{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JW3QW4R3FL7CQ7H4MTHYSM7BP5","short_pith_number":"pith:JW3QW4R3","schema_version":"1.0","canonical_sha256":"4db70b723b2afe287cfc64cf8933e17f6baf4907a4c21092300e01b2b7b6920a","source":{"kind":"arxiv","id":"2404.08700","version":3},"attestation_state":"computed","paper":{"title":"DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Giuseppe Riccardi, Seyed Mahed Mousavi, Simone Alghisi","submitted_at":"2024-04-10T18:08:59Z","abstract_excerpt":"LLMs acquire knowledge from massive data snapshots collected at different timestamps. Their knowledge is then commonly evaluated using static benchmarks. However, factual knowledge is generally subject to time-sensitive changes, and static benchmarks cannot address those cases. We present an approach to dynamically evaluate the knowledge in LLMs and their time-sensitiveness against Wikidata, a publicly available up-to-date knowledge graph. We evaluate the time-sensitive knowledge in twenty-four private and open-source LLMs, as well as the effectiveness of four editing methods in updating the o"},"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":"2404.08700","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-10T18:08:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99b71f0e8ed30392bf61dde0addaae152a36757eb72817f115448ccfb0c3f32e","abstract_canon_sha256":"c8f530a0a57a66b2b277367e3c005b72cbdc798f7a23d83ab2f0a993ac5ef0f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:31.912614Z","signature_b64":"7cL2iIYM/6YK5muvgQyH4aSl95gHaUijNt0zqCRp36hBrW1IC1PjWxyAvD5sl8fXMAhiVi8OzrI5Blm0g/RxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4db70b723b2afe287cfc64cf8933e17f6baf4907a4c21092300e01b2b7b6920a","last_reissued_at":"2026-07-05T09:14:31.912127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:31.912127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Giuseppe Riccardi, Seyed Mahed Mousavi, Simone Alghisi","submitted_at":"2024-04-10T18:08:59Z","abstract_excerpt":"LLMs acquire knowledge from massive data snapshots collected at different timestamps. Their knowledge is then commonly evaluated using static benchmarks. However, factual knowledge is generally subject to time-sensitive changes, and static benchmarks cannot address those cases. We present an approach to dynamically evaluate the knowledge in LLMs and their time-sensitiveness against Wikidata, a publicly available up-to-date knowledge graph. We evaluate the time-sensitive knowledge in twenty-four private and open-source LLMs, as well as the effectiveness of four editing methods in updating the o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08700","kind":"arxiv","version":3},"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/2404.08700/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":"2404.08700","created_at":"2026-07-05T09:14:31.912185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08700v3","created_at":"2026-07-05T09:14:31.912185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08700","created_at":"2026-07-05T09:14:31.912185+00:00"},{"alias_kind":"pith_short_12","alias_value":"JW3QW4R3FL7C","created_at":"2026-07-05T09:14:31.912185+00:00"},{"alias_kind":"pith_short_16","alias_value":"JW3QW4R3FL7CQ7H4","created_at":"2026-07-05T09:14:31.912185+00:00"},{"alias_kind":"pith_short_8","alias_value":"JW3QW4R3","created_at":"2026-07-05T09:14:31.912185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00570","citing_title":"Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24276","citing_title":"G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15676","citing_title":"EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JW3QW4R3FL7CQ7H4MTHYSM7BP5","json":"https://pith.science/pith/JW3QW4R3FL7CQ7H4MTHYSM7BP5.json","graph_json":"https://pith.science/api/pith-number/JW3QW4R3FL7CQ7H4MTHYSM7BP5/graph.json","events_json":"https://pith.science/api/pith-number/JW3QW4R3FL7CQ7H4MTHYSM7BP5/events.json","paper":"https://pith.science/paper/JW3QW4R3"},"agent_actions":{"view_html":"https://pith.science/pith/JW3QW4R3FL7CQ7H4MTHYSM7BP5","download_json":"https://pith.science/pith/JW3QW4R3FL7CQ7H4MTHYSM7BP5.json","view_paper":"https://pith.science/paper/JW3QW4R3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08700&json=true","fetch_graph":"https://pith.science/api/pith-number/JW3QW4R3FL7CQ7H4MTHYSM7BP5/graph.json","fetch_events":"https://pith.science/api/pith-number/JW3QW4R3FL7CQ7H4MTHYSM7BP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JW3QW4R3FL7CQ7H4MTHYSM7BP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JW3QW4R3FL7CQ7H4MTHYSM7BP5/action/storage_attestation","attest_author":"https://pith.science/pith/JW3QW4R3FL7CQ7H4MTHYSM7BP5/action/author_attestation","sign_citation":"https://pith.science/pith/JW3QW4R3FL7CQ7H4MTHYSM7BP5/action/citation_signature","submit_replication":"https://pith.science/pith/JW3QW4R3FL7CQ7H4MTHYSM7BP5/action/replication_record"}},"created_at":"2026-07-05T09:14:31.912185+00:00","updated_at":"2026-07-05T09:14:31.912185+00:00"}