{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NMZI7E4Y64PS24PWPAEJPKQOTH","short_pith_number":"pith:NMZI7E4Y","canonical_record":{"source":{"id":"2505.24040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T22:23:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8fa4aeb37fc2a4ba28f21c0a35750efc4faa7f0f8670b7fa9f495bcc1aadd93d","abstract_canon_sha256":"bbb27522825ed9cf193f0d44f7052185ec086dfb1ae478589e950e1485576b84"},"schema_version":"1.0"},"canonical_sha256":"6b328f9398f71f2d71f6780897aa0e99d84038745c6ba96e6017103975e53f79","source":{"kind":"arxiv","id":"2505.24040","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24040","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24040v1","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24040","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"pith_short_12","alias_value":"NMZI7E4Y64PS","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"pith_short_16","alias_value":"NMZI7E4Y64PS24PW","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"pith_short_8","alias_value":"NMZI7E4Y","created_at":"2026-07-05T11:12:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NMZI7E4Y64PS24PWPAEJPKQOTH","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T22:23:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8fa4aeb37fc2a4ba28f21c0a35750efc4faa7f0f8670b7fa9f495bcc1aadd93d","abstract_canon_sha256":"bbb27522825ed9cf193f0d44f7052185ec086dfb1ae478589e950e1485576b84"},"schema_version":"1.0"},"canonical_sha256":"6b328f9398f71f2d71f6780897aa0e99d84038745c6ba96e6017103975e53f79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:40.603502Z","signature_b64":"GdWW2FoWPmlbATnmAYbavc++uZ+0iTagmxfBVFRqcbwfZMRxUNXEhRxizqDzk2rdH4stSpNoYL47af4U1kO6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b328f9398f71f2d71f6780897aa0e99d84038745c6ba96e6017103975e53f79","last_reissued_at":"2026-07-05T11:12:40.602955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:40.602955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24040","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":"2026-07-05T11:12:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oZRIwMyXW+xhehSvvmdsspReaxFBlpLXbJQb+2pnJjjogrscSEhKPVjKKtbSIZadVd1O+BQ/VHy9tFZj71GMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:42:52.429675Z"},"content_sha256":"d1a08fc413c112bed4ad34896ef6d3d8032e26864b3fab136044936a3e7edf3a","schema_version":"1.0","event_id":"sha256:d1a08fc413c112bed4ad34896ef6d3d8032e26864b3fab136044936a3e7edf3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NMZI7E4Y64PS24PWPAEJPKQOTH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ariel D. Stern, Haoran Zhang, Hyewon Jeong, Isha Puri, Kumail Alhamoud, Marzyeh Ghassemi, Mike Schaekermann, Philip Torr, Yuexing Hao","submitted_at":"2025-05-29T22:23:48Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable performance on various medical question-answering (QA) benchmarks, including standardized medical exams. However, correct answers alone do not ensure correct logic, and models may reach accurate conclusions through flawed processes. In this study, we introduce the MedPAIR (Medical Dataset Comparing Physicians and AI Relevance Estimation and Question Answering) dataset to evaluate how physician trainees and LLMs prioritize relevant information when answering QA questions. We obtain annotations on 1,300 QA pairs from 36 physician trainees"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24040","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/2505.24040/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":"2026-07-05T11:12:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1KSfElpVfZadLyY7dYeJ2aY0+y04e87nVBRUs/vmYzdKrriqmIBfINReVy8aAyMnkuaehDrzhqovLYm1WjpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:42:52.430195Z"},"content_sha256":"2cffb021c5b7705b5c2b83478943b502d7ca771da6218656ac4ad6d6d754ea16","schema_version":"1.0","event_id":"sha256:2cffb021c5b7705b5c2b83478943b502d7ca771da6218656ac4ad6d6d754ea16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NMZI7E4Y64PS24PWPAEJPKQOTH/bundle.json","state_url":"https://pith.science/pith/NMZI7E4Y64PS24PWPAEJPKQOTH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NMZI7E4Y64PS24PWPAEJPKQOTH/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":"2026-08-09T11:42:52Z","links":{"resolver":"https://pith.science/pith/NMZI7E4Y64PS24PWPAEJPKQOTH","bundle":"https://pith.science/pith/NMZI7E4Y64PS24PWPAEJPKQOTH/bundle.json","state":"https://pith.science/pith/NMZI7E4Y64PS24PWPAEJPKQOTH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NMZI7E4Y64PS24PWPAEJPKQOTH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NMZI7E4Y64PS24PWPAEJPKQOTH","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":"bbb27522825ed9cf193f0d44f7052185ec086dfb1ae478589e950e1485576b84","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T22:23:48Z","title_canon_sha256":"8fa4aeb37fc2a4ba28f21c0a35750efc4faa7f0f8670b7fa9f495bcc1aadd93d"},"schema_version":"1.0","source":{"id":"2505.24040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24040","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24040v1","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24040","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"pith_short_12","alias_value":"NMZI7E4Y64PS","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"pith_short_16","alias_value":"NMZI7E4Y64PS24PW","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"pith_short_8","alias_value":"NMZI7E4Y","created_at":"2026-07-05T11:12:40Z"}],"graph_snapshots":[{"event_id":"sha256:2cffb021c5b7705b5c2b83478943b502d7ca771da6218656ac4ad6d6d754ea16","target":"graph","created_at":"2026-07-05T11:12:40Z","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/2505.24040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable performance on various medical question-answering (QA) benchmarks, including standardized medical exams. However, correct answers alone do not ensure correct logic, and models may reach accurate conclusions through flawed processes. In this study, we introduce the MedPAIR (Medical Dataset Comparing Physicians and AI Relevance Estimation and Question Answering) dataset to evaluate how physician trainees and LLMs prioritize relevant information when answering QA questions. We obtain annotations on 1,300 QA pairs from 36 physician trainees","authors_text":"Ariel D. Stern, Haoran Zhang, Hyewon Jeong, Isha Puri, Kumail Alhamoud, Marzyeh Ghassemi, Mike Schaekermann, Philip Torr, Yuexing Hao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T22:23:48Z","title":"MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24040","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:d1a08fc413c112bed4ad34896ef6d3d8032e26864b3fab136044936a3e7edf3a","target":"record","created_at":"2026-07-05T11:12:40Z","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":"bbb27522825ed9cf193f0d44f7052185ec086dfb1ae478589e950e1485576b84","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T22:23:48Z","title_canon_sha256":"8fa4aeb37fc2a4ba28f21c0a35750efc4faa7f0f8670b7fa9f495bcc1aadd93d"},"schema_version":"1.0","source":{"id":"2505.24040","kind":"arxiv","version":1}},"canonical_sha256":"6b328f9398f71f2d71f6780897aa0e99d84038745c6ba96e6017103975e53f79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b328f9398f71f2d71f6780897aa0e99d84038745c6ba96e6017103975e53f79","first_computed_at":"2026-07-05T11:12:40.602955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:40.602955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GdWW2FoWPmlbATnmAYbavc++uZ+0iTagmxfBVFRqcbwfZMRxUNXEhRxizqDzk2rdH4stSpNoYL47af4U1kO6Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:40.603502Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1a08fc413c112bed4ad34896ef6d3d8032e26864b3fab136044936a3e7edf3a","sha256:2cffb021c5b7705b5c2b83478943b502d7ca771da6218656ac4ad6d6d754ea16"],"state_sha256":"4f979dc2cad3f6b7b870799e9d43d55c83688160dc66dee6f4a0280f55debb23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TALwuUWv1L9tvFNAlPa9pNSNfpSQiT8MwCJYy/XO0W3aUpiaPJ9UublzRA5WoZkY2D2I88ks6Y61DzOXXX1XAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:42:52.435341Z","bundle_sha256":"e61e3f0429189ffd0169f2199710c2db3f0d487deafa0b7205584aa1948534ad"}}