{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UNCXMYP2BKE3HQABQIFNCTB2JF","short_pith_number":"pith:UNCXMYP2","canonical_record":{"source":{"id":"2506.17163","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-20T17:09:27Z","cross_cats_sorted":[],"title_canon_sha256":"5ed9102f39366002da5c58d563ffec62549099bd2c4d441863de9f5055443f8f","abstract_canon_sha256":"2cf17efc5246331ad6e5ae39e79dddcd2c403349c8cd87ad5088f06891811c1e"},"schema_version":"1.0"},"canonical_sha256":"a3457661fa0a89b3c001820ad14c3a497c6c84c6a984563c006d938284203b6c","source":{"kind":"arxiv","id":"2506.17163","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UNCXMYP2BKE3HQABQIFNCTB2JF","target":"record","payload":{"canonical_record":{"source":{"id":"2506.17163","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-20T17:09:27Z","cross_cats_sorted":[],"title_canon_sha256":"5ed9102f39366002da5c58d563ffec62549099bd2c4d441863de9f5055443f8f","abstract_canon_sha256":"2cf17efc5246331ad6e5ae39e79dddcd2c403349c8cd87ad5088f06891811c1e"},"schema_version":"1.0"},"canonical_sha256":"a3457661fa0a89b3c001820ad14c3a497c6c84c6a984563c006d938284203b6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:57.235918Z","signature_b64":"CysZYFZBYMvTlZQviZ4bT82RciFcBvz0haBVG8qkPMDu6Npv78b7Y9pWFSci3YJW5pe+hKV6ywYbYEH7DSNZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3457661fa0a89b3c001820ad14c3a497c6c84c6a984563c006d938284203b6c","last_reissued_at":"2026-07-05T11:24:57.235326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:57.235326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.17163","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":"2026-07-05T11:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wsu/4n1gc+2UPGVOVq9267EBRVLIE0KAmeDmmacPziKGDP9VS7rCOUp1Kjp5CDdoL+GYUFZNjiP6VsOObXxyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:06:18.756569Z"},"content_sha256":"46aa818ebe0295c8a70750d5c77407b580a98399bd35299beb159d85e7f9bb5c","schema_version":"1.0","event_id":"sha256:46aa818ebe0295c8a70750d5c77407b580a98399bd35299beb159d85e7f9bb5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UNCXMYP2BKE3HQABQIFNCTB2JF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The MedPerturb Dataset: What Non-Content Perturbations Reveal About Human and Clinical LLM Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abinitha Gourabathina, Marzyeh Ghassemi, Walter Gerych, Yuexing Hao","submitted_at":"2025-06-20T17:09:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17163","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/2506.17163/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":"2026-07-05T11:24:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mV5yCm4nGLWM3NK1OEXkNKUH2T/cTIj39NBaH3IiO3OXXxEXmUWKhFQTDGuSN5iS/1+mP6ZaVFIvFUJrOXT4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:06:18.757104Z"},"content_sha256":"c5d1c6f4117da940f0d653df2db17180b9e0f7497cf6ec547aff5d18a9754740","schema_version":"1.0","event_id":"sha256:c5d1c6f4117da940f0d653df2db17180b9e0f7497cf6ec547aff5d18a9754740"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNCXMYP2BKE3HQABQIFNCTB2JF/bundle.json","state_url":"https://pith.science/pith/UNCXMYP2BKE3HQABQIFNCTB2JF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNCXMYP2BKE3HQABQIFNCTB2JF/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":"2026-08-07T17:06:18Z","links":{"resolver":"https://pith.science/pith/UNCXMYP2BKE3HQABQIFNCTB2JF","bundle":"https://pith.science/pith/UNCXMYP2BKE3HQABQIFNCTB2JF/bundle.json","state":"https://pith.science/pith/UNCXMYP2BKE3HQABQIFNCTB2JF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNCXMYP2BKE3HQABQIFNCTB2JF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vHWfuM/L7KrF8QSmzUorVuVaUDZg32y3s7kJWnU5jzUSvXB9SNwoc1wkUyKNmAiLzNuwL4O843cCa8lRSGzQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:06:18.768802Z","bundle_sha256":"088e1a4e86fa667af408107c235736c5a8ffb7dfb2a56110fd594c6c04c55a71"}}