{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6G764Q6CNOG4XEOO2SNL3ZDJWO","short_pith_number":"pith:6G764Q6C","schema_version":"1.0","canonical_sha256":"f1bfee43c26b8dcb91ced49abde469b3bf5c4c948ceb043399af580f9b06f865","source":{"kind":"arxiv","id":"2310.00835","version":3},"attestation_state":"computed","paper":{"title":"TRAM: Benchmarking Temporal Reasoning for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yun Zhao, Yuqing Wang","submitted_at":"2023-10-02T00:59:07Z","abstract_excerpt":"Reasoning about time is essential for understanding the nuances of events described in natural language. Previous research on this topic has been limited in scope, characterized by a lack of standardized benchmarks that would allow for consistent evaluations across different studies. In this paper, we introduce TRAM, a temporal reasoning benchmark composed of ten datasets, encompassing various temporal aspects of events such as order, arithmetic, frequency, and duration, designed to facilitate a comprehensive evaluation of the TeR capabilities of large language models (LLMs). We evaluate popul"},"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":"2310.00835","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T00:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"771b00439f6f1e399439fdd945f9c00e09953f62e9d664c7192996d5675712ff","abstract_canon_sha256":"3e2d61e18b24a471e1f7db273e8f2520a2e0b9027f1514081347bd9ba1c9fef3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:28.922356Z","signature_b64":"6Y0s31/R6SG7ptj0fF/L33XHKfQ6USictvlAGJqRqdH6/qHHRMOhxa3gXrDD7rTLV+0gNqCYFAVAIHMzQoETBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1bfee43c26b8dcb91ced49abde469b3bf5c4c948ceb043399af580f9b06f865","last_reissued_at":"2026-07-05T08:25:28.921915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:28.921915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRAM: Benchmarking Temporal Reasoning for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yun Zhao, Yuqing Wang","submitted_at":"2023-10-02T00:59:07Z","abstract_excerpt":"Reasoning about time is essential for understanding the nuances of events described in natural language. Previous research on this topic has been limited in scope, characterized by a lack of standardized benchmarks that would allow for consistent evaluations across different studies. In this paper, we introduce TRAM, a temporal reasoning benchmark composed of ten datasets, encompassing various temporal aspects of events such as order, arithmetic, frequency, and duration, designed to facilitate a comprehensive evaluation of the TeR capabilities of large language models (LLMs). We evaluate popul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00835","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/2310.00835/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":"2310.00835","created_at":"2026-07-05T08:25:28.921981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00835v3","created_at":"2026-07-05T08:25:28.921981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00835","created_at":"2026-07-05T08:25:28.921981+00:00"},{"alias_kind":"pith_short_12","alias_value":"6G764Q6CNOG4","created_at":"2026-07-05T08:25:28.921981+00:00"},{"alias_kind":"pith_short_16","alias_value":"6G764Q6CNOG4XEOO","created_at":"2026-07-05T08:25:28.921981+00:00"},{"alias_kind":"pith_short_8","alias_value":"6G764Q6C","created_at":"2026-07-05T08:25:28.921981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"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":250,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05194","citing_title":"Temporal Preference Concepts and their Functions in a Large Language Model","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25902","citing_title":"Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing","ref_index":22,"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":79,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17753","citing_title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","ref_index":156,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6G764Q6CNOG4XEOO2SNL3ZDJWO","json":"https://pith.science/pith/6G764Q6CNOG4XEOO2SNL3ZDJWO.json","graph_json":"https://pith.science/api/pith-number/6G764Q6CNOG4XEOO2SNL3ZDJWO/graph.json","events_json":"https://pith.science/api/pith-number/6G764Q6CNOG4XEOO2SNL3ZDJWO/events.json","paper":"https://pith.science/paper/6G764Q6C"},"agent_actions":{"view_html":"https://pith.science/pith/6G764Q6CNOG4XEOO2SNL3ZDJWO","download_json":"https://pith.science/pith/6G764Q6CNOG4XEOO2SNL3ZDJWO.json","view_paper":"https://pith.science/paper/6G764Q6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00835&json=true","fetch_graph":"https://pith.science/api/pith-number/6G764Q6CNOG4XEOO2SNL3ZDJWO/graph.json","fetch_events":"https://pith.science/api/pith-number/6G764Q6CNOG4XEOO2SNL3ZDJWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6G764Q6CNOG4XEOO2SNL3ZDJWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6G764Q6CNOG4XEOO2SNL3ZDJWO/action/storage_attestation","attest_author":"https://pith.science/pith/6G764Q6CNOG4XEOO2SNL3ZDJWO/action/author_attestation","sign_citation":"https://pith.science/pith/6G764Q6CNOG4XEOO2SNL3ZDJWO/action/citation_signature","submit_replication":"https://pith.science/pith/6G764Q6CNOG4XEOO2SNL3ZDJWO/action/replication_record"}},"created_at":"2026-07-05T08:25:28.921981+00:00","updated_at":"2026-07-05T08:25:28.921981+00:00"}