{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6OWTT67GEENK3QTDCHZIF4BL3M","short_pith_number":"pith:6OWTT67G","canonical_record":{"source":{"id":"2605.13045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T06:04:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"38c4a622fdb66904cc042f5cf4bff2c4478828d6af137e30665ecca493009f48","abstract_canon_sha256":"c1118bfb2465e9a059dac4b7aaa921c2ade30a82eda494c702fb624d3f7bcca1"},"schema_version":"1.0"},"canonical_sha256":"f3ad39fbe6211aadc26311f282f02bdb01ceef388619218b4861cf6b57152355","source":{"kind":"arxiv","id":"2605.13045","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13045","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13045v1","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13045","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"6OWTT67GEENK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6OWTT67GEENK3QTD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6OWTT67G","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6OWTT67GEENK3QTDCHZIF4BL3M","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T06:04:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"38c4a622fdb66904cc042f5cf4bff2c4478828d6af137e30665ecca493009f48","abstract_canon_sha256":"c1118bfb2465e9a059dac4b7aaa921c2ade30a82eda494c702fb624d3f7bcca1"},"schema_version":"1.0"},"canonical_sha256":"f3ad39fbe6211aadc26311f282f02bdb01ceef388619218b4861cf6b57152355","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:59.454297Z","signature_b64":"HxLwRemh7887KKs1gdVqhUEO1vlZAk7ZpgcbcAemVDbCrIV9G2fLtHIZdnCMvFKZFImqr5IgCcIowQSAaJscDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3ad39fbe6211aadc26311f282f02bdb01ceef388619218b4861cf6b57152355","last_reissued_at":"2026-05-18T03:08:59.453598Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:59.453598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13045","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":"2026-05-18T03:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qCx7JM4qaKmmulEC76OVjXkp/7HnT2/qxPZ301sO+U7s8O2+9C7GKe2oSEuO9jre0OJ8/hdQoG2FoDJP26fzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:00:50.136400Z"},"content_sha256":"1922fe52cbb51f311b8b000137e6d3f06b4f0160a5d1e15afa14984a65ed5104","schema_version":"1.0","event_id":"sha256:1922fe52cbb51f311b8b000137e6d3f06b4f0160a5d1e15afa14984a65ed5104"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6OWTT67GEENK3QTDCHZIF4BL3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models Lack Temporal Awareness of Medical Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Large language models lack awareness of when medical knowledge applies in time.","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Anil Vullikanti, Fangyuan Chen, Guangzhi Xiong, Mengxuan Hu, Qiao Jin, Qingyu Chen, Yifan Peng, Zhiyong Lu, Zihan Guan","submitted_at":"2026-05-13T06:04:40Z","abstract_excerpt":"The existing methods for evaluating the medical knowledge of Large Language Models (LLMs) are largely based on atemporal examination-style benchmarks, while in reality, medical knowledge is inherently dynamic and continuously evolves as new evidence emerges and treatments are approved. Consequently, evaluating medical knowledge without a temporal context may provide an incomplete assessment of whether LLMs can accurately reason about time-specific medical knowledge. Moreover, most medical data are historical, requiring the models not only to recall the correct knowledge, but also to know when "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LLMs lack temporal awareness in medical knowledge: performance on up-to-date knowledge declines gradually rather than showing sharp cutoff, historical knowledge accuracy is only 25.37%-53.89% of up-to-date, and models exhibit temporally inconsistent behaviors.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the selected evolving medical guidelines in TempoMed-Bench are representative of temporal medical knowledge changes and that model outputs reflect internal parametric knowledge rather than prompt or retrieval artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLMs lack temporal awareness of medical knowledge, showing gradual performance decline on up-to-date facts, much lower accuracy on historical knowledge (25-54% relative), and inconsistent year-to-year predictions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large language models lack awareness of when medical knowledge applies in time.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"602eff3df8c72203971b150a13131afa5f490c080a913fa420471453c1513e84"},"source":{"id":"2605.13045","kind":"arxiv","version":1},"verdict":{"id":"cbfd81a9-b9e3-4dc0-850b-e5c48e60962b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:13:56.264058Z","strongest_claim":"LLMs lack temporal awareness in medical knowledge: performance on up-to-date knowledge declines gradually rather than showing sharp cutoff, historical knowledge accuracy is only 25.37%-53.89% of up-to-date, and models exhibit temporally inconsistent behaviors.","one_line_summary":"LLMs lack temporal awareness of medical knowledge, showing gradual performance decline on up-to-date facts, much lower accuracy on historical knowledge (25-54% relative), and inconsistent year-to-year predictions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the selected evolving medical guidelines in TempoMed-Bench are representative of temporal medical knowledge changes and that model outputs reflect internal parametric knowledge rather than prompt or retrieval artifacts.","pith_extraction_headline":"Large language models lack awareness of when medical knowledge applies in time."