{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PAR64MGJLCBK4PH5SGLPKPIXTM","short_pith_number":"pith:PAR64MGJ","schema_version":"1.0","canonical_sha256":"7823ee30c95882ae3cfd9196f53d179b08502c1c36c38c6dc53cb7021741db2b","source":{"kind":"arxiv","id":"2401.00757","version":3},"attestation_state":"computed","paper":{"title":"LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LO"],"primary_cat":"cs.SE","authors_text":"Jen-tse Huang, Michael R. Lyu, Pinjia He, Wenxiang Jiao, Wenxuan Wang, Yiliu Yang, Youliang Yuan, Yuxuan Wan","submitted_at":"2024-01-01T13:53:53Z","abstract_excerpt":"We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) such as ChatGPT and GPT-4. Despite LLMs' prowess in tasks like writing assistance, code generation, and machine translation, assessing their ability to reason has been challenging. Traditional evaluations often prioritize accuracy on downstream tasks over direct assessments of reasoning processes. LogicAsker addresses this gap by employing a set of atomic reasoning skills grounded in propositional and predicate logic to systematically examine and improve 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":"2401.00757","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-01T13:53:53Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LO"],"title_canon_sha256":"1bf8e7f5a739c1ab0ad6cd5ca1814cbd25cffdbef4592172faad73d75944da1f","abstract_canon_sha256":"6955d6b58555a9c1268ddf0ad2ba6984c65b046ddab183ecbac4f719c4eb05f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:36.286129Z","signature_b64":"P0A5GcpWIqCEgFELzf0Xr0yAncPRRb/wTCMJuc6t0hEG18cc72i0kG86gpqfOMT0j3SXWsqjpSo2bJx3zyKnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7823ee30c95882ae3cfd9196f53d179b08502c1c36c38c6dc53cb7021741db2b","last_reissued_at":"2026-07-05T09:17:36.285683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:36.285683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LO"],"primary_cat":"cs.SE","authors_text":"Jen-tse Huang, Michael R. Lyu, Pinjia He, Wenxiang Jiao, Wenxuan Wang, Yiliu Yang, Youliang Yuan, Yuxuan Wan","submitted_at":"2024-01-01T13:53:53Z","abstract_excerpt":"We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) such as ChatGPT and GPT-4. Despite LLMs' prowess in tasks like writing assistance, code generation, and machine translation, assessing their ability to reason has been challenging. Traditional evaluations often prioritize accuracy on downstream tasks over direct assessments of reasoning processes. LogicAsker addresses this gap by employing a set of atomic reasoning skills grounded in propositional and predicate logic to systematically examine and improve the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00757","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/2401.00757/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":"2401.00757","created_at":"2026-07-05T09:17:36.285748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00757v3","created_at":"2026-07-05T09:17:36.285748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00757","created_at":"2026-07-05T09:17:36.285748+00:00"},{"alias_kind":"pith_short_12","alias_value":"PAR64MGJLCBK","created_at":"2026-07-05T09:17:36.285748+00:00"},{"alias_kind":"pith_short_16","alias_value":"PAR64MGJLCBK4PH5","created_at":"2026-07-05T09:17:36.285748+00:00"},{"alias_kind":"pith_short_8","alias_value":"PAR64MGJ","created_at":"2026-07-05T09:17:36.285748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21215","citing_title":"Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PAR64MGJLCBK4PH5SGLPKPIXTM","json":"https://pith.science/pith/PAR64MGJLCBK4PH5SGLPKPIXTM.json","graph_json":"https://pith.science/api/pith-number/PAR64MGJLCBK4PH5SGLPKPIXTM/graph.json","events_json":"https://pith.science/api/pith-number/PAR64MGJLCBK4PH5SGLPKPIXTM/events.json","paper":"https://pith.science/paper/PAR64MGJ"},"agent_actions":{"view_html":"https://pith.science/pith/PAR64MGJLCBK4PH5SGLPKPIXTM","download_json":"https://pith.science/pith/PAR64MGJLCBK4PH5SGLPKPIXTM.json","view_paper":"https://pith.science/paper/PAR64MGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00757&json=true","fetch_graph":"https://pith.science/api/pith-number/PAR64MGJLCBK4PH5SGLPKPIXTM/graph.json","fetch_events":"https://pith.science/api/pith-number/PAR64MGJLCBK4PH5SGLPKPIXTM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PAR64MGJLCBK4PH5SGLPKPIXTM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PAR64MGJLCBK4PH5SGLPKPIXTM/action/storage_attestation","attest_author":"https://pith.science/pith/PAR64MGJLCBK4PH5SGLPKPIXTM/action/author_attestation","sign_citation":"https://pith.science/pith/PAR64MGJLCBK4PH5SGLPKPIXTM/action/citation_signature","submit_replication":"https://pith.science/pith/PAR64MGJLCBK4PH5SGLPKPIXTM/action/replication_record"}},"created_at":"2026-07-05T09:17:36.285748+00:00","updated_at":"2026-07-05T09:17:36.285748+00:00"}