{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X3EYE4L6QDXX5N5YOSDZMZOQI4","short_pith_number":"pith:X3EYE4L6","canonical_record":{"source":{"id":"2408.12547","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T17:01:34Z","cross_cats_sorted":[],"title_canon_sha256":"33966769003fc783e62dc432989be2f599aa4617c653d8a9e3d9ffe1ef58a2cd","abstract_canon_sha256":"9698fe5e80d1412d27ef3953dd197a16ff99a282f10bd85bb5d5d5c2e9ab8c54"},"schema_version":"1.0"},"canonical_sha256":"bec982717e80ef7eb7b874879665d0472d838cd8ae8ef5bfba19e33fcc241347","source":{"kind":"arxiv","id":"2408.12547","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12547","created_at":"2026-07-05T09:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12547v2","created_at":"2026-07-05T09:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12547","created_at":"2026-07-05T09:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"X3EYE4L6QDXX","created_at":"2026-07-05T09:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"X3EYE4L6QDXX5N5Y","created_at":"2026-07-05T09:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"X3EYE4L6","created_at":"2026-07-05T09:03:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X3EYE4L6QDXX5N5YOSDZMZOQI4","target":"record","payload":{"canonical_record":{"source":{"id":"2408.12547","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T17:01:34Z","cross_cats_sorted":[],"title_canon_sha256":"33966769003fc783e62dc432989be2f599aa4617c653d8a9e3d9ffe1ef58a2cd","abstract_canon_sha256":"9698fe5e80d1412d27ef3953dd197a16ff99a282f10bd85bb5d5d5c2e9ab8c54"},"schema_version":"1.0"},"canonical_sha256":"bec982717e80ef7eb7b874879665d0472d838cd8ae8ef5bfba19e33fcc241347","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:40.971179Z","signature_b64":"9YCeQOL7w1HEBiLTsnuz6Q84Y0zvSv/26/Hr8Jpb/G4JQWmn8fNCkdu8dLArE0Tpapd55SkBYN5AhQm67wSACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bec982717e80ef7eb7b874879665d0472d838cd8ae8ef5bfba19e33fcc241347","last_reissued_at":"2026-07-05T09:03:40.970706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:40.970706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.12547","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:03:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jUvAke4aPBnpNmHB6Q9or7stovF2pISAnOmum04LqiTFFVcLA5gFm5oD5GJnZGUMLRIRKGo+XQAzj8WQxL4SCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:00:55.104974Z"},"content_sha256":"ff56ba0a6c804d0ebb807e5b06af485329cdd1c29802a347e721e38e6bfe6ac7","schema_version":"1.0","event_id":"sha256:ff56ba0a6c804d0ebb807e5b06af485329cdd1c29802a347e721e38e6bfe6ac7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X3EYE4L6QDXX5N5YOSDZMZOQI4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Evaluating and Building Versatile Large Language Models for Medicine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaoyi Wu, Hongfei Gu, Jinxin Liu, Na Li, Pengcheng Qiu, Weidi Xie, Yanfeng Wang, Ya Zhang","submitted_at":"2024-08-22T17:01:34Z","abstract_excerpt":"In this study, we present MedS-Bench, a comprehensive benchmark designed to evaluate the performance of large language models (LLMs) in clinical contexts. Unlike existing benchmarks that focus on multiple-choice question answering, MedS-Bench spans 11 high-level clinical tasks, including clinical report summarization, treatment recommendations, diagnosis, named entity recognition, and medical concept explanation, among others. We evaluated six leading LLMs, e.g., MEDITRON, Mistral, InternLM 2, Llama 3, GPT-4, and Claude-3.5 using few-shot prompting, and found that even the most sophisticated m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12547","kind":"arxiv","version":2},"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/2408.12547/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":"2026-07-05T09:03:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bs4PjD7RzjVgA9D7kT0zWiztd/1d29Am2+Z3tR5mh/WQcINe2sXE5P369XKz7OmD3BKImgyY3X4al3IkeAEWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:00:55.107105Z"},"content_sha256":"7be31fc28f1ca2d211e7ee6826ec98da508b5560d614163c3daac4b81a1e1f32","schema_version":"1.0","event_id":"sha256:7be31fc28f1ca2d211e7ee6826ec98da508b5560d614163c3daac4b81a1e1f32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X3EYE4L6QDXX5N5YOSDZMZOQI4/bundle.json","state_url":"https://pith.science