},"references":{"count":62,"sample":[{"doi":"","year":2025,"title":"gpt-oss-120b & gpt-oss-20b Model Card","work_id":"178c1f7e-4f19-4392-a45d-45a6dfa88ead","ref_index":1,"cited_arxiv_id":"2508.10925","is_internal_anchor":true},{"doi":"","year":2025,"title":"The distracting effect: Understanding irrelevant passages in rag","work_id":"153de318-71f7-44de-ac1d-aadcea5188a7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","work_id":"5d613c2c-158f-488c-9981-fc9b82a5e093","ref_index":3,"cited_arxiv_id":"2505.08775","is_internal_anchor":true},{"doi":"","year":2024,"title":"Jae Hyun Bae, Ji-Hee Haam, Eonju Jeon, Seo Young Kang, SuJin Song, Cheol-Young Park, Hyuktae Kwon, Committee of Clinical Practice Guidelines, et al. 2024 clinical practice guidelines for the diagnosis","work_id":"57553244-8629-4d81-9c16-ff85672051bd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Diagnostic accuracy of a large language model in pediatric case studies.JAMA pediatrics, 178(3):313–315, 2024","work_id":"0f440dca-ddff-46fd-b787-68d504d8f466","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":62,"snapshot_sha256":"405ff4665692bbd05ec0cf42b89e10498dd979ac1efc99bf20b40a0059a61b37","internal_anchors":9},"formal_canon":{"evidence_count":2,"snapshot_sha256":"abd01da47dcf8afd97d71c568c2e7cadb181d6e5c9d026a9c39c159c06af52ed"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"cbfd81a9-b9e3-4dc0-850b-e5c48e60962b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3J7G6KZ+uFpqP+T1/IM+loYO893PINrLCT2B+X8KhhqdptFJfp4wzz9W3OGSNh0LT3kHp8/Ai6fRlRgGSBUhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:00:50.137228Z"},"content_sha256":"9bec9d9ed801f1d11de6d5d1ada2597fdd76b7c1042d8ade62049839dd5a62da","schema_version":"1.0","event_id":"sha256:9bec9d9ed801f1d11de6d5d1ada2597fdd76b7c1042d8ade62049839dd5a62da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6OWTT67GEENK3QTDCHZIF4BL3M/bundle.json","state_url":"https://pith.science/pith/6OWTT67GEENK3QTDCHZIF4BL3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6OWTT67GEENK3QTDCHZIF4BL3M/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":"2026-06-01T18:00:50Z","links":{"resolver":"https://pith.science/pith/6OWTT67GEENK3QTDCHZIF4BL3M","bundle":"https://pith.science/pith/6OWTT67GEENK3QTDCHZIF4BL3M/bundle.json","state":"https://pith.science/pith/6OWTT67GEENK3QTDCHZIF4BL3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6OWTT67GEENK3QTDCHZIF4BL3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6OWTT67GEENK3QTDCHZIF4BL3M","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":"c1118bfb2465e9a059dac4b7aaa921c2ade30a82eda494c702fb624d3f7bcca1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T06:04:40Z","title_canon_sha256":"38c4a622fdb66904cc042f5cf4bff2c4478828d6af137e30665ecca493009f48"},"schema_version":"1.0","source":{"id":"2605.13045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13045","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13045v1","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13045","created_at":"2026-05-18T03:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"6OWTT67GEENK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6OWTT67GEENK3QTD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6OWTT67G","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:9bec9d9ed801f1d11de6d5d1ada2597fdd76b7c1042d8ade62049839dd5a62da","target":"graph","created_at":"2026-05-18T03:08:59Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"LLMs lack temporal awareness in medical knowledge: performance on up-to-date knowledge declines gradually rather than showing sharp cutoff, historical knowledge accuracy is only 25.37%-53.89% of up-to-date, and models exhibit temporally inconsistent behaviors."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the selected evolving medical guidelines in TempoMed-Bench are representative of temporal medical knowledge changes and that model outputs reflect internal parametric knowledge rather than prompt or retrieval artifacts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LLMs lack temporal awareness of medical knowledge, showing gradual performance decline on up-to-date facts, much lower accuracy on historical knowledge (25-54% relative), and inconsistent year-to-year predictions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Large language models lack awareness of when medical knowledge applies in time."