{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MG6FPBP6EVEQAPKU3ISLUBCJ6W","short_pith_number":"pith:MG6FPBP6","schema_version":"1.0","canonical_sha256":"61bc5785fe2549003d54da24ba0449f5a91ec5bfd81ef22c48b6a87cfb02f1d7","source":{"kind":"arxiv","id":"2406.02787","version":1},"attestation_state":"computed","paper":{"title":"Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haochen Xue, Jindong Wang, Kaijie Zhu, Lingyao Li, Lizhou Fan, Mingyu Jin, Shuhang Lin, Wenyue Hua, Yongfeng Zhang, Zelong Li","submitted_at":"2024-06-04T21:25:06Z","abstract_excerpt":"This study intends to systematically disentangle pure logic reasoning and text understanding by investigating the contrast across abstract and contextualized logical problems from a comprehensive set of domains. We explore whether LLMs demonstrate genuine reasoning capabilities across various domains when the underlying logical structure remains constant. We focus on two main questions (1) Can abstract logical problems alone accurately benchmark an LLM's reasoning ability in real-world scenarios, disentangled from contextual support in practical settings? (2) Does fine-tuning LLMs on abstract "},"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":"2406.02787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T21:25:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"29e0c1c610d2f465a18570ae36489dd59510bb4138ea61b1f911bb86a04fb849","abstract_canon_sha256":"d452c39cbfce8b0e79e5d9aadd129376888249f3d92b71f7ed3f031307d19419"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:30.368604Z","signature_b64":"ReiqSyvcXaWrYE9GRiq5fIKAT0zl95QVucjqctRfnSa4JTBSnMUjudHUHPYKAP86MZBb5x78mQ5f+l0rWFywBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61bc5785fe2549003d54da24ba0449f5a91ec5bfd81ef22c48b6a87cfb02f1d7","last_reissued_at":"2026-07-05T08:27:30.368103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:30.368103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haochen Xue, Jindong Wang, Kaijie Zhu, Lingyao Li, Lizhou Fan, Mingyu Jin, Shuhang Lin, Wenyue Hua, Yongfeng Zhang, Zelong Li","submitted_at":"2024-06-04T21:25:06Z","abstract_excerpt":"This study intends to systematically disentangle pure logic reasoning and text understanding by investigating the contrast across abstract and contextualized logical problems from a comprehensive set of domains. We explore whether LLMs demonstrate genuine reasoning capabilities across various domains when the underlying logical structure remains constant. We focus on two main questions (1) Can abstract logical problems alone accurately benchmark an LLM's reasoning ability in real-world scenarios, disentangled from contextual support in practical settings? (2) Does fine-tuning LLMs on abstract "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02787","kind":"arxiv","version":1},"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/2406.02787/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":"2406.02787","created_at":"2026-07-05T08:27:30.368161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02787v1","created_at":"2026-07-05T08:27:30.368161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02787","created_at":"2026-07-05T08:27:30.368161+00:00"},{"alias_kind":"pith_short_12","alias_value":"MG6FPBP6EVEQ","created_at":"2026-07-05T08:27:30.368161+00:00"},{"alias_kind":"pith_short_16","alias_value":"MG6FPBP6EVEQAPKU","created_at":"2026-07-05T08:27:30.368161+00:00"},{"alias_kind":"pith_short_8","alias_value":"MG6FPBP6","created_at":"2026-07-05T08:27:30.368161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07642","citing_title":"Do VLMs See What Sensors Feel? A Scalable Expert-Guided Design for Wheelchair Accessibility Assessment from Street View","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2406.12708","citing_title":"AgentReview: Exploring Peer Review Dynamics with LLM Agents","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01608","citing_title":"From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MG6FPBP6EVEQAPKU3ISLUBCJ6W","json":"https://pith.science/pith/MG6FPBP6EVEQAPKU3ISLUBCJ6W.json","graph_json":"https://pith.science/api/pith-number/MG6FPBP6EVEQAPKU3ISLUBCJ6W/graph.json","events_json":"https://pith.science/api/pith-number/MG6FPBP6EVEQAPKU3ISLUBCJ6W/events.json","paper":"https://pith.science/paper/MG6FPBP6"},"agent_actions":{"view_html":"https://pith.science/pith/MG6FPBP6EVEQAPKU3ISLUBCJ6W","download_json":"https://pith.science/pith/MG6FPBP6EVEQAPKU3ISLUBCJ6W.json","view_paper":"https://pith.science/paper/MG6FPBP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02787&json=true","fetch_graph":"https://pith.science/api/pith-number/MG6FPBP6EVEQAPKU3ISLUBCJ6W/graph.json","fetch_events":"https://pith.science/api/pith-number/MG6FPBP6EVEQAPKU3ISLUBCJ6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MG6FPBP6EVEQAPKU3ISLUBCJ6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MG6FPBP6EVEQAPKU3ISLUBCJ6W/action/storage_attestation","attest_author":"https://pith.science/pith/MG6FPBP6EVEQAPKU3ISLUBCJ6W/action/author_attestation","sign_citation":"https://pith.science/pith/MG6FPBP6EVEQAPKU3ISLUBCJ6W/action/citation_signature","submit_replication":"https://pith.science/pith/MG6FPBP6EVEQAPKU3ISLUBCJ6W/action/replication_record"}},"created_at":"2026-07-05T08:27:30.368161+00:00","updated_at":"2026-07-05T08:27:30.368161+00:00"}