{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HHPHGIBAHOTREUMRZ5B4CZSCW2","short_pith_number":"pith:HHPHGIBA","schema_version":"1.0","canonical_sha256":"39de7320203ba7125191cf43c16642b6bc2f9f8907b4216062f0d3bc0d5ddc22","source":{"kind":"arxiv","id":"2406.09072","version":1},"attestation_state":"computed","paper":{"title":"Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Juntao Li, Jun Zhang, Min Zhang, Pan Zhou, Tong Zhu, Xiaoye Qu, Yan Bowen, Yu Cheng, Zhaochen Su","submitted_at":"2024-06-13T12:56:21Z","abstract_excerpt":"Temporal reasoning is fundamental for large language models (LLMs) to comprehend the world. Current temporal reasoning datasets are limited to questions about single or isolated events, falling short in mirroring the realistic temporal characteristics involving concurrent nature and intricate temporal interconnections. In this paper, we introduce CoTempQA, a comprehensive co-temporal Question Answering (QA) benchmark containing four co-temporal scenarios (Equal, Overlap, During, Mix) with 4,748 samples for evaluating the co-temporal comprehension and reasoning abilities of LLMs. Our extensive "},"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":"2406.09072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T12:56:21Z","cross_cats_sorted":[],"title_canon_sha256":"f57e20427a0347400449d91b6b75e37bcdb19cf534458393221ccf6e8ce38a92","abstract_canon_sha256":"78df7802bb72fa7ae12da4f926b2bdaf2b699832ca5112c404b5c705a9641f69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:27.686437Z","signature_b64":"l77UxQCDVNiHXX/p537cPjwQ5zy/8t2/7I2+9LP8MfokarYlQrF5r2//L9qS+9lrR2rWZNtoTXDt2m4eWk3QBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39de7320203ba7125191cf43c16642b6bc2f9f8907b4216062f0d3bc0d5ddc22","last_reissued_at":"2026-07-05T08:31:27.685864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:27.685864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Juntao Li, Jun Zhang, Min Zhang, Pan Zhou, Tong Zhu, Xiaoye Qu, Yan Bowen, Yu Cheng, Zhaochen Su","submitted_at":"2024-06-13T12:56:21Z","abstract_excerpt":"Temporal reasoning is fundamental for large language models (LLMs) to comprehend the world. Current temporal reasoning datasets are limited to questions about single or isolated events, falling short in mirroring the realistic temporal characteristics involving concurrent nature and intricate temporal interconnections. In this paper, we introduce CoTempQA, a comprehensive co-temporal Question Answering (QA) benchmark containing four co-temporal scenarios (Equal, Overlap, During, Mix) with 4,748 samples for evaluating the co-temporal comprehension and reasoning abilities of LLMs. Our extensive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09072","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/2406.09072/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":"2406.09072","created_at":"2026-07-05T08:31:27.685925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09072v1","created_at":"2026-07-05T08:31:27.685925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09072","created_at":"2026-07-05T08:31:27.685925+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHPHGIBAHOTR","created_at":"2026-07-05T08:31:27.685925+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHPHGIBAHOTREUMR","created_at":"2026-07-05T08:31:27.685925+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHPHGIBA","created_at":"2026-07-05T08:31:27.685925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":222,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13052","citing_title":"RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHPHGIBAHOTREUMRZ5B4CZSCW2","json":"https://pith.science/pith/HHPHGIBAHOTREUMRZ5B4CZSCW2.json","graph_json":"https://pith.science/api/pith-number/HHPHGIBAHOTREUMRZ5B4CZSCW2/graph.json","events_json":"https://pith.science/api/pith-number/HHPHGIBAHOTREUMRZ5B4CZSCW2/events.json","paper":"https://pith.science/paper/HHPHGIBA"},"agent_actions":{"view_html":"https://pith.science/pith/HHPHGIBAHOTREUMRZ5B4CZSCW2","download_json":"https://pith.science/pith/HHPHGIBAHOTREUMRZ5B4CZSCW2.json","view_paper":"https://pith.science/paper/HHPHGIBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09072&json=true","fetch_graph":"https://pith.science/api/pith-number/HHPHGIBAHOTREUMRZ5B4CZSCW2/graph.json","fetch_events":"https://pith.science/api/pith-number/HHPHGIBAHOTREUMRZ5B4CZSCW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHPHGIBAHOTREUMRZ5B4CZSCW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHPHGIBAHOTREUMRZ5B4CZSCW2/action/storage_attestation","attest_author":"https://pith.science/pith/HHPHGIBAHOTREUMRZ5B4CZSCW2/action/author_attestation","sign_citation":"https://pith.science/pith/HHPHGIBAHOTREUMRZ5B4CZSCW2/action/citation_signature","submit_replication":"https://pith.science/pith/HHPHGIBAHOTREUMRZ5B4CZSCW2/action/replication_record"}},"created_at":"2026-07-05T08:31:27.685925+00:00","updated_at":"2026-07-05T08:31:27.685925+00:00"}