{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6BEEI6KRCQZ44AEH4TKQE6SFN5","short_pith_number":"pith:6BEEI6KR","schema_version":"1.0","canonical_sha256":"f0484479511433ce0087e4d5027a456f6e421c9b658d24b0fad99558ab72a5dc","source":{"kind":"arxiv","id":"2007.08124","version":1},"attestation_state":"computed","paper":{"title":"LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dandan Huang, Hanmeng Liu, Jian Liu, Leyang Cui, Yile Wang, Yue Zhang","submitted_at":"2020-07-16T05:52:16Z","abstract_excerpt":"Machine reading is a fundamental task for testing the capability of natural language understanding, which is closely related to human cognition in many aspects. With the rising of deep learning techniques, algorithmic models rival human performances on simple QA, and thus increasingly challenging machine reading datasets have been proposed. Though various challenges such as evidence integration and commonsense knowledge have been integrated, one of the fundamental capabilities in human reading, namely logical reasoning, is not fully investigated. We build a comprehensive dataset, named LogiQA,"},"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":"2007.08124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-16T05:52:16Z","cross_cats_sorted":[],"title_canon_sha256":"9f75e214ed55f354a366a91fec4759c388c3d68bae7408306347918b0ab0ee54","abstract_canon_sha256":"f4c152ab6d6553f7df94d5220050dc3dad4010e57836becc57adc27dd61c925c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:44.137195Z","signature_b64":"pvd26VUqMmCbeORVcWi4Yw0vUcoWnz0rBKUXYYJhGkWWJc8ycZhRtTXo1oujzBEFpcHBPQjRDkeHGt9ivKDCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0484479511433ce0087e4d5027a456f6e421c9b658d24b0fad99558ab72a5dc","last_reissued_at":"2026-07-05T01:19:44.136689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:44.136689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dandan Huang, Hanmeng Liu, Jian Liu, Leyang Cui, Yile Wang, Yue Zhang","submitted_at":"2020-07-16T05:52:16Z","abstract_excerpt":"Machine reading is a fundamental task for testing the capability of natural language understanding, which is closely related to human cognition in many aspects. With the rising of deep learning techniques, algorithmic models rival human performances on simple QA, and thus increasingly challenging machine reading datasets have been proposed. Though various challenges such as evidence integration and commonsense knowledge have been integrated, one of the fundamental capabilities in human reading, namely logical reasoning, is not fully investigated. We build a comprehensive dataset, named LogiQA,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08124","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/2007.08124/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":"2007.08124","created_at":"2026-07-05T01:19:44.136751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.08124v1","created_at":"2026-07-05T01:19:44.136751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08124","created_at":"2026-07-05T01:19:44.136751+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BEEI6KRCQZ4","created_at":"2026-07-05T01:19:44.136751+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BEEI6KRCQZ44AEH","created_at":"2026-07-05T01:19:44.136751+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BEEI6KR","created_at":"2026-07-05T01:19:44.136751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23238","citing_title":"HOLMES: Evaluating Higher-Order Logical Reasoning in LLMs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18663","citing_title":"RegMix-D: Dynamic Data Mixing via Proxy Training Trajectories","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01612","citing_title":"Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02032","citing_title":"PACE: A Proxy for Agentic Capability Evaluation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25603","citing_title":"Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00103","citing_title":"Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29247","citing_title":"DenseSteer: Steering Small Language Models towards Dense Math Reasoning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01168","citing_title":"Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15640","citing_title":"Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20856","citing_title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2406.10162","citing_title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","ref_index":228,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13751","citing_title":"MIDUS: Memory-Infused Depth Up-Scaling","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2311.16867","citing_title":"The Falcon Series of Open Language Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02188","citing_title":"Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12517","citing_title":"Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05893","citing_title":"Logic-Regularized Verifier Elicits Reasoning from LLMs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10590","citing_title":"Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12397","citing_title":"KoCo: Conditioning Language Model Pre-training on Knowledge Coordinates","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09285","citing_title":"SAGE: A Service Agent Graph-guided Evaluation Benchmark","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05227","citing_title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BEEI6KRCQZ44AEH4TKQE6SFN5","json":"https://pith.science/pith/6BEEI6KRCQZ44AEH4TKQE6SFN5.json","graph_json":"https://pith.science/api/pith-number/6BEEI6KRCQZ44AEH4TKQE6SFN5/graph.json","events_json":"https://pith.science/api/pith-number/6BEEI6KRCQZ44AEH4TKQE6SFN5/events.json","paper":"https://pith.science/paper/6BEEI6KR"},"agent_actions":{"view_html":"https://pith.science/pith/6BEEI6KRCQZ44AEH4TKQE6SFN5","download_json":"https://pith.science/pith/6BEEI6KRCQZ44AEH4TKQE6SFN5.json","view_paper":"https://pith.science/paper/6BEEI6KR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.08124&json=true","fetch_graph":"https://pith.science/api/pith-number/6BEEI6KRCQZ44AEH4TKQE6SFN5/graph.json","fetch_events":"https://pith.science/api/pith-number/6BEEI6KRCQZ44AEH4TKQE6SFN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BEEI6KRCQZ44AEH4TKQE6SFN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BEEI6KRCQZ44AEH4TKQE6SFN5/action/storage_attestation","attest_author":"https://pith.science/pith/6BEEI6KRCQZ44AEH4TKQE6SFN5/action/author_attestation","sign_citation":"https://pith.science/pith/6BEEI6KRCQZ44AEH4TKQE6SFN5/action/citation_signature","submit_replication":"https://pith.science/pith/6BEEI6KRCQZ44AEH4TKQE6SFN5/action/replication_record"}},"created_at":"2026-07-05T01:19:44.136751+00:00","updated_at":"2026-07-05T01:19:44.136751+00:00"}