{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NXPBA6POD3VEKWYSTR5UYOONIH","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":"066263a9df1944b7eb3ce396f269ad6233f0787d17e4b41bc70afef2da73ae7d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-09T03:56:50Z","title_canon_sha256":"320f57ec07baa1ef94e68a4706b6b6994c30a7f35c8fa8fcb655e1a042ca47ca"},"schema_version":"1.0","source":{"id":"2410.06526","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06526","created_at":"2026-07-05T10:22:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06526v3","created_at":"2026-07-05T10:22:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06526","created_at":"2026-07-05T10:22:06Z"},{"alias_kind":"pith_short_12","alias_value":"NXPBA6POD3VE","created_at":"2026-07-05T10:22:06Z"},{"alias_kind":"pith_short_16","alias_value":"NXPBA6POD3VEKWYS","created_at":"2026-07-05T10:22:06Z"},{"alias_kind":"pith_short_8","alias_value":"NXPBA6PO","created_at":"2026-07-05T10:22:06Z"}],"graph_snapshots":[{"event_id":"sha256:cf3b306b274fb884ea8aa5892c3ed0a76c44a17b4457d9eb654db9eb7e752355","target":"graph","created_at":"2026-07-05T10:22:06Z","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/2410.06526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce Knowledge-Orthogonal Reasoning (KOR), a concept aimed at minimizing reliance on domain-specific knowledge, enabling more accurate evaluation of models' reasoning abilities in out-of-distribution settings. Based on this concept, we propose the Knowledge-Orthogonal Reasoning Benchmark (KOR-Bench), encompassing five task categories: Operation, Logic, Cipher, Puzzle, and Counterfactual. KOR-Bench emphasizes models' effectiveness in applying new rule descriptions to solve novel rule-driven questions. O1-Preview and O1-Mini achieve accuracies of 72.88% and 70.16%, surpass","authors_text":"Ge Zhang, Haoran Zhang, Jiaheng Liu, Jian Yang, Kaijing Ma, Minghao Liu, Wenhao Huang, Xiang Yue, Xingwei Qu, Xinrun Du, Yunran Wang, Zhoufutu Wen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-09T03:56:50Z","title":"KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06526","kind":"arxiv","version":3},"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:c09507f1bea5fc68fd14243952af814537f5f75fec2355a2cfccb5d176b0a761","target":"record","created_at":"2026-07-05T10:22:06Z","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":"066263a9df1944b7eb3ce396f269ad6233f0787d17e4b41bc70afef2da73ae7d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-09T03:56:50Z","title_canon_sha256":"320f57ec07baa1ef94e68a4706b6b6994c30a7f35c8fa8fcb655e1a042ca47ca"},"schema_version":"1.0","source":{"id":"2410.06526","kind":"arxiv","version":3}},"canonical_sha256":"6dde1079ee1eea455b129c7b4c39cd41fe90f89e43817de12ce5423749a5fe89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dde1079ee1eea455b129c7b4c39cd41fe90f89e43817de12ce5423749a5fe89","first_computed_at":"2026-07-05T10:22:06.751741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:06.751741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pNaEFuVcAnViCSF+4l8XBKr9SAkF9HluAdX/PlaV7daex7KF4VtsIamaMvHnQYDfClo+cxQm7nu67H4/ajDmBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:06.752292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06526","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c09507f1bea5fc68fd14243952af814537f5f75fec2355a2cfccb5d176b0a761","sha256:cf3b306b274fb884ea8aa5892c3ed0a76c44a17b4457d9eb654db9eb7e752355"],"state_sha256":"ef04d8d295050f10e32aa0f679a0f2184baa229cf501ecefef10457478a56bcf"}