{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CMXI7MN56HAYCHKLIVOSCPNLUL","short_pith_number":"pith:CMXI7MN5","canonical_record":{"source":{"id":"2405.07468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T05:08:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52699966bf642ebb427fdd41348cdf2c4ed59cdc6dea94a98bda23071e839740","abstract_canon_sha256":"689fd608f7aece9449422685b5154ebf59f8fb46da02b0c1b1a83d95cb5c1ac2"},"schema_version":"1.0"},"canonical_sha256":"132e8fb1bdf1c1811d4b455d213daba2c53c28c4b0ab35cd6aebe9089ed5dabf","source":{"kind":"arxiv","id":"2405.07468","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.07468","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"arxiv_version","alias_value":"2405.07468v1","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07468","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"pith_short_12","alias_value":"CMXI7MN56HAY","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"pith_short_16","alias_value":"CMXI7MN56HAYCHKL","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"pith_short_8","alias_value":"CMXI7MN5","created_at":"2026-07-05T08:18:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CMXI7MN56HAYCHKLIVOSCPNLUL","target":"record","payload":{"canonical_record":{"source":{"id":"2405.07468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T05:08:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52699966bf642ebb427fdd41348cdf2c4ed59cdc6dea94a98bda23071e839740","abstract_canon_sha256":"689fd608f7aece9449422685b5154ebf59f8fb46da02b0c1b1a83d95cb5c1ac2"},"schema_version":"1.0"},"canonical_sha256":"132e8fb1bdf1c1811d4b455d213daba2c53c28c4b0ab35cd6aebe9089ed5dabf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:22.945029Z","signature_b64":"b5op3bS6XON/zEDeEsF3Sb/pJskgW1VdfklFDqZFtArOVEP8VITFAoYjd7/NSetpgSIc77bFzo+4DPu8XIMfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"132e8fb1bdf1c1811d4b455d213daba2c53c28c4b0ab35cd6aebe9089ed5dabf","last_reissued_at":"2026-07-05T08:18:22.944618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:22.944618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.07468","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":"2026-07-05T08:18:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+KBMXKmKfDTH74gpDG6h/puvDrqUmUW3J8kMgrxupFMDWTRU0EshQgWUp9vm6UofvgwB5ZuP8SRNTPDokAcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:33:37.305649Z"},"content_sha256":"8e0ebcf35e2ed38bcea4825081bc9f71dd6f932b56159f628d9288f535281608","schema_version":"1.0","event_id":"sha256:8e0ebcf35e2ed38bcea4825081bc9f71dd6f932b56159f628d9288f535281608"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CMXI7MN56HAYCHKLIVOSCPNLUL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating large language models in medical applications: a survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Danli Shi, Jiayang Xiang, Mingguang He, Shanfu Lu, Xiaolan Chen, Yexin Liu","submitted_at":"2024-05-13T05:08:33Z","abstract_excerpt":"Large language models (LLMs) have emerged as powerful tools with transformative potential across numerous domains, including healthcare and medicine. In the medical domain, LLMs hold promise for tasks ranging from clinical decision support to patient education. However, evaluating the performance of LLMs in medical contexts presents unique challenges due to the complex and critical nature of medical information. This paper provides a comprehensive overview of the landscape of medical LLM evaluation, synthesizing insights from existing studies and highlighting evaluation data sources, task scen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07468","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/2405.07468/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":"2026-07-05T08:18:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LFj+0f5TOsifwFcc1YMLNe/y6Sup0T71M94FTMjOVbBK8u4UhjTBAOLkpjO6dbOLX33JrYZBNH82q6fA82QWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:33:37.306026Z"},"content_sha256":"e3089fe17661f02a3501c747c7285351bda8b3779da4b13408a9b4113ec3c555","schema_version":"1.0","event_id":"sha256:e3089fe17661f02a3501c747c7285351bda8b3779da4b13408a9b4113ec3c555"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMXI7MN56HAYCHKLIVOSCPNLUL/bundle.json","state_url