{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2R45YI6PH7K7ACTPA4YBYGTNEH","short_pith_number":"pith:2R45YI6P","canonical_record":{"source":{"id":"2507.08916","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T16:09:25Z","cross_cats_sorted":[],"title_canon_sha256":"259a098098dd30764b5addd68a915d5b282577043f4fdf3f1dc4ebd7fbd0703b","abstract_canon_sha256":"4a0b281b3f12f7760c35bdffb39b8336c678a3b4ddebbcef6c5135df0c43b911"},"schema_version":"1.0"},"canonical_sha256":"d479dc23cf3fd5f00a6f07301c1a6d21f31ab131904ef4b7ad718af1b3a5a7a4","source":{"kind":"arxiv","id":"2507.08916","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08916","created_at":"2026-07-05T11:36:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08916v1","created_at":"2026-07-05T11:36:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08916","created_at":"2026-07-05T11:36:00Z"},{"alias_kind":"pith_short_12","alias_value":"2R45YI6PH7K7","created_at":"2026-07-05T11:36:00Z"},{"alias_kind":"pith_short_16","alias_value":"2R45YI6PH7K7ACTP","created_at":"2026-07-05T11:36:00Z"},{"alias_kind":"pith_short_8","alias_value":"2R45YI6P","created_at":"2026-07-05T11:36:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2R45YI6PH7K7ACTPA4YBYGTNEH","target":"record","payload":{"canonical_record":{"source":{"id":"2507.08916","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T16:09:25Z","cross_cats_sorted":[],"title_canon_sha256":"259a098098dd30764b5addd68a915d5b282577043f4fdf3f1dc4ebd7fbd0703b","abstract_canon_sha256":"4a0b281b3f12f7760c35bdffb39b8336c678a3b4ddebbcef6c5135df0c43b911"},"schema_version":"1.0"},"canonical_sha256":"d479dc23cf3fd5f00a6f07301c1a6d21f31ab131904ef4b7ad718af1b3a5a7a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:00.669540Z","signature_b64":"XvgdU+y27Pf/3qn1p0pQY7FNFKN9lqoi33IY+H6CChdb1GlBwV6ZT47dvu0UWHLhTlaBSisFqQcq8Vt8bFv9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d479dc23cf3fd5f00a6f07301c1a6d21f31ab131904ef4b7ad718af1b3a5a7a4","last_reissued_at":"2026-07-05T11:36:00.669056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:00.669056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.08916","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":"2026-07-05T11:36:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bpcylr2guFeB4+chSOz0VCY6l3pLNWCQOHH8iTe/bE/MHFAHfH7fX6qVNieGmmowtI41hW5VJK+VxDCA+TzDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:24:58.517268Z"},"content_sha256":"c90ae092e73663f5e2b2393b49d1acc15e6eeb88ebd7e651c33b4697dc6255ca","schema_version":"1.0","event_id":"sha256:c90ae092e73663f5e2b2393b49d1acc15e6eeb88ebd7e651c33b4697dc6255ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2R45YI6PH7K7ACTPA4YBYGTNEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating LLMs in Medicine: A Call for Rigor, Transparency","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Nagori, Mahmoud Alwakeel, Rishikesan Kamaleswaran, Vijay Krishnamoorthy","submitted_at":"2025-07-11T16:09:25Z","abstract_excerpt":"Objectives: To evaluate the current limitations of large language models (LLMs) in medical question answering, focusing on the quality of datasets used for their evaluation. Materials and Methods: Widely-used benchmark datasets, including MedQA, MedMCQA, PubMedQA, and MMLU, were reviewed for their rigor, transparency, and relevance to clinical scenarios. Alternatives, such as challenge questions in medical journals, were also analyzed to identify their potential as unbiased evaluation tools. Results: Most existing datasets lack clinical realism, transparency, and robust validation processes. P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08916","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/2507.08916/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":"2026-07-05T11:36:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QayUMuszEOyGXbYkBORkrUPm8xY0gicnKDgQC1QlF228h7RkLGssH/iYyEzE/2SF8IoB929G0BDdPXB8x0l8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:24:58.517762Z"},"content_sha256":"c0287abd4ca3d6001f4683515c9f7f88589cc02c7c97944c1ea823e4561841af","schema_version":"1.0","event_id":"sha256:c0287abd4ca3d6001f4683515c9f7f88589cc02c7c97944c1ea823e4561841af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2R45YI6PH7K7ACTPA4YBYGTNEH/bundle.json","state_url":"https://pith.science