{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WH2RK4HEQST323WBEU5IMKP3GA","short_pith_number":"pith:WH2RK4HE","schema_version":"1.0","canonical_sha256":"b1f51570e484a7bd6ec1253a8629fb302d1e577bc4539687ceec48f2606b22fa","source":{"kind":"arxiv","id":"2412.13377","version":2},"attestation_state":"computed","paper":{"title":"DateLogicQA: Benchmarking Temporal Biases in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cristina Mahanta, Gagan Bhatia, Madiha Kazi, Mingze Tang","submitted_at":"2024-12-17T23:25:47Z","abstract_excerpt":"This paper introduces DateLogicQA, a benchmark with 190 questions covering diverse date formats, temporal contexts, and reasoning types. We propose the Semantic Integrity Metric to assess tokenization quality and analyse two biases: Representation-Level Bias, affecting embeddings, and Logical-Level Bias, influencing reasoning outputs. Our findings provide a comprehensive evaluation of LLMs' capabilities and limitations in temporal reasoning, highlighting key challenges in handling temporal data accurately."},"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":"2412.13377","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T23:25:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b718e8a0570baee8335a42e64a00ffcb45c8cfa01091c4cbec18c1836df80f7d","abstract_canon_sha256":"40deb6f77a7cb179d870d2868f6ab1d0505d3b2ab4b4bcee672acdbf313118ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:42.914340Z","signature_b64":"sLNXWBmerlBoIwutUKpvkJSW3vVPaw4gsh8TdrgPJkJsPSi11gaNSQAXmE3N3P94AoSY2Qg0EEMvTHazgZo+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1f51570e484a7bd6ec1253a8629fb302d1e577bc4539687ceec48f2606b22fa","last_reissued_at":"2026-07-05T11:04:42.913911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:42.913911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DateLogicQA: Benchmarking Temporal Biases in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cristina Mahanta, Gagan Bhatia, Madiha Kazi, Mingze Tang","submitted_at":"2024-12-17T23:25:47Z","abstract_excerpt":"This paper introduces DateLogicQA, a benchmark with 190 questions covering diverse date formats, temporal contexts, and reasoning types. We propose the Semantic Integrity Metric to assess tokenization quality and analyse two biases: Representation-Level Bias, affecting embeddings, and Logical-Level Bias, influencing reasoning outputs. Our findings provide a comprehensive evaluation of LLMs' capabilities and limitations in temporal reasoning, highlighting key challenges in handling temporal data accurately."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13377","kind":"arxiv","version":2},"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/2412.13377/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":"2412.13377","created_at":"2026-07-05T11:04:42.913969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13377v2","created_at":"2026-07-05T11:04:42.913969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13377","created_at":"2026-07-05T11:04:42.913969+00:00"},{"alias_kind":"pith_short_12","alias_value":"WH2RK4HEQST3","created_at":"2026-07-05T11:04:42.913969+00:00"},{"alias_kind":"pith_short_16","alias_value":"WH2RK4HEQST323WB","created_at":"2026-07-05T11:04:42.913969+00:00"},{"alias_kind":"pith_short_8","alias_value":"WH2RK4HE","created_at":"2026-07-05T11:04:42.913969+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/WH2RK4HEQST323WBEU5IMKP3GA","json":"https://pith.science/pith/WH2RK4HEQST323WBEU5IMKP3GA.json","graph_json":"https://pith.science/api/pith-number/WH2RK4HEQST323WBEU5IMKP3GA/graph.json","events_json":"https://pith.science/api/pith-number/WH2RK4HEQST323WBEU5IMKP3GA/events.json","paper":"https://pith.science/paper/WH2RK4HE"},"agent_actions":{"view_html":"https://pith.science/pith/WH2RK4HEQST323WBEU5IMKP3GA","download_json":"https://pith.science/pith/WH2RK4HEQST323WBEU5IMKP3GA.json","view_paper":"https://pith.science/paper/WH2RK4HE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13377&json=true","fetch_graph":"https://pith.science/api/pith-number/WH2RK4HEQST323WBEU5IMKP3GA/graph.json","fetch_events":"https://pith.science/api/pith-number/WH2RK4HEQST323WBEU5IMKP3GA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WH2RK4HEQST323WBEU5IMKP3GA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WH2RK4HEQST323WBEU5IMKP3GA/action/storage_attestation","attest_author":"https://pith.science/pith/WH2RK4HEQST323WBEU5IMKP3GA/action/author_attestation","sign_citation":"https://pith.science/pith/WH2RK4HEQST323WBEU5IMKP3GA/action/citation_signature","submit_replication":"https://pith.science/pith/WH2RK4HEQST323WBEU5IMKP3GA/action/replication_record"}},"created_at":"2026-07-05T11:04:42.913969+00:00","updated_at":"2026-07-05T11:04:42.913969+00:00"}