea4b7ad9b58e0eec44e8317159f95f8c3d28"},"schema_version":"1.0","source":{"id":"2607.01103","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01103","created_at":"2026-07-02T01:18:29Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01103v1","created_at":"2026-07-02T01:18:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01103","created_at":"2026-07-02T01:18:29Z"},{"alias_kind":"pith_short_12","alias_value":"7XEZO4ZA5LQ3","created_at":"2026-07-02T01:18:29Z"},{"alias_kind":"pith_short_16","alias_value":"7XEZO4ZA5LQ3PD7N","created_at":"2026-07-02T01:18:29Z"},{"alias_kind":"pith_short_8","alias_value":"7XEZO4ZA","created_at":"2026-07-02T01:18:29Z"}],"graph_snapshots":[{"event_id":"sha256:0fdf6c7840d29ebfc122d187a6307def5e0aff73689f34f80f713640685af380","target":"graph","created_at":"2026-07-02T01:18:29Z","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/2607.01103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T15:55:31Z","title":"Clinician-Level Agreement Without Clinical Caution: LLM Evaluator Limits in Medical AI Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01103","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":"sha256:9343d6a821617cb052b7d95cbd5d4bbb776094988717d1d1aba8288c869a3280","target":"record","created_at":"2026-07-02T01:18:29Z","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":"ca7a77642d207f6e775e94a1cf34da34ca665a48d815abbff0a0765705a07f50","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T15:55:31Z","title_canon_sha256":"77a83bc3f909e0f427bfd538ee7fea4b7ad9b58e0eec44e8317159f95f8c3d28"},"schema_version":"1.0","source":{"id":"2607.01103","kind":"arxiv","version":1}},"canonical_sha256":"fdc9977320eae1b78fed4e8635169af4894fb0b13399d4229750f03c1c26860f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdc9977320eae1b78fed4e8635169af4894fb0b13399d4229750f03c1c26860f","first_computed_at":"2026-07-02T01:18:29.144063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:29.144063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d81le4WGAPIU6ZRzDlxVunt2DKy4bF2UYIbz5Rvs8n7a7ICY7upT164mS3imekZ2WPKSjflsVaUB/vi/BcJPDA==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:29.144437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01103","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9343d6a821617cb052b7d95cbd5d4bbb776094988717d1d1aba8288c869a3280","sha256:0fdf6c7840d29ebfc122d187a6307def5e0aff73689f34f80f713640685af380"],"state_sha256":"bdbb692473159299c2614c06ccec8e233248a0fe081f2b72d23dcfb240a2da30"}