{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HFOM2IKPYPXZLR6PYABUHN7IR7","short_pith_number":"pith:HFOM2IKP","canonical_record":{"source":{"id":"2506.04078","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T15:43:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a74da155a1278ac41f6affb9be3df976d1897e0740354fcc7634d1ce08b9b4bd","abstract_canon_sha256":"b4b681ea9e0af73a7b8e3a0c788ed5068cebe823538c2696205d7b3b554f8afe"},"schema_version":"1.0"},"canonical_sha256":"395ccd214fc3ef95c7cfc00343b7e88fd4cb2afc029a60c55fd3951dcf9c0c45","source":{"kind":"arxiv","id":"2506.04078","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04078","created_at":"2026-07-05T12:02:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04078v3","created_at":"2026-07-05T12:02:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04078","created_at":"2026-07-05T12:02:02Z"},{"alias_kind":"pith_short_12","alias_value":"HFOM2IKPYPXZ","created_at":"2026-07-05T12:02:02Z"},{"alias_kind":"pith_short_16","alias_value":"HFOM2IKPYPXZLR6P","created_at":"2026-07-05T12:02:02Z"},{"alias_kind":"pith_short_8","alias_value":"HFOM2IKP","created_at":"2026-07-05T12:02:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HFOM2IKPYPXZLR6PYABUHN7IR7","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04078","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T15:43:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a74da155a1278ac41f6affb9be3df976d1897e0740354fcc7634d1ce08b9b4bd","abstract_canon_sha256":"b4b681ea9e0af73a7b8e3a0c788ed5068cebe823538c2696205d7b3b554f8afe"},"schema_version":"1.0"},"canonical_sha256":"395ccd214fc3ef95c7cfc00343b7e88fd4cb2afc029a60c55fd3951dcf9c0c45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:02.366521Z","signature_b64":"SLn+y/tP/kZmfALMYtBvZOZbOKjmTeTaHmYscoTySP4HZU/eOj87LOFOA2g3M85+GiLXHUwT2TMj8QSNTzCbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"395ccd214fc3ef95c7cfc00343b7e88fd4cb2afc029a60c55fd3951dcf9c0c45","last_reissued_at":"2026-07-05T12:02:02.365994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:02.365994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04078","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Xv5mEZKmQNg3m6+kaP2lZdKF0WXML3LjfcZHsrnXbihZeFX48iJ2svJ3SvpXCWGDaQGujy70dQQJpisYClhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:42:55.820881Z"},"content_sha256":"b80dcb2783402ae314c6014dc109cb001dd133a928ba8075037670dd5dd2cc7c","schema_version":"1.0","event_id":"sha256:b80dcb2783402ae314c6014dc109cb001dd133a928ba8075037670dd5dd2cc7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HFOM2IKPYPXZLR6PYABUHN7IR7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Binze Hu, Changhao Jiang, Chenhao Huang, Huayu Sha, Jingqi Tong, Mingxu Chai, Ming Zhang, Qi Zhang, Shichun Liu, Shihan Dou, Tao Gui, Xuanjing Huang, Yuhui Wang, Yujiong Shen, Zelin Li, Zhiheng Xi","submitted_at":"2025-06-04T15:43:14Z","abstract_excerpt":"Evaluating large language models (LLMs) in medicine is crucial because medical applications require high accuracy with little room for error. Current medical benchmarks have three main types: medical exam-based, comprehensive medical, and specialized assessments. However, these benchmarks have limitations in question design (mostly multiple-choice), data sources (often not derived from real clinical scenarios), and evaluation methods (poor assessment of complex reasoning). To address these issues, we present LLMEval-Med, a new benchmark covering five core medical areas, including 2,996 questio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04078","kind":"arxiv","version":3},"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/2506.04078/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":"2026-07-05T12:02:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/E0VDAOPOiDsasn1wmfgBzhkYpd4ZTJmJ5Umk8wJSPR2/bMQBZ2NnFYu94A1MzPRZVafVaa1b9FiK+Cz4JQrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:42:55.821409Z"},"content_sha256":"cdfc6f3f6192d185512837a99c4ed0500246512f4ecf95e7649e2c8776864177","schema_version":"1.0","event_id":"sha256:cdfc6f3f6192d185512837a99c4ed0500246512f4ecf95e7649e2c8776864177"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HFOM2IKPYPXZLR6PYABUHN7IR7/bundle.json","state_url":"https://pith.science/pith/HFOM2IKPYPXZLR6PYABUHN7IR7