{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S4AVSFP2GGP4SQU2ADNV5SEZMU","short_pith_number":"pith:S4AVSFP2","schema_version":"1.0","canonical_sha256":"97015915fa319fc9429a00db5ec899653a0fd1f82ccf4940bfbdb64d35f54741","source":{"kind":"arxiv","id":"2306.09841","version":4},"attestation_state":"computed","paper":{"title":"Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Erik Cambria, Fangzhi Xu, Jiawei Han, Jun Liu, Qika Lin, Tianzhe Zhao","submitted_at":"2023-06-16T13:39:35Z","abstract_excerpt":"Logical reasoning consistently plays a fundamental and significant role in the domains of knowledge engineering and artificial intelligence. Recently, Large Language Models (LLMs) have emerged as a noteworthy innovation in natural language processing (NLP). However, the question of whether LLMs can effectively address the task of logical reasoning, which requires gradual cognitive inference similar to human intelligence, remains unanswered. To this end, we aim to bridge this gap and provide comprehensive evaluations in this paper. Firstly, to offer systematic evaluations, we select fifteen typ"},"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":"2306.09841","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-16T13:39:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"acf05028a2585322453900932cbe05db92daa5cc7465ac33c19c33311476bc18","abstract_canon_sha256":"0135b4be22e6048feffe5488e5ac68ad5eeb2cd3cf380ed1cd04807fd0603a2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:54.069719Z","signature_b64":"0WnX+GAWYEVeCSgd5e7pVreJLb3gTwNjoiF+iAKIXIzjmy4eW9TdpWMnAly8HHHZmrMZNsK40ImegTwRfktxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97015915fa319fc9429a00db5ec899653a0fd1f82ccf4940bfbdb64d35f54741","last_reissued_at":"2026-07-05T09:06:54.069262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:54.069262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Erik Cambria, Fangzhi Xu, Jiawei Han, Jun Liu, Qika Lin, Tianzhe Zhao","submitted_at":"2023-06-16T13:39:35Z","abstract_excerpt":"Logical reasoning consistently plays a fundamental and significant role in the domains of knowledge engineering and artificial intelligence. Recently, Large Language Models (LLMs) have emerged as a noteworthy innovation in natural language processing (NLP). However, the question of whether LLMs can effectively address the task of logical reasoning, which requires gradual cognitive inference similar to human intelligence, remains unanswered. To this end, we aim to bridge this gap and provide comprehensive evaluations in this paper. Firstly, to offer systematic evaluations, we select fifteen typ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09841","kind":"arxiv","version":4},"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/2306.09841/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":"2306.09841","created_at":"2026-07-05T09:06:54.069322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09841v4","created_at":"2026-07-05T09:06:54.069322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09841","created_at":"2026-07-05T09:06:54.069322+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4AVSFP2GGP4","created_at":"2026-07-05T09:06:54.069322+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4AVSFP2GGP4SQU2","created_at":"2026-07-05T09:06:54.069322+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4AVSFP2","created_at":"2026-07-05T09:06:54.069322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23063","citing_title":"Math Natural Language Inference: this should be easy!","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4AVSFP2GGP4SQU2ADNV5SEZMU","json":"https://pith.science/pith/S4AVSFP2GGP4SQU2ADNV5SEZMU.json","graph_json":"https://pith.science/api/pith-number/S4AVSFP2GGP4SQU2ADNV5SEZMU/graph.json","events_json":"https://pith.science/api/pith-number/S4AVSFP2GGP4SQU2ADNV5SEZMU/events.json","paper":"https://pith.science/paper/S4AVSFP2"},"agent_actions":{"view_html":"https://pith.science/pith/S4AVSFP2GGP4SQU2ADNV5SEZMU","download_json":"https://pith.science/pith/S4AVSFP2GGP4SQU2ADNV5SEZMU.json","view_paper":"https://pith.science/paper/S4AVSFP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09841&json=true","fetch_graph":"https://pith.science/api/pith-number/S4AVSFP2GGP4SQU2ADNV5SEZMU/graph.json","fetch_events":"https://pith.science/api/pith-number/S4AVSFP2GGP4SQU2ADNV5SEZMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4AVSFP2GGP4SQU2ADNV5SEZMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4AVSFP2GGP4SQU2ADNV5SEZMU/action/storage_attestation","attest_author":"https://pith.science/pith/S4AVSFP2GGP4SQU2ADNV5SEZMU/action/author_attestation","sign_citation":"https://pith.science/pith/S4AVSFP2GGP4SQU2ADNV5SEZMU/action/citation_signature","submit_replication":"https://pith.science/pith/S4AVSFP2GGP4SQU2ADNV5SEZMU/action/replication_record"}},"created_at":"2026-07-05T09:06:54.069322+00:00","updated_at":"2026-07-05T09:06:54.069322+00:00"}