{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NXPBA6POD3VEKWYSTR5UYOONIH","short_pith_number":"pith:NXPBA6PO","schema_version":"1.0","canonical_sha256":"6dde1079ee1eea455b129c7b4c39cd41fe90f89e43817de12ce5423749a5fe89","source":{"kind":"arxiv","id":"2410.06526","version":3},"attestation_state":"computed","paper":{"title":"KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","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","submitted_at":"2024-10-09T03:56:50Z","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"},"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":"2410.06526","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-09T03:56:50Z","cross_cats_sorted":[],"title_canon_sha256":"320f57ec07baa1ef94e68a4706b6b6994c30a7f35c8fa8fcb655e1a042ca47ca","abstract_canon_sha256":"066263a9df1944b7eb3ce396f269ad6233f0787d17e4b41bc70afef2da73ae7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:06.752292Z","signature_b64":"pNaEFuVcAnViCSF+4l8XBKr9SAkF9HluAdX/PlaV7daex7KF4VtsIamaMvHnQYDfClo+cxQm7nu67H4/ajDmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dde1079ee1eea455b129c7b4c39cd41fe90f89e43817de12ce5423749a5fe89","last_reissued_at":"2026-07-05T10:22:06.751741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:06.751741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","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","submitted_at":"2024-10-09T03:56:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06526","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/2410.06526/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":"2410.06526","created_at":"2026-07-05T10:22:06.751801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06526v3","created_at":"2026-07-05T10:22:06.751801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06526","created_at":"2026-07-05T10:22:06.751801+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXPBA6POD3VE","created_at":"2026-07-05T10:22:06.751801+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXPBA6POD3VEKWYS","created_at":"2026-07-05T10:22:06.751801+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXPBA6PO","created_at":"2026-07-05T10:22:06.751801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10722","citing_title":"Continual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00248","citing_title":"Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2508.08636","citing_title":"InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08738","citing_title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2510.06133","citing_title":"CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15593","citing_title":"Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20633","citing_title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11887","citing_title":"Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08738","citing_title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08905","citing_title":"Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06116","citing_title":"Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18292","citing_title":"Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NXPBA6POD3VEKWYSTR5UYOONIH","json":"https://pith.science/pith/NXPBA6POD3VEKWYSTR5UYOONIH.json","graph_json":"https://pith.science/api/pith-number/NXPBA6POD3VEKWYSTR5UYOONIH/graph.json","events_json":"https://pith.science/api/pith-number/NXPBA6POD3VEKWYSTR5UYOONIH/events.json","paper":"https://pith.science/paper/NXPBA6PO"},"agent_actions":{"view_html":"https://pith.science/pith/NXPBA6POD3VEKWYSTR5UYOONIH","download_json":"https://pith.science/pith/NXPBA6POD3VEKWYSTR5UYOONIH.json","view_paper":"https://pith.science/paper/NXPBA6PO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06526&json=true","fetch_graph":"https://pith.science/api/pith-number/NXPBA6POD3VEKWYSTR5UYOONIH/graph.json","fetch_events":"https://pith.science/api/pith-number/NXPBA6POD3VEKWYSTR5UYOONIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXPBA6POD3VEKWYSTR5UYOONIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXPBA6POD3VEKWYSTR5UYOONIH/action/storage_attestation","attest_author":"https://pith.science/pith/NXPBA6POD3VEKWYSTR5UYOONIH/action/author_attestation","sign_citation":"https://pith.science/pith/NXPBA6POD3VEKWYSTR5UYOONIH/action/citation_signature","submit_replication":"https://pith.science/pith/NXPBA6POD3VEKWYSTR5UYOONIH/action/replication_record"}},"created_at":"2026-07-05T10:22:06.751801+00:00","updated_at":"2026-07-05T10:22:06.751801+00:00"}