{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FK3VP34FVQ5RUYG4RRWOTSP5N5","short_pith_number":"pith:FK3VP34F","schema_version":"1.0","canonical_sha256":"2ab757ef85ac3b1a60dc8c6ce9c9fd6f7af631ab9853aa385300dd7f38fe760d","source":{"kind":"arxiv","id":"2502.01220","version":6},"attestation_state":"computed","paper":{"title":"Factual Knowledge in Language Models: Robustness and Anomalies under Simple Temporal Context Variations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexis Nasr, Fr\\'ed\\'eric B\\'echet, Gw\\'enol\\'e Lecorv\\'e, Hichem Ammar Khodja, Quentin Brabant","submitted_at":"2025-02-03T10:24:55Z","abstract_excerpt":"This paper explores the robustness of language models (LMs) to variations in the temporal context within factual knowledge. It examines whether LMs can correctly associate a temporal context with a past fact valid over a defined period, by asking them to differentiate correct from incorrect contexts. The LMs' ability to distinguish is analyzed along two dimensions: the distance of the incorrect context from the validity period and the granularity of the context. To this end, a dataset called TimeStress is introduced, enabling the evaluation of 18 diverse LMs. Results reveal that the best LM ac"},"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":"2502.01220","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T10:24:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c98b9ae177a29e390cf5b6675c574eb11d21f9208b82c9a3a39f18c7635ed1db","abstract_canon_sha256":"e681666965714be5dee2b0214dc1b6645eba32428b2ece1d1c2fc7d649fd57dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:41.680403Z","signature_b64":"1O68IELSd7VaWlhm5eC8I7pS8arc4kEBvIbJ6uHSOCq1sYRsl9rMEKJd6KsHdGOB0RnVbqvO/8QhZwI/lLtLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ab757ef85ac3b1a60dc8c6ce9c9fd6f7af631ab9853aa385300dd7f38fe760d","last_reissued_at":"2026-07-05T11:25:41.679945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:41.679945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factual Knowledge in Language Models: Robustness and Anomalies under Simple Temporal Context Variations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexis Nasr, Fr\\'ed\\'eric B\\'echet, Gw\\'enol\\'e Lecorv\\'e, Hichem Ammar Khodja, Quentin Brabant","submitted_at":"2025-02-03T10:24:55Z","abstract_excerpt":"This paper explores the robustness of language models (LMs) to variations in the temporal context within factual knowledge. It examines whether LMs can correctly associate a temporal context with a past fact valid over a defined period, by asking them to differentiate correct from incorrect contexts. The LMs' ability to distinguish is analyzed along two dimensions: the distance of the incorrect context from the validity period and the granularity of the context. To this end, a dataset called TimeStress is introduced, enabling the evaluation of 18 diverse LMs. Results reveal that the best LM ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01220","kind":"arxiv","version":6},"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/2502.01220/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":"2502.01220","created_at":"2026-07-05T11:25:41.680000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01220v6","created_at":"2026-07-05T11:25:41.680000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01220","created_at":"2026-07-05T11:25:41.680000+00:00"},{"alias_kind":"pith_short_12","alias_value":"FK3VP34FVQ5R","created_at":"2026-07-05T11:25:41.680000+00:00"},{"alias_kind":"pith_short_16","alias_value":"FK3VP34FVQ5RUYG4","created_at":"2026-07-05T11:25:41.680000+00:00"},{"alias_kind":"pith_short_8","alias_value":"FK3VP34F","created_at":"2026-07-05T11:25:41.680000+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/FK3VP34FVQ5RUYG4RRWOTSP5N5","json":"https://pith.science/pith/FK3VP34FVQ5RUYG4RRWOTSP5N5.json","graph_json":"https://pith.science/api/pith-number/FK3VP34FVQ5RUYG4RRWOTSP5N5/graph.json","events_json":"https://pith.science/api/pith-number/FK3VP34FVQ5RUYG4RRWOTSP5N5/events.json","paper":"https://pith.science/paper/FK3VP34F"},"agent_actions":{"view_html":"https://pith.science/pith/FK3VP34FVQ5RUYG4RRWOTSP5N5","download_json":"https://pith.science/pith/FK3VP34FVQ5RUYG4RRWOTSP5N5.json","view_paper":"https://pith.science/paper/FK3VP34F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01220&json=true","fetch_graph":"https://pith.science/api/pith-number/FK3VP34FVQ5RUYG4RRWOTSP5N5/graph.json","fetch_events":"https://pith.science/api/pith-number/FK3VP34FVQ5RUYG4RRWOTSP5N5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FK3VP34FVQ5RUYG4RRWOTSP5N5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FK3VP34FVQ5RUYG4RRWOTSP5N5/action/storage_attestation","attest_author":"https://pith.science/pith/FK3VP34FVQ5RUYG4RRWOTSP5N5/action/author_attestation","sign_citation":"https://pith.science/pith/FK3VP34FVQ5RUYG4RRWOTSP5N5/action/citation_signature","submit_replication":"https://pith.science/pith/FK3VP34FVQ5RUYG4RRWOTSP5N5/action/replication_record"}},"created_at":"2026-07-05T11:25:41.680000+00:00","updated_at":"2026-07-05T11:25:41.680000+00:00"}