{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OQRT2IZ3JE6B2DJYQ7PXEFB4TV","short_pith_number":"pith:OQRT2IZ3","schema_version":"1.0","canonical_sha256":"74233d233b493c1d0d3887df72143c9d53914b98f1c449714f7f9af13a30aecc","source":{"kind":"arxiv","id":"2310.09107","version":2},"attestation_state":"computed","paper":{"title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hanmeng Liu, Ruoxi Ning, Xiaozhang Liu, Xiulai Li, Yiran Ding, Yue Zhang, Zhiyang Teng","submitted_at":"2023-10-13T13:52:15Z","abstract_excerpt":"Large language models (LLMs) have shown significant general language understanding abilities. However, there has been a scarcity of attempts to assess the logical reasoning capacities of these LLMs, an essential facet of natural language understanding. To encourage further investigation in this area, we introduce GLoRE, a General Logical Reasoning Evaluation platform that not only consolidates diverse datasets but also standardizes them into a unified format suitable for evaluating large language models across zero-shot and few-shot scenarios. Our experimental results show that compared to the"},"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":"2310.09107","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T13:52:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09742a9b82406b39d998d6fee2cefab277720d9a4a06955f958d0a3493fae2ed","abstract_canon_sha256":"ad4fade8fa572c4da81337afcc7d04435a0a912f05a09d237893b88cb27683a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:18.940642Z","signature_b64":"ZmiOwdpJ4nHdj1TA0HrzSpzwqK6wTSqFESwhYFUjme1YGt6uJIhIsrXDcc9kUUnt/11i9M8IKz/6zcJ/LK4iBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74233d233b493c1d0d3887df72143c9d53914b98f1c449714f7f9af13a30aecc","last_reissued_at":"2026-07-05T10:51:18.940143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:18.940143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hanmeng Liu, Ruoxi Ning, Xiaozhang Liu, Xiulai Li, Yiran Ding, Yue Zhang, Zhiyang Teng","submitted_at":"2023-10-13T13:52:15Z","abstract_excerpt":"Large language models (LLMs) have shown significant general language understanding abilities. However, there has been a scarcity of attempts to assess the logical reasoning capacities of these LLMs, an essential facet of natural language understanding. To encourage further investigation in this area, we introduce GLoRE, a General Logical Reasoning Evaluation platform that not only consolidates diverse datasets but also standardizes them into a unified format suitable for evaluating large language models across zero-shot and few-shot scenarios. Our experimental results show that compared to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09107","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/2310.09107/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":"2310.09107","created_at":"2026-07-05T10:51:18.940199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09107v2","created_at":"2026-07-05T10:51:18.940199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09107","created_at":"2026-07-05T10:51:18.940199+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQRT2IZ3JE6B","created_at":"2026-07-05T10:51:18.940199+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQRT2IZ3JE6B2DJY","created_at":"2026-07-05T10:51:18.940199+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQRT2IZ3","created_at":"2026-07-05T10:51:18.940199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06040","citing_title":"Novelty-based Tree-of-Thought Search for LLM Reasoning and Planning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQRT2IZ3JE6B2DJYQ7PXEFB4TV","json":"https://pith.science/pith/OQRT2IZ3JE6B2DJYQ7PXEFB4TV.json","graph_json":"https://pith.science/api/pith-number/OQRT2IZ3JE6B2DJYQ7PXEFB4TV/graph.json","events_json":"https://pith.science/api/pith-number/OQRT2IZ3JE6B2DJYQ7PXEFB4TV/events.json","paper":"https://pith.science/paper/OQRT2IZ3"},"agent_actions":{"view_html":"https://pith.science/pith/OQRT2IZ3JE6B2DJYQ7PXEFB4TV","download_json":"https://pith.science/pith/OQRT2IZ3JE6B2DJYQ7PXEFB4TV.json","view_paper":"https://pith.science/paper/OQRT2IZ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09107&json=true","fetch_graph":"https://pith.science/api/pith-number/OQRT2IZ3JE6B2DJYQ7PXEFB4TV/graph.json","fetch_events":"https://pith.science/api/pith-number/OQRT2IZ3JE6B2DJYQ7PXEFB4TV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQRT2IZ3JE6B2DJYQ7PXEFB4TV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQRT2IZ3JE6B2DJYQ7PXEFB4TV/action/storage_attestation","attest_author":"https://pith.science/pith/OQRT2IZ3JE6B2DJYQ7PXEFB4TV/action/author_attestation","sign_citation":"https://pith.science/pith/OQRT2IZ3JE6B2DJYQ7PXEFB4TV/action/citation_signature","submit_replication":"https://pith.science/pith/OQRT2IZ3JE6B2DJYQ7PXEFB4TV/action/replication_record"}},"created_at":"2026-07-05T10:51:18.940199+00:00","updated_at":"2026-07-05T10:51:18.940199+00:00"}