{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PB6PW25J5HEJLDLQYMIJIFAOHW","short_pith_number":"pith:PB6PW25J","canonical_record":{"source":{"id":"2407.10990","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T02:25:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35dc56236c4970757217149ab4c5abd551d9858caa744bb096042be9be5aa7e0","abstract_canon_sha256":"77e4ae7e232f04e3200fe748d8499d076dc5fa76c0a92e945dae30e9ce4e41f0"},"schema_version":"1.0"},"canonical_sha256":"787cfb6ba9e9c8958d70c31094140e3d98a97e29e66bf27427258c93f20fcc5a","source":{"kind":"arxiv","id":"2407.10990","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10990","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10990v1","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10990","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"PB6PW25J5HEJ","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"pith_short_16","alias_value":"PB6PW25J5HEJLDLQ","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"pith_short_8","alias_value":"PB6PW25J","created_at":"2026-07-05T08:44:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PB6PW25J5HEJLDLQYMIJIFAOHW","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10990","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T02:25:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35dc56236c4970757217149ab4c5abd551d9858caa744bb096042be9be5aa7e0","abstract_canon_sha256":"77e4ae7e232f04e3200fe748d8499d076dc5fa76c0a92e945dae30e9ce4e41f0"},"schema_version":"1.0"},"canonical_sha256":"787cfb6ba9e9c8958d70c31094140e3d98a97e29e66bf27427258c93f20fcc5a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:16.688460Z","signature_b64":"l2emzvA9uljA/u/IdPQ+0zs/KdsX9qAWnMs/wkOpp/Fn+6B0pyDFPMPXCZVzj2Fc1G4vao14sJkPrIP+AGAwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"787cfb6ba9e9c8958d70c31094140e3d98a97e29e66bf27427258c93f20fcc5a","last_reissued_at":"2026-07-05T08:44:16.687894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:16.687894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10990","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":"2026-07-05T08:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0rbne1AkOicOjnhhpeqDhleRfwmJPcDlNCWQLIRlRe4F6slmUj0ush5YzmTMP7xRKpbcqyN+CmAqFRx3Xp19Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:44:45.662526Z"},"content_sha256":"f6b1abb24fbdc774dc18b719fb2803c2edca34206742162d94a1425c8520626f","schema_version":"1.0","event_id":"sha256:f6b1abb24fbdc774dc18b719fb2803c2edca34206742162d94a1425c8520626f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PB6PW25J5HEJLDLQYMIJIFAOHW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Haitao Song, Haofen Wang, Jie Xu, Jinru Ding, Kang Li, Lifeng Zhu, Mianxin Liu, Pengfei Liu, Shanshan Wang, Shaoting Zhang, Tong Ruan, Weiguo Hu, Xiaofan Zhang, Xiaoming Shi, Xiaoyang Li, Xin Sun, Xuanjing Huang, Zhian Bai","submitted_at":"2024-06-24T02:25:48Z","abstract_excerpt":"Ensuring the general efficacy and goodness for human beings from medical large language models (LLM) before real-world deployment is crucial. However, a widely accepted and accessible evaluation process for medical LLM, especially in the Chinese context, remains to be established. In this work, we introduce \"MedBench\", a comprehensive, standardized, and reliable benchmarking system for Chinese medical LLM. First, MedBench assembles the currently largest evaluation dataset (300,901 questions) to cover 43 clinical specialties and performs multi-facet evaluation on medical LLM. Second, MedBench p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10990","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/2407.10990/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":"2026-07-05T08:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NwRx4u09oDSHBqRp5wAHUOCklErue56Kdv9z2R6QoUFledSH0zoKNnt4ATYgu2ONjsSa+goNGywT+bjL/JrSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:44:45.663438Z"},"content_sha256":"4819aa6aad12f948598c3ff0105b10d0866e6e6c128d132e7b7680950134ed6f","schema_version":"1.0","event_id":"sha256:4819aa6aad12f948598c3ff0105b10d0866e6e6c128d132e7b7680950134ed6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PB6PW25J5HEJLDLQYMIJIFAOHW/bundle.json","state_url":"https://pith.science/pith/PB6PW25J5HEJLDLQYMIJIFAOHW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PB6PW25J5HEJLDLQYMIJIFAOHW/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":"2026-08-15T19:44:45Z","links":{"resolver":"https://pith.science/pith/PB6PW25J5HEJLDLQYMIJIFAOHW","bundle":"https://pith.science/pith/PB6PW25J5HEJLDLQYMIJIFAOHW/bundle.json","state":"https://pith.science/pith/PB6PW25J5HEJLDLQYMIJIFAOHW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PB6PW25J5HEJLDLQYMIJIFAOHW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PB6PW25J5HEJLDLQYMIJIFAOHW","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":"77e4ae7e232f04e3200fe748d8499d076dc5fa76c0a92e945dae30e9ce4e41f0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T02:25:48Z","title_canon_sha256":"35dc56236c4970757217149ab4c5abd551d9858caa744bb096042be9be5aa7e0"},"schema_version":"1.0","source":{"id":"2407.10990","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10990","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10990v1","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10990","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"PB6PW25J5HEJ","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"pith_short_16","alias_value":"PB6PW25J5HEJLDLQ","created_at":"2026-07-05T08:44:16Z"},{"alias_kind":"pith_short_8","alias_value":"PB6PW25J","created_at":"2026-07-05T08:44:16Z"}],"graph_snapshots":[{"event_id":"sha256:4819aa6aad12f948598c3ff0105b10d0866e6e6c128d132e7b7680950134ed6f","target":"graph","created_at":"2026-07-05T08:44:16Z","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/2407.10990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring the general efficacy and goodness for human beings from medical large language models (LLM) before real-world deployment is crucial. However, a widely accepted and accessible evaluation process for medical LLM, especially in the Chinese context, remains to be established. In this work, we introduce \"MedBench\", a comprehensive, standardized, and reliable benchmarking system for Chinese medical LLM. First, MedBench assembles the currently largest evaluation dataset (300,901 questions) to cover 43 clinical specialties and performs multi-facet evaluation on medical LLM. Second, MedBench p","authors_text":"Benyou Wang, Haitao Song, Haofen Wang, Jie Xu, Jinru Ding, Kang Li, Lifeng Zhu, Mianxin Liu, Pengfei Liu, Shanshan Wang, Shaoting Zhang, Tong Ruan, Weiguo Hu, Xiaofan Zhang, Xiaoming Shi, Xiaoyang Li, Xin Sun, Xuanjing Huang, Zhian Bai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T02:25:48Z","title":"MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10990","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:f6b1abb24fbdc774dc18b719fb2803c2edca34206742162d94a1425c8520626f","target":"record","created_at":"2026-07-05T08:44:16Z","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":"77e4ae7e232f04e3200fe748d8499d076dc5fa76c0a92e945dae30e9ce4e41f0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T02:25:48Z","title_canon_sha256":"35dc56236c4970757217149ab4c5abd551d9858caa744bb096042be9be5aa7e0"},"schema_version":"1.0","source":{"id":"2407.10990","kind":"arxiv","version":1}},"canonical_sha256":"787cfb6ba9e9c8958d70c31094140e3d98a97e29e66bf27427258c93f20fcc5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"787cfb6ba9e9c8958d70c31094140e3d98a97e29e66bf27427258c93f20fcc5a","first_computed_at":"2026-07-05T08:44:16.687894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:16.687894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l2emzvA9uljA/u/IdPQ+0zs/KdsX9qAWnMs/wkOpp/Fn+6B0pyDFPMPXCZVzj2Fc1G4vao14sJkPrIP+AGAwCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:16.688460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10990","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6b1abb24fbdc774dc18b719fb2803c2edca34206742162d94a1425c8520626f","sha256:4819aa6aad12f948598c3ff0105b10d0866e6e6c128d132e7b7680950134ed6f"],"state_sha256":"30498b3db659d38b8bc13475549f1a4213ed2214ad9fadaf576d945e8b5d3c87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dw06imL7oavKZLapIN4Lewb0G7hdZRbEndk1a6btlQjfedMFNKoeePN0EpLAtZhZH/zVm7sGDDMsqxpqjbgmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:44:45.671323Z","bundle_sha256":"ced4503a518935e8cd214ef5837c25712c1d9a4cc550c6ad3b0d35a2025e09b1"}}