{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JBNKV4GKL3HLFMRJXFG5V3EB5N","short_pith_number":"pith:JBNKV4GK","canonical_record":{"source":{"id":"2607.02175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T13:46:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2cb67fa8c093451d9f46bb4081e604ca2003397e97358a6143cb53e875a8087c","abstract_canon_sha256":"d8d184bccedd2f4f619d818086a9ff0a5675cd8a8f92cfe95d097aefdbdff1d7"},"schema_version":"1.0"},"canonical_sha256":"485aaaf0ca5eceb2b229b94ddaec81eb7284a32066ca132cb03c1c9822e18f9a","source":{"kind":"arxiv","id":"2607.02175","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JBNKV4GKL3HLFMRJXFG5V3EB5N","target":"record","payload":{"canonical_record":{"source":{"id":"2607.02175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T13:46:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2cb67fa8c093451d9f46bb4081e604ca2003397e97358a6143cb53e875a8087c","abstract_canon_sha256":"d8d184bccedd2f4f619d818086a9ff0a5675cd8a8f92cfe95d097aefdbdff1d7"},"schema_version":"1.0"},"canonical_sha256":"485aaaf0ca5eceb2b229b94ddaec81eb7284a32066ca132cb03c1c9822e18f9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:44.056363Z","signature_b64":"mbicc88qHvV6ORp/GBMTVSmsUX9fvpCvgza1bPRQMLVpWANsv2d5cF9PuRlBohS6yU0COFjjpNXQ7j3045gHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"485aaaf0ca5eceb2b229b94ddaec81eb7284a32066ca132cb03c1c9822e18f9a","last_reissued_at":"2026-07-03T01:17:44.055906Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:44.055906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.02175","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-03T01:17:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oWm6DKt2EIIaf6Kt3qE6+9DyIE4Bjb91gaEzjxRSPtu64yVvUFiNjfW5/JZEEA8s0m6SM7e6lqHo8m+OVjeqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T04:13:11.795514Z"},"content_sha256":"7fc7621883071175c6ed1ecb5c4b5be2db5de19cf879d221a7e8e94152a0b52a","schema_version":"1.0","event_id":"sha256:7fc7621883071175c6ed1ecb5c4b5be2db5de19cf879d221a7e8e94152a0b52a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JBNKV4GKL3HLFMRJXFG5V3EB5N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A rubric-based controlled comparison of frontier language models on expert-authored clinical reasoning tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ali Merali, Fan X. Chen, Samiha A. Ismail","submitted_at":"2026-07-02T13:46:24Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02175","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/2607.02175/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-03T01:17:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"su1tkLYrjwaR8mmMhKhNTMFvhuDPVQec700R9wwVe+p6Fhw81zdPR7G+rP0+9D1mg5UIFWn2LrmoA8A0cqChDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T04:13:11.795928Z"},"content_sha256":"28255290478e3047b79a4081d88f800b72c2484358b8b793f4cbbecbed17fd61","schema_version":"1.0","event_id":"sha256:28255290478e3047b79a4081d88f800b72c2484358b8b793f4cbbecbed17fd61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JBNKV4GKL3HLFMRJXFG5V3EB5N/bundle.json","state_url":"https://pith.science/pith/JBNKV4GKL3HLFMRJXFG5V3EB5N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JBNKV4GKL3HLFMRJXFG5V3EB5N/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T04:13:11Z","links":{"resolver":"https://pith.science/pith/JBNKV4GKL3HLFMRJXFG5V3EB5N","bundle":"https://pith.science/pith/JBNKV4GKL3HLFMRJXFG5V3EB5N/bundle.json","state":"https://pith.science/pith/JBNKV4GKL3HLFMRJXFG5V3EB5N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JBNKV4GKL3HLFMRJXFG5V3EB5N/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJMhLH+8nKktVHXZt5yHpfWLyaQfDABc0bRnGnCx96/c72cYnS1Xj30GpmChl0fi8PlBcEx64i5wG5LvE5r2AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T04:13:11.798241Z","bundle_sha256":"e6a843ba2a3054c5d4356c7a11cca4f2b8e07ada9a319a0260071c1fbcb70775"}}