{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XJGVZHBM6CEXXWDVB7ATWYHUXQ","short_pith_number":"pith:XJGVZHBM","schema_version":"1.0","canonical_sha256":"ba4d5c9c2cf0897bd8750fc13b60f4bc26d8b281cdd226fd95ce5d1c316bfb5c","source":{"kind":"arxiv","id":"2409.13338","version":3},"attestation_state":"computed","paper":{"title":"Time Awareness in Large Language Models: Benchmarking Fact Recall Across Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Herel, Jiri Jirak, Tomas Mikolov, Vojtech Bartek","submitted_at":"2024-09-20T08:57:20Z","abstract_excerpt":"Who is the US President? The answer changes depending on when the question is asked. While large language models (LLMs) are evaluated on various reasoning tasks, they often miss a crucial dimension: time. In real-world scenarios, the correctness of answers is frequently tied to temporal context. To address this gap, we present a novel framework and dataset spanning over 8,000 events from 2018 to 2024, annotated with day-level granularity and sourced globally across domains such as politics, science, and business. Our TimeShift evaluation method systematically probes LLMs for temporal reasoning"},"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":"2409.13338","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T08:57:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc5f6b58dc4cd5dfff66a5aa270fea3e6948cf84b4c98f3d1b33598136812ead","abstract_canon_sha256":"ee6bb6f9e02875dd14846f0fd162849de0a7f5096917ff27de2d6d2d907caa84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:16.947428Z","signature_b64":"Xnsjli2tLrCTTqnYSssVbWxEc2sCRiGx+1qmSCvhvyxtXJUu2B/hFg+YUuCufN1cPVzkFCeZT0P4Rq1Ca7cfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba4d5c9c2cf0897bd8750fc13b60f4bc26d8b281cdd226fd95ce5d1c316bfb5c","last_reissued_at":"2026-07-05T11:03:16.946975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:16.946975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time Awareness in Large Language Models: Benchmarking Fact Recall Across Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Herel, Jiri Jirak, Tomas Mikolov, Vojtech Bartek","submitted_at":"2024-09-20T08:57:20Z","abstract_excerpt":"Who is the US President? The answer changes depending on when the question is asked. While large language models (LLMs) are evaluated on various reasoning tasks, they often miss a crucial dimension: time. In real-world scenarios, the correctness of answers is frequently tied to temporal context. To address this gap, we present a novel framework and dataset spanning over 8,000 events from 2018 to 2024, annotated with day-level granularity and sourced globally across domains such as politics, science, and business. Our TimeShift evaluation method systematically probes LLMs for temporal reasoning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13338","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/2409.13338/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":"2409.13338","created_at":"2026-07-05T11:03:16.947031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13338v3","created_at":"2026-07-05T11:03:16.947031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13338","created_at":"2026-07-05T11:03:16.947031+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJGVZHBM6CEX","created_at":"2026-07-05T11:03:16.947031+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJGVZHBM6CEXXWDV","created_at":"2026-07-05T11:03:16.947031+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJGVZHBM","created_at":"2026-07-05T11:03:16.947031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27199","citing_title":"Forecasting With LLMs: Improved Generalization Through Feature Steering","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20959","citing_title":"Right Knowledge, Wrong Answer: Characterizing Parametric Temporal Conflict in Open-Weight Language Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05194","citing_title":"Temporal Preference Concepts and their Functions in a Large Language Model","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16303","citing_title":"From Demographics to Survey Anchors: Evaluating LLM Agents for Modeling Retirement Attitudes","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2601.05300","citing_title":"TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJGVZHBM6CEXXWDVB7ATWYHUXQ","json":"https://pith.science/pith/XJGVZHBM6CEXXWDVB7ATWYHUXQ.json","graph_json":"https://pith.science/api/pith-number/XJGVZHBM6CEXXWDVB7ATWYHUXQ/graph.json","events_json":"https://pith.science/api/pith-number/XJGVZHBM6CEXXWDVB7ATWYHUXQ/events.json","paper":"https://pith.science/paper/XJGVZHBM"},"agent_actions":{"view_html":"https://pith.science/pith/XJGVZHBM6CEXXWDVB7ATWYHUXQ","download_json":"https://pith.science/pith/XJGVZHBM6CEXXWDVB7ATWYHUXQ.json","view_paper":"https://pith.science/paper/XJGVZHBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13338&json=true","fetch_graph":"https://pith.science/api/pith-number/XJGVZHBM6CEXXWDVB7ATWYHUXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XJGVZHBM6CEXXWDVB7ATWYHUXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJGVZHBM6CEXXWDVB7ATWYHUXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJGVZHBM6CEXXWDVB7ATWYHUXQ/action/storage_attestation","attest_author":"https://pith.science/pith/XJGVZHBM6CEXXWDVB7ATWYHUXQ/action/author_attestation","sign_citation":"https://pith.science/pith/XJGVZHBM6CEXXWDVB7ATWYHUXQ/action/citation_signature","submit_replication":"https://pith.science/pith/XJGVZHBM6CEXXWDVB7ATWYHUXQ/action/replication_record"}},"created_at":"2026-07-05T11:03:16.947031+00:00","updated_at":"2026-07-05T11:03:16.947031+00:00"}