{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QI42SNFBQAORHB4DPIYPKV2FOZ","short_pith_number":"pith:QI42SNFB","schema_version":"1.0","canonical_sha256":"8239a934a1801d1387837a30f557457679df68d37e6e1269dbede9b147b5baaf","source":{"kind":"arxiv","id":"2506.12577","version":1},"attestation_state":"computed","paper":{"title":"OneEval: Benchmarking LLM Knowledge-intensive Reasoning over Diverse Knowledge Bases","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guilin Qi, Haofen Wang, Haolei Zhu, Hongjie Deng, Huajun Chen, Jiajun Liu, Jiazhen Kang, Jing Yu, Keyan Ding, Lin Ren, Nan Hu, Pengfei Shen, Qiu Ji, Sheng Bi, Shenyu Zhang, Tianxing Wu, Tongtong Wu, Wenliang Chen, Wen Zhang, Xinbang Dai, Xinda Wang, Yisong Wang, Yongrui Chen, Zhiqiang Liu","submitted_at":"2025-06-14T17:16:05Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated substantial progress on reasoning tasks involving unstructured text, yet their capabilities significantly deteriorate when reasoning requires integrating structured external knowledge such as knowledge graphs, code snippets, or formal logic. This limitation is partly due to the absence of benchmarks capable of systematically evaluating LLM performance across diverse structured knowledge modalities. To address this gap, we introduce \\textbf{\\textsc{OneEval}}, a comprehensive benchmark explicitly designed to assess the knowledge-intensive reasoning "},"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":"2506.12577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-14T17:16:05Z","cross_cats_sorted":[],"title_canon_sha256":"9c88458f52e522df1e4da8cb4090b1d60d3fe57674cf4da5c4ff2bab3c4c14e7","abstract_canon_sha256":"6d39a70aaf99a4678b98d7c19764fb5ac5aaf24c0c1e4af6e7185a2479f3b2e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:55.736231Z","signature_b64":"1vtA9Sa1lj+qiBRZVrv3tRfti+kJfL8/3KICExu5MprwOCTn6/LkP1AgxqkNH/mqkcWFczDDsclCIUvs9bnfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8239a934a1801d1387837a30f557457679df68d37e6e1269dbede9b147b5baaf","last_reissued_at":"2026-07-05T11:21:55.735707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:55.735707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OneEval: Benchmarking LLM Knowledge-intensive Reasoning over Diverse Knowledge Bases","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guilin Qi, Haofen Wang, Haolei Zhu, Hongjie Deng, Huajun Chen, Jiajun Liu, Jiazhen Kang, Jing Yu, Keyan Ding, Lin Ren, Nan Hu, Pengfei Shen, Qiu Ji, Sheng Bi, Shenyu Zhang, Tianxing Wu, Tongtong Wu, Wenliang Chen, Wen Zhang, Xinbang Dai, Xinda Wang, Yisong Wang, Yongrui Chen, Zhiqiang Liu","submitted_at":"2025-06-14T17:16:05Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated substantial progress on reasoning tasks involving unstructured text, yet their capabilities significantly deteriorate when reasoning requires integrating structured external knowledge such as knowledge graphs, code snippets, or formal logic. This limitation is partly due to the absence of benchmarks capable of systematically evaluating LLM performance across diverse structured knowledge modalities. To address this gap, we introduce \\textbf{\\textsc{OneEval}}, a comprehensive benchmark explicitly designed to assess the knowledge-intensive reasoning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12577","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/2506.12577/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":"2506.12577","created_at":"2026-07-05T11:21:55.735774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12577v1","created_at":"2026-07-05T11:21:55.735774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12577","created_at":"2026-07-05T11:21:55.735774+00:00"},{"alias_kind":"pith_short_12","alias_value":"QI42SNFBQAOR","created_at":"2026-07-05T11:21:55.735774+00:00"},{"alias_kind":"pith_short_16","alias_value":"QI42SNFBQAORHB4D","created_at":"2026-07-05T11:21:55.735774+00:00"},{"alias_kind":"pith_short_8","alias_value":"QI42SNFB","created_at":"2026-07-05T11:21:55.735774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QI42SNFBQAORHB4DPIYPKV2FOZ","json":"https://pith.science/pith/QI42SNFBQAORHB4DPIYPKV2FOZ.json","graph_json":"https://pith.science/api/pith-number/QI42SNFBQAORHB4DPIYPKV2FOZ/graph.json","events_json":"https://pith.science/api/pith-number/QI42SNFBQAORHB4DPIYPKV2FOZ/events.json","paper":"https://pith.science/paper/QI42SNFB"},"agent_actions":{"view_html":"https://pith.science/pith/QI42SNFBQAORHB4DPIYPKV2FOZ","download_json":"https://pith.science/pith/QI42SNFBQAORHB4DPIYPKV2FOZ.json","view_paper":"https://pith.science/paper/QI42SNFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12577&json=true","fetch_graph":"https://pith.science/api/pith-number/QI42SNFBQAORHB4DPIYPKV2FOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QI42SNFBQAORHB4DPIYPKV2FOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QI42SNFBQAORHB4DPIYPKV2FOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QI42SNFBQAORHB4DPIYPKV2FOZ/action/storage_attestation","attest_author":"https://pith.science/pith/QI42SNFBQAORHB4DPIYPKV2FOZ/action/author_attestation","sign_citation":"https://pith.science/pith/QI42SNFBQAORHB4DPIYPKV2FOZ/action/citation_signature","submit_replication":"https://pith.science/pith/QI42SNFBQAORHB4DPIYPKV2FOZ/action/replication_record"}},"created_at":"2026-07-05T11:21:55.735774+00:00","updated_at":"2026-07-05T11:21:55.735774+00:00"}