{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PXYAK2CVKMCCL4D347J7HO3TFE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a914afa63ef3aec64d0c3bbb30e9f7fda38e73517a5bc9198341bf2ce854993c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T05:36:14Z","title_canon_sha256":"2a784a7d295f104929be54320c8efd9f0b6c7abeb41ca3cf89af66720791a00d"},"schema_version":"1.0","source":{"id":"2505.11854","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11854","created_at":"2026-07-05T11:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11854v1","created_at":"2026-07-05T11:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11854","created_at":"2026-07-05T11:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"PXYAK2CVKMCC","created_at":"2026-07-05T11:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"PXYAK2CVKMCCL4D3","created_at":"2026-07-05T11:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"PXYAK2CV","created_at":"2026-07-05T11:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:ddb89a33c4edef25244b718e209253faea4a505605d95c86fda6e39368d5f6a7","target":"graph","created_at":"2026-07-05T11:04:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.11854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chaoli Zhang, Hanmeng Liu, Xiaozhang Liu, Yiran Ding, Yue Zhang, Zhizhang Fu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T05:36:14Z","title":"Evaluating the Logical Reasoning Abilities of Large Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11854","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8f89475dfe899e2e506395ead94de833ac205c39a14c879e37cdfd18b8fb2d3e","target":"record","created_at":"2026-07-05T11:04:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a914afa63ef3aec64d0c3bbb30e9f7fda38e73517a5bc9198341bf2ce854993c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T05:36:14Z","title_canon_sha256":"2a784a7d295f104929be54320c8efd9f0b6c7abeb41ca3cf89af66720791a00d"},"schema_version":"1.0","source":{"id":"2505.11854","kind":"arxiv","version":1}},"canonical_sha256":"7df0056855530425f07be7d3f3bb732906d952986bf8e420f5f58cc32c0eeb6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7df0056855530425f07be7d3f3bb732906d952986bf8e420f5f58cc32c0eeb6f","first_computed_at":"2026-07-05T11:04:53.215893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:53.215893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QDnNsj7E9apnyU62zHnCs0Oek/1Y9ztlbnVbGFKrPPoUamfsOnyVJK446FLyeBnbsJGo0w7jmYqfC5e2EBaTBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:53.216432Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11854","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f89475dfe899e2e506395ead94de833ac205c39a14c879e37cdfd18b8fb2d3e","sha256:ddb89a33c4edef25244b718e209253faea4a505605d95c86fda6e39368d5f6a7"],"state_sha256":"ae9d491ec4e6072b612acf45c65c8e443805af781a2ad910e9b225fa980d0362"}