{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NLTOSHW2UZS43U36PZYLM2A6IF","short_pith_number":"pith:NLTOSHW2","schema_version":"1.0","canonical_sha256":"6ae6e91edaa665cdd37e7e70b6681e41497e1a61aadd6d42d4a74bd189a3ca7c","source":{"kind":"arxiv","id":"2510.09517","version":2},"attestation_state":"computed","paper":{"title":"StatEval: A Comprehensive Benchmark for Large Language Models in Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changyu Zhu, Fan Zhou, Jiayi Xiang, Run Yang, Shuguang Yu, Wenxin E, Yichen Zhang, Yuchen Lu, Ziwei Wang","submitted_at":"2025-10-10T16:28:43Z","abstract_excerpt":"Despite rapid advances in large language models (LLMs), statistical reasoning remains underrepresented in existing LLM benchmarks, which often do not reflect the layered, proof-driven nature of real statistical practice. To address this gap, we introduce \\textbf{StatEval}, the first large-scale benchmark for statistical reasoning across curricular and research-level settings. StatEval includes over 100,000 curated problems, with 20,000+ foundational questions spanning undergraduate and graduate curricula and 80,000+ research-level proof tasks extracted from leading statistical journals. To con"},"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":"2510.09517","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-10T16:28:43Z","cross_cats_sorted":[],"title_canon_sha256":"181c804619f646f9528cede5a8412a45fcead5c6ee81289f8a72227fa2dc35bc","abstract_canon_sha256":"ea68079f1774421382d279899a404773df55bd3704961b14182afbae058dbb84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:13.612117Z","signature_b64":"uxtEr4ZLlzY+b6TAclKN+hf7c89EUbTpzuDCc7CSpBlQWfCMTNTiBlkQPLUNozWMc0moNhG6N74X00AEWs4lCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ae6e91edaa665cdd37e7e70b6681e41497e1a61aadd6d42d4a74bd189a3ca7c","last_reissued_at":"2026-07-03T01:17:13.611624Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:13.611624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StatEval: A Comprehensive Benchmark for Large Language Models in Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changyu Zhu, Fan Zhou, Jiayi Xiang, Run Yang, Shuguang Yu, Wenxin E, Yichen Zhang, Yuchen Lu, Ziwei Wang","submitted_at":"2025-10-10T16:28:43Z","abstract_excerpt":"Despite rapid advances in large language models (LLMs), statistical reasoning remains underrepresented in existing LLM benchmarks, which often do not reflect the layered, proof-driven nature of real statistical practice. To address this gap, we introduce \\textbf{StatEval}, the first large-scale benchmark for statistical reasoning across curricular and research-level settings. StatEval includes over 100,000 curated problems, with 20,000+ foundational questions spanning undergraduate and graduate curricula and 80,000+ research-level proof tasks extracted from leading statistical journals. To con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09517","kind":"arxiv","version":2},"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/2510.09517/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":"2510.09517","created_at":"2026-07-03T01:17:13.611678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.09517v2","created_at":"2026-07-03T01:17:13.611678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09517","created_at":"2026-07-03T01:17:13.611678+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLTOSHW2UZS4","created_at":"2026-07-03T01:17:13.611678+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLTOSHW2UZS43U36","created_at":"2026-07-03T01:17:13.611678+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLTOSHW2","created_at":"2026-07-03T01:17:13.611678+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/NLTOSHW2UZS43U36PZYLM2A6IF","json":"https://pith.science/pith/NLTOSHW2UZS43U36PZYLM2A6IF.json","graph_json":"https://pith.science/api/pith-number/NLTOSHW2UZS43U36PZYLM2A6IF/graph.json","events_json":"https://pith.science/api/pith-number/NLTOSHW2UZS43U36PZYLM2A6IF/events.json","paper":"https://pith.science/paper/NLTOSHW2"},"agent_actions":{"view_html":"https://pith.science/pith/NLTOSHW2UZS43U36PZYLM2A6IF","download_json":"https://pith.science/pith/NLTOSHW2UZS43U36PZYLM2A6IF.json","view_paper":"https://pith.science/paper/NLTOSHW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.09517&json=true","fetch_graph":"https://pith.science/api/pith-number/NLTOSHW2UZS43U36PZYLM2A6IF/graph.json","fetch_events":"https://pith.science/api/pith-number/NLTOSHW2UZS43U36PZYLM2A6IF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLTOSHW2UZS43U36PZYLM2A6IF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLTOSHW2UZS43U36PZYLM2A6IF/action/storage_attestation","attest_author":"https://pith.science/pith/NLTOSHW2UZS43U36PZYLM2A6IF/action/author_attestation","sign_citation":"https://pith.science/pith/NLTOSHW2UZS43U36PZYLM2A6IF/action/citation_signature","submit_replication":"https://pith.science/pith/NLTOSHW2UZS43U36PZYLM2A6IF/action/replication_record"}},"created_at":"2026-07-03T01:17:13.611678+00:00","updated_at":"2026-07-03T01:17:13.611678+00:00"}