{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BHHSSAKJBP7MKXG7OSIPQ5FQAO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8d1fd352ef6346ceca90872c5dceb85bc36290d470e0c7110763e44f8bcc16a3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T08:44:41Z","title_canon_sha256":"0d8c2f5cab4b1290b38ebcd02eeaf76e56c186cdd332ac155e42a263bbd9a157"},"schema_version":"1.0","source":{"id":"2306.08952","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08952","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08952v2","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08952","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"pith_short_12","alias_value":"BHHSSAKJBP7M","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"pith_short_16","alias_value":"BHHSSAKJBP7MKXG7","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"pith_short_8","alias_value":"BHHSSAKJ","created_at":"2026-07-05T06:24:50Z"}],"graph_snapshots":[{"event_id":"sha256:6a12feaf96caedec59e885cd46b39818fe99ddd188abcb40c2f1a2747aacc1c5","target":"graph","created_at":"2026-07-05T06:24:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.08952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning about time is of fundamental importance. Many facts are time-dependent. For example, athletes change teams from time to time, and different government officials are elected periodically. Previous time-dependent question answering (QA) datasets tend to be biased in either their coverage of time spans or question types. In this paper, we introduce a comprehensive probing dataset \\tempreason to evaluate the temporal reasoning capability of large language models. Our dataset includes questions of three temporal reasoning levels. In addition, we also propose a novel learning framework to ","authors_text":"Hwee Tou Ng, Lidong Bing, Qingyu Tan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T08:44:41Z","title":"Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08952","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7091d62274c1e2fb57794d1c63f9aade614d96966c0fc20ebebc5d2406331a9c","target":"record","created_at":"2026-07-05T06:24:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8d1fd352ef6346ceca90872c5dceb85bc36290d470e0c7110763e44f8bcc16a3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T08:44:41Z","title_canon_sha256":"0d8c2f5cab4b1290b38ebcd02eeaf76e56c186cdd332ac155e42a263bbd9a157"},"schema_version":"1.0","source":{"id":"2306.08952","kind":"arxiv","version":2}},"canonical_sha256":"09cf2901490bfec55cdf7490f874b003aa248ff51772cfbb9c30e3ff43a8a5eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09cf2901490bfec55cdf7490f874b003aa248ff51772cfbb9c30e3ff43a8a5eb","first_computed_at":"2026-07-05T06:24:50.742138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:50.742138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KuiLZGV2cuEF93aUpEzy4b20Lr+KinDgjf/asl3c8d4YT28fsEjxye5jZDYXLa/cuX2CNjmE8OXf4WpC+x5aDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:50.742568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08952","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7091d62274c1e2fb57794d1c63f9aade614d96966c0fc20ebebc5d2406331a9c","sha256:6a12feaf96caedec59e885cd46b39818fe99ddd188abcb40c2f1a2747aacc1c5"],"state_sha256":"c1df5412726697777e7afcdd264dbbddd50cdb72bf95387a2c1c7ca90fb3e9d1"}