":"https://pith.science/pith/CMXI7MN56HAYCHKLIVOSCPNLUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMXI7MN56HAYCHKLIVOSCPNLUL/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":"2026-08-05T01:33:37Z","links":{"resolver":"https://pith.science/pith/CMXI7MN56HAYCHKLIVOSCPNLUL","bundle":"https://pith.science/pith/CMXI7MN56HAYCHKLIVOSCPNLUL/bundle.json","state":"https://pith.science/pith/CMXI7MN56HAYCHKLIVOSCPNLUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMXI7MN56HAYCHKLIVOSCPNLUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CMXI7MN56HAYCHKLIVOSCPNLUL","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":"689fd608f7aece9449422685b5154ebf59f8fb46da02b0c1b1a83d95cb5c1ac2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T05:08:33Z","title_canon_sha256":"52699966bf642ebb427fdd41348cdf2c4ed59cdc6dea94a98bda23071e839740"},"schema_version":"1.0","source":{"id":"2405.07468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.07468","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"arxiv_version","alias_value":"2405.07468v1","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07468","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"pith_short_12","alias_value":"CMXI7MN56HAY","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"pith_short_16","alias_value":"CMXI7MN56HAYCHKL","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"pith_short_8","alias_value":"CMXI7MN5","created_at":"2026-07-05T08:18:22Z"}],"graph_snapshots":[{"event_id":"sha256:e3089fe17661f02a3501c747c7285351bda8b3779da4b13408a9b4113ec3c555","target":"graph","created_at":"2026-07-05T08:18:22Z","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/2405.07468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have emerged as powerful tools with transformative potential across numerous domains, including healthcare and medicine. In the medical domain, LLMs hold promise for tasks ranging from clinical decision support to patient education. However, evaluating the performance of LLMs in medical contexts presents unique challenges due to the complex and critical nature of medical information. This paper provides a comprehensive overview of the landscape of medical LLM evaluation, synthesizing insights from existing studies and highlighting evaluation data sources, task scen","authors_text":"Danli Shi, Jiayang Xiang, Mingguang He, Shanfu Lu, Xiaolan Chen, Yexin Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T05:08:33Z","title":"Evaluating large language models in medical applications: a survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07468","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":"sha256:8e0ebcf35e2ed38bcea4825081bc9f71dd6f932b56159f628d9288f535281608","target":"record","created_at":"2026-07-05T08:18:22Z","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":"689fd608f7aece9449422685b5154ebf59f8fb46da02b0c1b1a83d95cb5c1ac2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-13T05:08:33Z","title_canon_sha256":"52699966bf642ebb427fdd41348cdf2c4ed59cdc6dea94a98bda23071e839740"},"schema_version":"1.0","source":{"id":"2405.07468","kind":"arxiv","version":1}},"canonical_sha256":"132e8fb1bdf1c1811d4b455d213daba2c53c28c4b0ab35cd6aebe9089ed5dabf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"132e8fb1bdf1c1811d4b455d213daba2c53c28c4b0ab35cd6aebe9089ed5dabf","first_computed_at":"2026-07-05T08:18:22.944618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:22.944618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b5op3bS6XON/zEDeEsF3Sb/pJskgW1VdfklFDqZFtArOVEP8VITFAoYjd7/NSetpgSIc77bFzo+4DPu8XIMfDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:22.945029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.07468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e0ebcf35e2ed38bcea4825081bc9f71dd6f932b56159f628d9288f535281608","sha256:e3089fe17661f02a3501c747c7285351bda8b3779da4b13408a9b4113ec3c555"],"state_sha256":"0447db97fd2a46d06b696847968b1bbfa781b4b9e71fc74c9d5c914a65fbf896"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SoX/wPAxb3iDnq1XM5ZEXDTpz0t28HR9O0VwzldzsB9j8+yMvwHtwOn/z9j9P3ZG5+tqXsKOcrSzRCa+uc1aCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:33:37.308828Z","bundle_sha256":"e5a9a38461888a232df7dae0463c4f5e73ef4e36c572ce553d93cb960c2fc158"}}