{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2DJ64P5PR3AKK2K33G5LQTEPGL","short_pith_number":"pith:2DJ64P5P","schema_version":"1.0","canonical_sha256":"d0d3ee3faf8ec0a5695bd9bab84c8f32e4733095f45af8a45fc325222ff8b2b6","source":{"kind":"arxiv","id":"2509.04304","version":1},"attestation_state":"computed","paper":{"title":"Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Florian Matthes, Juraj Vladika, Mahdi Dhaini","submitted_at":"2025-09-04T15:17:50Z","abstract_excerpt":"The growing capabilities of Large Language Models (LLMs) show significant potential to enhance healthcare by assisting medical researchers and physicians. However, their reliance on static training data is a major risk when medical recommendations evolve with new research and developments. When LLMs memorize outdated medical knowledge, they can provide harmful advice or fail at clinical reasoning tasks. To investigate this problem, we introduce two novel question-answering (QA) datasets derived from systematic reviews: MedRevQA (16,501 QA pairs covering general biomedical knowledge) and MedCha"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.04304","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T15:17:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9d318771bf5e38eb76a659ca4ebfa148b9115f1775f3f4dde12ee99024b21705","abstract_canon_sha256":"e9862c2adcc5d1be23807efc99f75a36b8526b771569f635497d8b2a7c2b1e4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:56.943108Z","signature_b64":"cdaE04d3rD4/AdnHKSu77fhGdLxFr9mxch60bU/GhYzR5Uejg/mplEibWsywo9WnyB7VcHwQ6dOwiMpF8HlIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0d3ee3faf8ec0a5695bd9bab84c8f32e4733095f45af8a45fc325222ff8b2b6","last_reissued_at":"2026-07-05T12:04:56.942558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:56.942558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Florian Matthes, Juraj Vladika, Mahdi Dhaini","submitted_at":"2025-09-04T15:17:50Z","abstract_excerpt":"The growing capabilities of Large Language Models (LLMs) show significant potential to enhance healthcare by assisting medical researchers and physicians. However, their reliance on static training data is a major risk when medical recommendations evolve with new research and developments. When LLMs memorize outdated medical knowledge, they can provide harmful advice or fail at clinical reasoning tasks. To investigate this problem, we introduce two novel question-answering (QA) datasets derived from systematic reviews: MedRevQA (16,501 QA pairs covering general biomedical knowledge) and MedCha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04304","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/2509.04304/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.04304","created_at":"2026-07-05T12:04:56.942618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04304v1","created_at":"2026-07-05T12:04:56.942618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04304","created_at":"2026-07-05T12:04:56.942618+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DJ64P5PR3AK","created_at":"2026-07-05T12:04:56.942618+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DJ64P5PR3AKK2K3","created_at":"2026-07-05T12:04:56.942618+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DJ64P5P","created_at":"2026-07-05T12:04:56.942618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DJ64P5PR3AKK2K33G5LQTEPGL","json":"https://pith.science/pith/2DJ64P5PR3AKK2K33G5LQTEPGL.json","graph_json":"https://pith.science/api/pith-number/2DJ64P5PR3AKK2K33G5LQTEPGL/graph.json","events_json":"https://pith.science/api/pith-number/2DJ64P5PR3AKK2K33G5LQTEPGL/events.json","paper":"https://pith.science/paper/2DJ64P5P"},"agent_actions":{"view_html":"https://pith.science/pith/2DJ64P5PR3AKK2K33G5LQTEPGL","download_json":"https://pith.science/pith/2DJ64P5PR3AKK2K33G5LQTEPGL.json","view_paper":"https://pith.science/paper/2DJ64P5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04304&json=true","fetch_graph":"https://pith.science/api/pith-number/2DJ64P5PR3AKK2K33G5LQTEPGL/graph.json","fetch_events":"https://pith.science/api/pith-number/2DJ64P5PR3AKK2K33G5LQTEPGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DJ64P5PR3AKK2K33G5LQTEPGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DJ64P5PR3AKK2K33G5LQTEPGL/action/storage_attestation","attest_author":"https://pith.science/pith/2DJ64P5PR3AKK2K33G5LQTEPGL/action/author_attestation","sign_citation":"https://pith.science/pith/2DJ64P5PR3AKK2K33G5LQTEPGL/action/citation_signature","submit_replication":"https://pith.science/pith/2DJ64P5PR3AKK2K33G5LQTEPGL/action/replication_record"}},"created_at":"2026-07-05T12:04:56.942618+00:00","updated_at":"2026-07-05T12:04:56.942618+00:00"}