{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6RZ4RFIKVCA2ET3VRPS4U5VOEM","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":"3241fd383f58242775624e5813f929ca8f19b73482db5026c9a40a429c24ab7a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T09:39:49Z","title_canon_sha256":"c831d258cbe0cf52b65b015671062cb767df4474916ed1d549826f53c94ca157"},"schema_version":"1.0","source":{"id":"2608.02617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02617","created_at":"2026-08-05T00:37:58Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02617v1","created_at":"2026-08-05T00:37:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02617","created_at":"2026-08-05T00:37:58Z"},{"alias_kind":"pith_short_12","alias_value":"6RZ4RFIKVCA2","created_at":"2026-08-05T00:37:58Z"},{"alias_kind":"pith_short_16","alias_value":"6RZ4RFIKVCA2ET3V","created_at":"2026-08-05T00:37:58Z"},{"alias_kind":"pith_short_8","alias_value":"6RZ4RFIK","created_at":"2026-08-05T00:37:58Z"}],"graph_snapshots":[{"event_id":"sha256:12f9cab1ab3af0cfe764922a4a46e1abd39add5c4fc617aa8135726fa83ece6b","target":"graph","created_at":"2026-08-05T00:37:58Z","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/2608.02617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We evaluate whether clinician pairwise preferences provide a reliable signal of clinical safety in large language model (LLM) evaluation using expert feedback from MOOVE (Massive Open Online Validation and Evaluation), a clinician-led platform collecting blinded pairwise preferences alongside multi-criterion rubric ratings. Clinicians assign scores on a discrete $[-2, +2]$ scale, where negative values indicate clinically unsafe or misleading content. Using 26{,}804 pairwise judgments across outputs from 13 LLMs, contributed by more than 736 clinicians across 28+ countries, we find that clinici","authors_text":"Alexandra Kulinkina, David Sasu, Fay Elhassan, Lars Henning Klein, Mary-Anne Hartley","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T09:39:49Z","title":"Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02617","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:d4fc62b3a704bdf903ad127b4c405f5d60ee83feaf552bc41c457a28373341e1","target":"record","created_at":"2026-08-05T00:37:58Z","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":"3241fd383f58242775624e5813f929ca8f19b73482db5026c9a40a429c24ab7a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T09:39:49Z","title_canon_sha256":"c831d258cbe0cf52b65b015671062cb767df4474916ed1d549826f53c94ca157"},"schema_version":"1.0","source":{"id":"2608.02617","kind":"arxiv","version":1}},"canonical_sha256":"f473c8950aa881a24f758be5ca76ae2314fed738d23136c42d77c1fc41001c82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f473c8950aa881a24f758be5ca76ae2314fed738d23136c42d77c1fc41001c82","first_computed_at":"2026-08-05T00:37:58.870385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:37:58.870385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"60RPwGUsV3kAIcXPD3KtwvC8gv6Y4W8rQfn8aRt6qm1IU3TvN5L0hNSeOxM3ets3VxE4dIuvs4QL3Byau1NoAw==","signature_status":"signed_v1","signed_at":"2026-08-05T00:37:58.872823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4fc62b3a704bdf903ad127b4c405f5d60ee83feaf552bc41c457a28373341e1","sha256:12f9cab1ab3af0cfe764922a4a46e1abd39add5c4fc617aa8135726fa83ece6b"],"state_sha256":"66fe0dda9032cb8e85384e8b4d623e64f39e2fe4e3c68201b310e4ccc5793811"}