{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2IVF5LKFEH5PG6TZ5IQMXVPR4C","short_pith_number":"pith:2IVF5LKF","schema_version":"1.0","canonical_sha256":"d22a5ead4521faf37a79ea20cbd5f1e08134d4cfc8228af62289fa0b5137b64e","source":{"kind":"arxiv","id":"2002.04326","version":3},"attestation_state":"computed","paper":{"title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiashi Feng, Weihao Yu, Yanfei Dong, Zihang Jiang","submitted_at":"2020-02-11T11:54:29Z","abstract_excerpt":"Recent powerful pre-trained language models have achieved remarkable performance on most of the popular datasets for reading comprehension. It is time to introduce more challenging datasets to push the development of this field towards more comprehensive reasoning of text. In this paper, we introduce a new Reading Comprehension dataset requiring logical reasoning (ReClor) extracted from standardized graduate admission examinations. As earlier studies suggest, human-annotated datasets usually contain biases, which are often exploited by models to achieve high accuracy without truly understandin"},"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":"2002.04326","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-11T11:54:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"50c155c5b83de52e67fd5780e8f0ded8849350628b9788641a8c53575edf571a","abstract_canon_sha256":"1824608ef40e93152bd80847f3fb9c90b9380369559fabeb50203a874b80a2be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:03.057913Z","signature_b64":"6dpjHpNoZjl+oKXG2KmT7y+OxwPESRWCWgZfvhKnqjjtetx8GRXMTq7mOHaPd6JPjTjXXB7QceAwvYkZLOhaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d22a5ead4521faf37a79ea20cbd5f1e08134d4cfc8228af62289fa0b5137b64e","last_reissued_at":"2026-07-05T01:29:03.057435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:03.057435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiashi Feng, Weihao Yu, Yanfei Dong, Zihang Jiang","submitted_at":"2020-02-11T11:54:29Z","abstract_excerpt":"Recent powerful pre-trained language models have achieved remarkable performance on most of the popular datasets for reading comprehension. It is time to introduce more challenging datasets to push the development of this field towards more comprehensive reasoning of text. In this paper, we introduce a new Reading Comprehension dataset requiring logical reasoning (ReClor) extracted from standardized graduate admission examinations. As earlier studies suggest, human-annotated datasets usually contain biases, which are often exploited by models to achieve high accuracy without truly understandin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04326","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/2002.04326/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":"2002.04326","created_at":"2026-07-05T01:29:03.057494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.04326v3","created_at":"2026-07-05T01:29:03.057494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04326","created_at":"2026-07-05T01:29:03.057494+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IVF5LKFEH5P","created_at":"2026-07-05T01:29:03.057494+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IVF5LKFEH5PG6TZ","created_at":"2026-07-05T01:29:03.057494+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IVF5LKF","created_at":"2026-07-05T01:29:03.057494+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23965","citing_title":"LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23965","citing_title":"LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03237","citing_title":"The Persuasion Paradox: When LLM Explanations Fail to Improve Human-AI Team Performance","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09034","citing_title":"The nextAI Solution to the NeurIPS 2023 LLM Efficiency Challenge","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02442","citing_title":"Measuring AI Reasoning: A Guide for Researchers","ref_index":129,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2IVF5LKFEH5PG6TZ5IQMXVPR4C","json":"https://pith.science/pith/2IVF5LKFEH5PG6TZ5IQMXVPR4C.json","graph_json":"https://pith.science/api/pith-number/2IVF5LKFEH5PG6TZ5IQMXVPR4C/graph.json","events_json":"https://pith.science/api/pith-number/2IVF5LKFEH5PG6TZ5IQMXVPR4C/events.json","paper":"https://pith.science/paper/2IVF5LKF"},"agent_actions":{"view_html":"https://pith.science/pith/2IVF5LKFEH5PG6TZ5IQMXVPR4C","download_json":"https://pith.science/pith/2IVF5LKFEH5PG6TZ5IQMXVPR4C.json","view_paper":"https://pith.science/paper/2IVF5LKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.04326&json=true","fetch_graph":"https://pith.science/api/pith-number/2IVF5LKFEH5PG6TZ5IQMXVPR4C/graph.json","fetch_events":"https://pith.science/api/pith-number/2IVF5LKFEH5PG6TZ5IQMXVPR4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IVF5LKFEH5PG6TZ5IQMXVPR4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IVF5LKFEH5PG6TZ5IQMXVPR4C/action/storage_attestation","attest_author":"https://pith.science/pith/2IVF5LKFEH5PG6TZ5IQMXVPR4C/action/author_attestation","sign_citation":"https://pith.science/pith/2IVF5LKFEH5PG6TZ5IQMXVPR4C/action/citation_signature","submit_replication":"https://pith.science/pith/2IVF5LKFEH5PG6TZ5IQMXVPR4C/action/replication_record"}},"created_at":"2026-07-05T01:29:03.057494+00:00","updated_at":"2026-07-05T01:29:03.057494+00:00"}