{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JBNKV4GKL3HLFMRJXFG5V3EB5N","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":"d8d184bccedd2f4f619d818086a9ff0a5675cd8a8f92cfe95d097aefdbdff1d7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T13:46:24Z","title_canon_sha256":"2cb67fa8c093451d9f46bb4081e604ca2003397e97358a6143cb53e875a8087c"},"schema_version":"1.0","source":{"id":"2607.02175","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02175","created_at":"2026-07-03T01:17:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02175v1","created_at":"2026-07-03T01:17:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02175","created_at":"2026-07-03T01:17:44Z"},{"alias_kind":"pith_short_12","alias_value":"JBNKV4GKL3HL","created_at":"2026-07-03T01:17:44Z"},{"alias_kind":"pith_short_16","alias_value":"JBNKV4GKL3HLFMRJ","created_at":"2026-07-03T01:17:44Z"},{"alias_kind":"pith_short_8","alias_value":"JBNKV4GK","created_at":"2026-07-03T01:17:44Z"}],"graph_snapshots":[{"event_id":"sha256:28255290478e3047b79a4081d88f800b72c2484358b8b793f4cbbecbed17fd61","target":"graph","created_at":"2026-07-03T01:17:44Z","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/2607.02175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multiple-choice medical benchmarks are increasingly saturated, and recent rubric-based evaluations such as HealthBench have shown that open-ended clinical performance is far from solved - its \"Hard\" subset top score remains 32%. We present a small, deliberately difficult evaluation dataset of five clinician-authored clinical scenarios spanning four specialties (anaesthesia, internal/family medicine, emergency medicine, and obstetrics), each accompanied by an atomic, weighted, MECE rubric (25-62 criteria per task; 184 criteria total) authored from a clinician-drafted golden answer. We evaluate ","authors_text":"Ali Merali, Fan X. Chen, Samiha A. Ismail","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T13:46:24Z","title":"A rubric-based controlled comparison of frontier language models on expert-authored clinical reasoning tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02175","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":"sha256:7fc7621883071175c6ed1ecb5c4b5be2db5de19cf879d221a7e8e94152a0b52a","target":"record","created_at":"2026-07-03T01:17:44Z","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":"d8d184bccedd2f4f619d818086a9ff0a5675cd8a8f92cfe95d097aefdbdff1d7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T13:46:24Z","title_canon_sha256":"2cb67fa8c093451d9f46bb4081e604ca2003397e97358a6143cb53e875a8087c"},"schema_version":"1.0","source":{"id":"2607.02175","kind":"arxiv","version":1}},"canonical_sha256":"485aaaf0ca5eceb2b229b94ddaec81eb7284a32066ca132cb03c1c9822e18f9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"485aaaf0ca5eceb2b229b94ddaec81eb7284a32066ca132cb03c1c9822e18f9a","first_computed_at":"2026-07-03T01:17:44.055906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:44.055906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mbicc88qHvV6ORp/GBMTVSmsUX9fvpCvgza1bPRQMLVpWANsv2d5cF9PuRlBohS6yU0COFjjpNXQ7j3045gHCQ==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:44.056363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02175","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fc7621883071175c6ed1ecb5c4b5be2db5de19cf879d221a7e8e94152a0b52a","sha256:28255290478e3047b79a4081d88f800b72c2484358b8b793f4cbbecbed17fd61"],"state_sha256":"81cb31f0e23c1be68359a32de217687f7ad6237a74bd0a33cd5084a86c45d812"}