}],"snapshot_sha256":"602eff3df8c72203971b150a13131afa5f490c080a913fa420471453c1513e84"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"abd01da47dcf8afd97d71c568c2e7cadb181d6e5c9d026a9c39c159c06af52ed"},"paper":{"abstract_excerpt":"The existing methods for evaluating the medical knowledge of Large Language Models (LLMs) are largely based on atemporal examination-style benchmarks, while in reality, medical knowledge is inherently dynamic and continuously evolves as new evidence emerges and treatments are approved. Consequently, evaluating medical knowledge without a temporal context may provide an incomplete assessment of whether LLMs can accurately reason about time-specific medical knowledge. Moreover, most medical data are historical, requiring the models not only to recall the correct knowledge, but also to know when ","authors_text":"Anil Vullikanti, Fangyuan Chen, Guangzhi Xiong, Mengxuan Hu, Qiao Jin, Qingyu Chen, Yifan Peng, Zhiyong Lu, Zihan Guan","cross_cats":["cs.CL"],"headline":"Large language models lack awareness of when medical knowledge applies in time.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T06:04:40Z","title":"Large Language Models Lack Temporal Awareness of Medical Knowledge"},"references":{"count":62,"internal_anchors":9,"resolved_work":62,"sample":[{"cited_arxiv_id":"2508.10925","doi":"","is_internal_anchor":true,"ref_index":1,"title":"gpt-oss-120b & gpt-oss-20b Model Card","work_id":"178c1f7e-4f19-4392-a45d-45a6dfa88ead","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"The distracting effect: Understanding irrelevant passages in rag","work_id":"153de318-71f7-44de-ac1d-aadcea5188a7","year":2025},{"cited_arxiv_id":"2505.08775","doi":"","is_internal_anchor":true,"ref_index":3,"title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","work_id":"5d613c2c-158f-488c-9981-fc9b82a5e093","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Jae Hyun Bae, Ji-Hee Haam, Eonju Jeon, Seo Young Kang, SuJin Song, Cheol-Young Park, Hyuktae Kwon, Committee of Clinical Practice Guidelines, et al. 2024 clinical practice guidelines for the diagnosis","work_id":"57553244-8629-4d81-9c16-ff85672051bd","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Diagnostic accuracy of a large language model in pediatric case studies.JAMA pediatrics, 178(3):313–315, 2024","work_id":"0f440dca-ddff-46fd-b787-68d504d8f466","year":2024}],"snapshot_sha256":"405ff4665692bbd05ec0cf42b89e10498dd979ac1efc99bf20b40a0059a61b37"},"source":{"id":"2605.13045","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:13:56.264058Z","id":"cbfd81a9-b9e3-4dc0-850b-e5c48e60962b","model_set":{"reader":"grok-4.3"},"one_line_summary":"LLMs lack temporal awareness of medical knowledge, showing gradual performance decline on up-to-date facts, much lower accuracy on historical knowledge (25-54% relative), and inconsistent year-to-year predictions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Large language models lack awareness of when medical knowledge applies in time.","strongest_claim":"LLMs lack temporal awareness in medical knowledge: performance on up-to-date knowledge declines gradually rather than showing sharp cutoff, historical knowledge accuracy is only 25.37%-53.89% of up-to-date, and models exhibit temporally inconsistent behaviors.","weakest_assumption":"That the selected evolving medical guidelines in TempoMed-Bench are representative of temporal medical knowledge changes and that model outputs reflect internal parametric knowledge rather than prompt or retrieval artifacts."}},"verdict_id":"cbfd81a9-b9e3-4dc0-850b-e5c48e60962b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1922fe52cbb51f311b8b000137e6d3f06b4f0160a5d1e15afa14984a65ed5104","target":"record","created_at":"2026-05-18T03:08:59Z","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":"c1118bfb2465e9a059dac4b7aaa921c2ade30a82eda494c702fb624d3f7bcca1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T06:04:40Z","title_canon_sha256":"38c4a622fdb66904cc042f5cf4bff2c4478828d6af137e30665ecca493009f48"},"schema_version":"1.0","source":{"id":"2605.13045","kind":"arxiv","version":1}},"canonical_sha256":"f3ad39fbe6211aadc26311f282f02bdb01ceef388619218b4861cf6b57152355","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3ad39fbe6211aadc26311f282f02bdb01ceef388619218b4861cf6b57152355","first_computed_at":"2026-05-18T03:08:59.453598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:59.453598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HxLwRemh7887KKs1gdVqhUEO1vlZAk7ZpgcbcAemVDbCrIV9G2fLtHIZdnCMvFKZFImqr5IgCcIowQSAaJscDw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:59.454297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1922fe52cbb51f311b8b000137e6d3f06b4f0160a5d1e15afa14984a65ed5104","sha256:9bec9d9ed801f1d11de6d5d1ada2597fdd76b7c1042d8ade62049839dd5a62da"],"state_sha256":"c06241ba6a3147c2378a1b648055e758c5e23b5d99490bfff6f5eca401f79ba7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ScMUbF7YYTUUR5+wgWCisqiP6UM6csXqSzi8KpY1jktauTjBx3/ogyJbdjElx5Ijpkt1IVsin7lT4+NwQBbMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T18:00:50.141542Z","bundle_sha256":"f5e1246470f4fbb8c161f586e230758a215fcc1d984a83feb075349c44362046"}}