/pith/2R45YI6PH7K7ACTPA4YBYGTNEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2R45YI6PH7K7ACTPA4YBYGTNEH/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":"2026-07-06T20:24:58Z","links":{"resolver":"https://pith.science/pith/2R45YI6PH7K7ACTPA4YBYGTNEH","bundle":"https://pith.science/pith/2R45YI6PH7K7ACTPA4YBYGTNEH/bundle.json","state":"https://pith.science/pith/2R45YI6PH7K7ACTPA4YBYGTNEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2R45YI6PH7K7ACTPA4YBYGTNEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2R45YI6PH7K7ACTPA4YBYGTNEH","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":"4a0b281b3f12f7760c35bdffb39b8336c678a3b4ddebbcef6c5135df0c43b911","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T16:09:25Z","title_canon_sha256":"259a098098dd30764b5addd68a915d5b282577043f4fdf3f1dc4ebd7fbd0703b"},"schema_version":"1.0","source":{"id":"2507.08916","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08916","created_at":"2026-07-05T11:36:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08916v1","created_at":"2026-07-05T11:36:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08916","created_at":"2026-07-05T11:36:00Z"},{"alias_kind":"pith_short_12","alias_value":"2R45YI6PH7K7","created_at":"2026-07-05T11:36:00Z"},{"alias_kind":"pith_short_16","alias_value":"2R45YI6PH7K7ACTP","created_at":"2026-07-05T11:36:00Z"},{"alias_kind":"pith_short_8","alias_value":"2R45YI6P","created_at":"2026-07-05T11:36:00Z"}],"graph_snapshots":[{"event_id":"sha256:c0287abd4ca3d6001f4683515c9f7f88589cc02c7c97944c1ea823e4561841af","target":"graph","created_at":"2026-07-05T11:36:00Z","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/2507.08916/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Objectives: To evaluate the current limitations of large language models (LLMs) in medical question answering, focusing on the quality of datasets used for their evaluation. Materials and Methods: Widely-used benchmark datasets, including MedQA, MedMCQA, PubMedQA, and MMLU, were reviewed for their rigor, transparency, and relevance to clinical scenarios. Alternatives, such as challenge questions in medical journals, were also analyzed to identify their potential as unbiased evaluation tools. Results: Most existing datasets lack clinical realism, transparency, and robust validation processes. P","authors_text":"Aditya Nagori, Mahmoud Alwakeel, Rishikesan Kamaleswaran, Vijay Krishnamoorthy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T16:09:25Z","title":"Evaluating LLMs in Medicine: A Call for Rigor, Transparency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08916","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:c90ae092e73663f5e2b2393b49d1acc15e6eeb88ebd7e651c33b4697dc6255ca","target":"record","created_at":"2026-07-05T11:36:00Z","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":"4a0b281b3f12f7760c35bdffb39b8336c678a3b4ddebbcef6c5135df0c43b911","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-11T16:09:25Z","title_canon_sha256":"259a098098dd30764b5addd68a915d5b282577043f4fdf3f1dc4ebd7fbd0703b"},"schema_version":"1.0","source":{"id":"2507.08916","kind":"arxiv","version":1}},"canonical_sha256":"d479dc23cf3fd5f00a6f07301c1a6d21f31ab131904ef4b7ad718af1b3a5a7a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d479dc23cf3fd5f00a6f07301c1a6d21f31ab131904ef4b7ad718af1b3a5a7a4","first_computed_at":"2026-07-05T11:36:00.669056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:00.669056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XvgdU+y27Pf/3qn1p0pQY7FNFKN9lqoi33IY+H6CChdb1GlBwV6ZT47dvu0UWHLhTlaBSisFqQcq8Vt8bFv9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:00.669540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08916","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c90ae092e73663f5e2b2393b49d1acc15e6eeb88ebd7e651c33b4697dc6255ca","sha256:c0287abd4ca3d6001f4683515c9f7f88589cc02c7c97944c1ea823e4561841af"],"state_sha256":"63bcaed08314ce89dcc7d2c380d10773f21757bfd3d1d6c90d40b539e61ff0cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pc1W9gTrxjh/eT+/VmBGh+QL3AMkfHoUsY2uo/P/2vfQBiAo2DByUrWdwyE9OXsDFhKs4aoW4aGhbqhNLlR/Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:24:58.519727Z","bundle_sha256":"d6d4a73d174c940764aef184c026b14d695a3e4d10798ea2ebfee3357c6227c9"}}