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HFOM2IKPYPXZLR6PYABUHN7IR7/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":"2026-08-01T05:42:55Z","links":{"resolver":"https://pith.science/pith/HFOM2IKPYPXZLR6PYABUHN7IR7","bundle":"https://pith.science/pith/HFOM2IKPYPXZLR6PYABUHN7IR7/bundle.json","state":"https://pith.science/pith/HFOM2IKPYPXZLR6PYABUHN7IR7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HFOM2IKPYPXZLR6PYABUHN7IR7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HFOM2IKPYPXZLR6PYABUHN7IR7","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":"b4b681ea9e0af73a7b8e3a0c788ed5068cebe823538c2696205d7b3b554f8afe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T15:43:14Z","title_canon_sha256":"a74da155a1278ac41f6affb9be3df976d1897e0740354fcc7634d1ce08b9b4bd"},"schema_version":"1.0","source":{"id":"2506.04078","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04078","created_at":"2026-07-05T12:02:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04078v3","created_at":"2026-07-05T12:02:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04078","created_at":"2026-07-05T12:02:02Z"},{"alias_kind":"pith_short_12","alias_value":"HFOM2IKPYPXZ","created_at":"2026-07-05T12:02:02Z"},{"alias_kind":"pith_short_16","alias_value":"HFOM2IKPYPXZLR6P","created_at":"2026-07-05T12:02:02Z"},{"alias_kind":"pith_short_8","alias_value":"HFOM2IKP","created_at":"2026-07-05T12:02:02Z"}],"graph_snapshots":[{"event_id":"sha256:cdfc6f3f6192d185512837a99c4ed0500246512f4ecf95e7649e2c8776864177","target":"graph","created_at":"2026-07-05T12:02:02Z","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/2506.04078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language models (LLMs) in medicine is crucial because medical applications require high accuracy with little room for error. Current medical benchmarks have three main types: medical exam-based, comprehensive medical, and specialized assessments. However, these benchmarks have limitations in question design (mostly multiple-choice), data sources (often not derived from real clinical scenarios), and evaluation methods (poor assessment of complex reasoning). To address these issues, we present LLMEval-Med, a new benchmark covering five core medical areas, including 2,996 questio","authors_text":"Binze Hu, Changhao Jiang, Chenhao Huang, Huayu Sha, Jingqi Tong, Mingxu Chai, Ming Zhang, Qi Zhang, Shichun Liu, Shihan Dou, Tao Gui, Xuanjing Huang, Yuhui Wang, Yujiong Shen, Zelin Li, Zhiheng Xi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T15:43:14Z","title":"LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04078","kind":"arxiv","version":3},"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:b80dcb2783402ae314c6014dc109cb001dd133a928ba8075037670dd5dd2cc7c","target":"record","created_at":"2026-07-05T12:02:02Z","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":"b4b681ea9e0af73a7b8e3a0c788ed5068cebe823538c2696205d7b3b554f8afe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T15:43:14Z","title_canon_sha256":"a74da155a1278ac41f6affb9be3df976d1897e0740354fcc7634d1ce08b9b4bd"},"schema_version":"1.0","source":{"id":"2506.04078","kind":"arxiv","version":3}},"canonical_sha256":"395ccd214fc3ef95c7cfc00343b7e88fd4cb2afc029a60c55fd3951dcf9c0c45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"395ccd214fc3ef95c7cfc00343b7e88fd4cb2afc029a60c55fd3951dcf9c0c45","first_computed_at":"2026-07-05T12:02:02.365994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:02.365994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SLn+y/tP/kZmfALMYtBvZOZbOKjmTeTaHmYscoTySP4HZU/eOj87LOFOA2g3M85+GiLXHUwT2TMj8QSNTzCbBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:02.366521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04078","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b80dcb2783402ae314c6014dc109cb001dd133a928ba8075037670dd5dd2cc7c","sha256:cdfc6f3f6192d185512837a99c4ed0500246512f4ecf95e7649e2c8776864177"],"state_sha256":"a1b8f6a04eeec24bd90d04dbf4bae8e7479f06a44fc9781b0c3a30a35fa53ad4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LSflHxOKWdc8YqgETUHCT1BJG8efBUtUu0JCrJdTYiDTTKgxtJZJ2BsQx5F8eLqQmcUoMSvXktCTs+HocW1TBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T05:42:55.826656Z","bundle_sha256":"3471b3c3d67d5f5d40e2d548738cd5ff5de1905a82ba8043a57a7062e10f786c"}}