{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:J3RPELJZGNSG5KINHKSNGNPYUW","short_pith_number":"pith:J3RPELJZ","canonical_record":{"source":{"id":"2305.07340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T09:37:13Z","cross_cats_sorted":[],"title_canon_sha256":"fd9681a81ceb3a184ea161956654d2d2cca383105a9d1fc1a26e91c9592f34d9","abstract_canon_sha256":"135e48559471d3e180433d02c5e60089bff7565139fa295ee10ca9cfe3e9fddf"},"schema_version":"1.0"},"canonical_sha256":"4ee2f22d3933646ea90d3aa4d335f8a5bbb992f2a107c2e97c1a112354dfd367","source":{"kind":"arxiv","id":"2305.07340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07340","created_at":"2026-07-05T06:09:34Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07340v1","created_at":"2026-07-05T06:09:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07340","created_at":"2026-07-05T06:09:34Z"},{"alias_kind":"pith_short_12","alias_value":"J3RPELJZGNSG","created_at":"2026-07-05T06:09:34Z"},{"alias_kind":"pith_short_16","alias_value":"J3RPELJZGNSG5KIN","created_at":"2026-07-05T06:09:34Z"},{"alias_kind":"pith_short_8","alias_value":"J3RPELJZ","created_at":"2026-07-05T06:09:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:J3RPELJZGNSG5KINHKSNGNPYUW","target":"record","payload":{"canonical_record":{"source":{"id":"2305.07340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T09:37:13Z","cross_cats_sorted":[],"title_canon_sha256":"fd9681a81ceb3a184ea161956654d2d2cca383105a9d1fc1a26e91c9592f34d9","abstract_canon_sha256":"135e48559471d3e180433d02c5e60089bff7565139fa295ee10ca9cfe3e9fddf"},"schema_version":"1.0"},"canonical_sha256":"4ee2f22d3933646ea90d3aa4d335f8a5bbb992f2a107c2e97c1a112354dfd367","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:34.324994Z","signature_b64":"toyfcnXynFa9qNaOgUST2pRygUpWtLCUFEC4bKSAZ96E0WP+V+aLsFbQArkmvoxZx7GcoI7flTnQQnjL18hmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ee2f22d3933646ea90d3aa4d335f8a5bbb992f2a107c2e97c1a112354dfd367","last_reissued_at":"2026-07-05T06:09:34.324555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:34.324555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.07340","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":"2026-07-05T06:09:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pkRHgw4QGjVe9yOfk3AoL8hyGssHJNE3ZjK2yJbKwM4VmvJ2aa+KMII5335qB1Tew3vNLMyRkFXMH8t5vPpNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:38:18.098746Z"},"content_sha256":"be29b8d910861e42cb8172f009f41e1bb3408cb517ace67eb2ee992ddd7e0b5b","schema_version":"1.0","event_id":"sha256:be29b8d910861e42cb8172f009f41e1bb3408cb517ace67eb2ee992ddd7e0b5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:J3RPELJZGNSG5KINHKSNGNPYUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MedGPTEval: A Dataset and Benchmark to Evaluate Responses of Large Language Models in Medicine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bilin Liang, Huan Song, Jiali Pang, Jie Xu, Jinru Ding, Kang Li, Lingrui Yang, Lu Lu, Sen Yang, Shaoting Zhang, Xiaoming Shi, Xin Sun, Xinwei Peng","submitted_at":"2023-05-12T09:37:13Z","abstract_excerpt":"METHODS: First, a set of evaluation criteria is designed based on a comprehensive literature review. Second, existing candidate criteria are optimized for using a Delphi method by five experts in medicine and engineering. Third, three clinical experts design a set of medical datasets to interact with LLMs. Finally, benchmarking experiments are conducted on the datasets. The responses generated by chatbots based on LLMs are recorded for blind evaluations by five licensed medical experts. RESULTS: The obtained evaluation criteria cover medical professional capabilities, social comprehensive capa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07340","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/2305.07340/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":"2026-07-05T06:09:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XeHTzdbYNBUP5bEu1RdGeB1gF97AlXzAG53oobbdoyJBGRS1ak9+WlcmTlhuo/ZkPtm52BfWE2yZZq+T37zfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:38:18.099378Z"},"content_sha256":"c09d24598467bece8a514ee3b5d1baf4c9fed8507c27ccde2da89f9307fbb852","schema_version":"1.0","event_id":"sha256:c09d24598467bece8a514ee3b5d1baf4c9fed8507c27ccde2da89f9307fbb852"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J3RPELJZGNSG5KINHKSNGNPYUW/bundle.json","state_url":"https://pith.science/pith/J3RPELJZGNSG5KINHKSNGNPYUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J3RPELJZGNSG5KINHKSNGNPYUW/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":"2026-08-17T02:38:18Z","links":{"resolver":"https://pith.science/pith/J3RPELJZGNSG5KINHKSNGNPYUW","bundle":"https://pith.science/pith/J3RPELJZGNSG5KINHKSNGNPYUW/bundle.json","state":"https://pith.science/pith/J3RPELJZGNSG5KINHKSNGNPYUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J3RPELJZGNSG5KINHKSNGNPYUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J3RPELJZGNSG5KINHKSNGNPYUW","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":"135e48559471d3e180433d02c5e60089bff7565139fa295ee10ca9cfe3e9fddf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T09:37:13Z","title_canon_sha256":"fd9681a81ceb3a184ea161956654d2d2cca383105a9d1fc1a26e91c9592f34d9"},"schema_version":"1.0","source":{"id":"2305.07340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.07340","created_at":"2026-07-05T06:09:34Z"},{"alias_kind":"arxiv_version","alias_value":"2305.07340v1","created_at":"2026-07-05T06:09:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07340","created_at":"2026-07-05T06:09:34Z"},{"alias_kind":"pith_short_12","alias_value":"J3RPELJZGNSG","created_at":"2026-07-05T06:09:34Z"},{"alias_kind":"pith_short_16","alias_value":"J3RPELJZGNSG5KIN","created_at":"2026-07-05T06:09:34Z"},{"alias_kind":"pith_short_8","alias_value":"J3RPELJZ","created_at":"2026-07-05T06:09:34Z"}],"graph_snapshots":[{"event_id":"sha256:c09d24598467bece8a514ee3b5d1baf4c9fed8507c27ccde2da89f9307fbb852","target":"graph","created_at":"2026-07-05T06:09:34Z","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/2305.07340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"METHODS: First, a set of evaluation criteria is designed based on a comprehensive literature review. Second, existing candidate criteria are optimized for using a Delphi method by five experts in medicine and engineering. Third, three clinical experts design a set of medical datasets to interact with LLMs. Finally, benchmarking experiments are conducted on the datasets. The responses generated by chatbots based on LLMs are recorded for blind evaluations by five licensed medical experts. RESULTS: The obtained evaluation criteria cover medical professional capabilities, social comprehensive capa","authors_text":"Bilin Liang, Huan Song, Jiali Pang, Jie Xu, Jinru Ding, Kang Li, Lingrui Yang, Lu Lu, Sen Yang, Shaoting Zhang, Xiaoming Shi, Xin Sun, Xinwei Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T09:37:13Z","title":"MedGPTEval: A Dataset and Benchmark to Evaluate Responses of Large Language Models in Medicine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07340","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:be29b8d910861e42cb8172f009f41e1bb3408cb517ace67eb2ee992ddd7e0b5b","target":"record","created_at":"2026-07-05T06:09:34Z","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":"135e48559471d3e180433d02c5e60089bff7565139fa295ee10ca9cfe3e9fddf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T09:37:13Z","title_canon_sha256":"fd9681a81ceb3a184ea161956654d2d2cca383105a9d1fc1a26e91c9592f34d9"},"schema_version":"1.0","source":{"id":"2305.07340","kind":"arxiv","version":1}},"canonical_sha256":"4ee2f22d3933646ea90d3aa4d335f8a5bbb992f2a107c2e97c1a112354dfd367","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ee2f22d3933646ea90d3aa4d335f8a5bbb992f2a107c2e97c1a112354dfd367","first_computed_at":"2026-07-05T06:09:34.324555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:34.324555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"toyfcnXynFa9qNaOgUST2pRygUpWtLCUFEC4bKSAZ96E0WP+V+aLsFbQArkmvoxZx7GcoI7flTnQQnjL18hmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:34.324994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.07340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be29b8d910861e42cb8172f009f41e1bb3408cb517ace67eb2ee992ddd7e0b5b","sha256:c09d24598467bece8a514ee3b5d1baf4c9fed8507c27ccde2da89f9307fbb852"],"state_sha256":"db50a091449d83a56e0384244ecd0bbb0925262b07e79c484d4bc533a254c918"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MovS6yxSQ3S4aZrc/eD08SnB0iXRcvSeWgNA5Mv8ixtBg9HKrXX5kPEpJxvWeaGVwsVbq8KBHWe0ip0GDx5jCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T02:38:18.104917Z","bundle_sha256":"d37da43a7305b6a94444b77ae9407714d1e865925c484cd783e7bc523cd1fa24"}}