/pith/X3EYE4L6QDXX5N5YOSDZMZOQI4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X3EYE4L6QDXX5N5YOSDZMZOQI4/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":"2026-08-21T19:00:55Z","links":{"resolver":"https://pith.science/pith/X3EYE4L6QDXX5N5YOSDZMZOQI4","bundle":"https://pith.science/pith/X3EYE4L6QDXX5N5YOSDZMZOQI4/bundle.json","state":"https://pith.science/pith/X3EYE4L6QDXX5N5YOSDZMZOQI4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X3EYE4L6QDXX5N5YOSDZMZOQI4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X3EYE4L6QDXX5N5YOSDZMZOQI4","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":"9698fe5e80d1412d27ef3953dd197a16ff99a282f10bd85bb5d5d5c2e9ab8c54","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T17:01:34Z","title_canon_sha256":"33966769003fc783e62dc432989be2f599aa4617c653d8a9e3d9ffe1ef58a2cd"},"schema_version":"1.0","source":{"id":"2408.12547","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12547","created_at":"2026-07-05T09:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12547v2","created_at":"2026-07-05T09:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12547","created_at":"2026-07-05T09:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"X3EYE4L6QDXX","created_at":"2026-07-05T09:03:40Z"},{"alias_kind":"pith_short_16","alias_value":"X3EYE4L6QDXX5N5Y","created_at":"2026-07-05T09:03:40Z"},{"alias_kind":"pith_short_8","alias_value":"X3EYE4L6","created_at":"2026-07-05T09:03:40Z"}],"graph_snapshots":[{"event_id":"sha256:7be31fc28f1ca2d211e7ee6826ec98da508b5560d614163c3daac4b81a1e1f32","target":"graph","created_at":"2026-07-05T09:03:40Z","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/2408.12547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we present MedS-Bench, a comprehensive benchmark designed to evaluate the performance of large language models (LLMs) in clinical contexts. Unlike existing benchmarks that focus on multiple-choice question answering, MedS-Bench spans 11 high-level clinical tasks, including clinical report summarization, treatment recommendations, diagnosis, named entity recognition, and medical concept explanation, among others. We evaluated six leading LLMs, e.g., MEDITRON, Mistral, InternLM 2, Llama 3, GPT-4, and Claude-3.5 using few-shot prompting, and found that even the most sophisticated m","authors_text":"Chaoyi Wu, Hongfei Gu, Jinxin Liu, Na Li, Pengcheng Qiu, Weidi Xie, Yanfeng Wang, Ya Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T17:01:34Z","title":"Towards Evaluating and Building Versatile Large Language Models for Medicine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12547","kind":"arxiv","version":2},"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:ff56ba0a6c804d0ebb807e5b06af485329cdd1c29802a347e721e38e6bfe6ac7","target":"record","created_at":"2026-07-05T09:03:40Z","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":"9698fe5e80d1412d27ef3953dd197a16ff99a282f10bd85bb5d5d5c2e9ab8c54","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T17:01:34Z","title_canon_sha256":"33966769003fc783e62dc432989be2f599aa4617c653d8a9e3d9ffe1ef58a2cd"},"schema_version":"1.0","source":{"id":"2408.12547","kind":"arxiv","version":2}},"canonical_sha256":"bec982717e80ef7eb7b874879665d0472d838cd8ae8ef5bfba19e33fcc241347","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bec982717e80ef7eb7b874879665d0472d838cd8ae8ef5bfba19e33fcc241347","first_computed_at":"2026-07-05T09:03:40.970706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:40.970706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9YCeQOL7w1HEBiLTsnuz6Q84Y0zvSv/26/Hr8Jpb/G4JQWmn8fNCkdu8dLArE0Tpapd55SkBYN5AhQm67wSACw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:40.971179Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12547","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff56ba0a6c804d0ebb807e5b06af485329cdd1c29802a347e721e38e6bfe6ac7","sha256:7be31fc28f1ca2d211e7ee6826ec98da508b5560d614163c3daac4b81a1e1f32"],"state_sha256":"2e3509ad368f0b7ef85210151f83fd4fa012b31137437e62da4d2c83608f4a9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3s/UTCSGMVZGHwvJduF1RBj+pcSu4rmTFTaj1Sfw1Xz4d2M+ghkUttXxeub39xEOhP/yCxQy6darpg3pFKFSBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T19:00:55.114665Z","bundle_sha256":"beceb9c5540ea94ffcb806f194c99fe9293b348910be2bd9eaa237a213353a93"}}