{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UNCXMYP2BKE3HQABQIFNCTB2JF","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":"2cf17efc5246331ad6e5ae39e79dddcd2c403349c8cd87ad5088f06891811c1e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-20T17:09:27Z","title_canon_sha256":"5ed9102f39366002da5c58d563ffec62549099bd2c4d441863de9f5055443f8f"},"schema_version":"1.0","source":{"id":"2506.17163","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17163","created_at":"2026-07-05T11:24:57Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17163v1","created_at":"2026-07-05T11:24:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17163","created_at":"2026-07-05T11:24:57Z"},{"alias_kind":"pith_short_12","alias_value":"UNCXMYP2BKE3","created_at":"2026-07-05T11:24:57Z"},{"alias_kind":"pith_short_16","alias_value":"UNCXMYP2BKE3HQAB","created_at":"2026-07-05T11:24:57Z"},{"alias_kind":"pith_short_8","alias_value":"UNCXMYP2","created_at":"2026-07-05T11:24:57Z"}],"graph_snapshots":[{"event_id":"sha256:c5d1c6f4117da940f0d653df2db17180b9e0f7497cf6ec547aff5d18a9754740","target":"graph","created_at":"2026-07-05T11:24:57Z","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/2506.17163/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clinical robustness is critical to the safe deployment of medical Large Language Models (LLMs), but key questions remain about how LLMs and humans may differ in response to the real-world variability typified by clinical settings. To address this, we introduce MedPerturb, a dataset designed to systematically evaluate medical LLMs under controlled perturbations of clinical input. MedPerturb consists of clinical vignettes spanning a range of pathologies, each transformed along three axes: (1) gender modifications (e.g., gender-swapping or gender-removal); (2) style variation (e.g., uncertain phr","authors_text":"Abinitha Gourabathina, Marzyeh Ghassemi, Walter Gerych, Yuexing Hao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-20T17:09:27Z","title":"The MedPerturb Dataset: What Non-Content Perturbations Reveal About Human and Clinical LLM Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17163","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":"sha256:46aa818ebe0295c8a70750d5c77407b580a98399bd35299beb159d85e7f9bb5c","target":"record","created_at":"2026-07-05T11:24:57Z","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":"2cf17efc5246331ad6e5ae39e79dddcd2c403349c8cd87ad5088f06891811c1e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-20T17:09:27Z","title_canon_sha256":"5ed9102f39366002da5c58d563ffec62549099bd2c4d441863de9f5055443f8f"},"schema_version":"1.0","source":{"id":"2506.17163","kind":"arxiv","version":1}},"canonical_sha256":"a3457661fa0a89b3c001820ad14c3a497c6c84c6a984563c006d938284203b6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3457661fa0a89b3c001820ad14c3a497c6c84c6a984563c006d938284203b6c","first_computed_at":"2026-07-05T11:24:57.235326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:57.235326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CysZYFZBYMvTlZQviZ4bT82RciFcBvz0haBVG8qkPMDu6Npv78b7Y9pWFSci3YJW5pe+hKV6ywYbYEH7DSNZBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:57.235918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17163","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46aa818ebe0295c8a70750d5c77407b580a98399bd35299beb159d85e7f9bb5c","sha256:c5d1c6f4117da940f0d653df2db17180b9e0f7497cf6ec547aff5d18a9754740"],"state_sha256":"e6138cc7ea1f63f0106d5f5cd1c9ac14aab9b40e90643c0cd2dcfb51ca343812"}