{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PXYAK2CVKMCCL4D347J7HO3TFE","short_pith_number":"pith:PXYAK2CV","schema_version":"1.0","canonical_sha256":"7df0056855530425f07be7d3f3bb732906d952986bf8e420f5f58cc32c0eeb6f","source":{"kind":"arxiv","id":"2505.11854","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Logical Reasoning Abilities of Large Reasoning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chaoli Zhang, Hanmeng Liu, Xiaozhang Liu, Yiran Ding, Yue Zhang, Zhizhang Fu","submitted_at":"2025-05-17T05:36:14Z","abstract_excerpt":"Large reasoning models, often post-trained on long chain-of-thought (long CoT) data with reinforcement learning, achieve state-of-the-art performance on mathematical, coding, and domain-specific reasoning benchmarks. However, their logical reasoning capabilities - fundamental to human cognition and independent of domain knowledge - remain understudied. To address this gap, we introduce LogiEval, a holistic benchmark for evaluating logical reasoning in large reasoning models. LogiEval spans diverse reasoning types (deductive, inductive, analogical, and abductive) and task formats (e.g., logical"},"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":"2505.11854","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T05:36:14Z","cross_cats_sorted":[],"title_canon_sha256":"2a784a7d295f104929be54320c8efd9f0b6c7abeb41ca3cf89af66720791a00d","abstract_canon_sha256":"a914afa63ef3aec64d0c3bbb30e9f7fda38e73517a5bc9198341bf2ce854993c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:53.216432Z","signature_b64":"QDnNsj7E9apnyU62zHnCs0Oek/1Y9ztlbnVbGFKrPPoUamfsOnyVJK446FLyeBnbsJGo0w7jmYqfC5e2EBaTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7df0056855530425f07be7d3f3bb732906d952986bf8e420f5f58cc32c0eeb6f","last_reissued_at":"2026-07-05T11:04:53.215893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:53.215893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Logical Reasoning Abilities of Large Reasoning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chaoli Zhang, Hanmeng Liu, Xiaozhang Liu, Yiran Ding, Yue Zhang, Zhizhang Fu","submitted_at":"2025-05-17T05:36:14Z","abstract_excerpt":"Large reasoning models, often post-trained on long chain-of-thought (long CoT) data with reinforcement learning, achieve state-of-the-art performance on mathematical, coding, and domain-specific reasoning benchmarks. However, their logical reasoning capabilities - fundamental to human cognition and independent of domain knowledge - remain understudied. To address this gap, we introduce LogiEval, a holistic benchmark for evaluating logical reasoning in large reasoning models. LogiEval spans diverse reasoning types (deductive, inductive, analogical, and abductive) and task formats (e.g., logical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11854","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/2505.11854/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":"2505.11854","created_at":"2026-07-05T11:04:53.215955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11854v1","created_at":"2026-07-05T11:04:53.215955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11854","created_at":"2026-07-05T11:04:53.215955+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXYAK2CVKMCC","created_at":"2026-07-05T11:04:53.215955+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXYAK2CVKMCCL4D3","created_at":"2026-07-05T11:04:53.215955+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXYAK2CV","created_at":"2026-07-05T11:04:53.215955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08317","citing_title":"Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23965","citing_title":"LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs","ref_index":28,"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":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27251","citing_title":"Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXYAK2CVKMCCL4D347J7HO3TFE","json":"https://pith.science/pith/PXYAK2CVKMCCL4D347J7HO3TFE.json","graph_json":"https://pith.science/api/pith-number/PXYAK2CVKMCCL4D347J7HO3TFE/graph.json","events_json":"https://pith.science/api/pith-number/PXYAK2CVKMCCL4D347J7HO3TFE/events.json","paper":"https://pith.science/paper/PXYAK2CV"},"agent_actions":{"view_html":"https://pith.science/pith/PXYAK2CVKMCCL4D347J7HO3TFE","download_json":"https://pith.science/pith/PXYAK2CVKMCCL4D347J7HO3TFE.json","view_paper":"https://pith.science/paper/PXYAK2CV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11854&json=true","fetch_graph":"https://pith.science/api/pith-number/PXYAK2CVKMCCL4D347J7HO3TFE/graph.json","fetch_events":"https://pith.science/api/pith-number/PXYAK2CVKMCCL4D347J7HO3TFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXYAK2CVKMCCL4D347J7HO3TFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXYAK2CVKMCCL4D347J7HO3TFE/action/storage_attestation","attest_author":"https://pith.science/pith/PXYAK2CVKMCCL4D347J7HO3TFE/action/author_attestation","sign_citation":"https://pith.science/pith/PXYAK2CVKMCCL4D347J7HO3TFE/action/citation_signature","submit_replication":"https://pith.science/pith/PXYAK2CVKMCCL4D347J7HO3TFE/action/replication_record"}},"created_at":"2026-07-05T11:04:53.215955+00:00","updated_at":"2026-07-05T11:04:53.215955+00:00"}