{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NLTOSHW2UZS43U36PZYLM2A6IF","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":"ea68079f1774421382d279899a404773df55bd3704961b14182afbae058dbb84","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-10T16:28:43Z","title_canon_sha256":"181c804619f646f9528cede5a8412a45fcead5c6ee81289f8a72227fa2dc35bc"},"schema_version":"1.0","source":{"id":"2510.09517","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.09517","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"2510.09517v2","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09517","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"NLTOSHW2UZS4","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"pith_short_16","alias_value":"NLTOSHW2UZS43U36","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"pith_short_8","alias_value":"NLTOSHW2","created_at":"2026-07-03T01:17:13Z"}],"graph_snapshots":[{"event_id":"sha256:cb07740919aa77a78a26e3eec05a5dcbe8cdef0d0706dfc978512910e5eed906","target":"graph","created_at":"2026-07-03T01:17:13Z","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/2510.09517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changyu Zhu, Fan Zhou, Jiayi Xiang, Run Yang, Shuguang Yu, Wenxin E, Yichen Zhang, Yuchen Lu, Ziwei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-10T16:28:43Z","title":"StatEval: A Comprehensive Benchmark for Large Language Models in Statistics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09517","kind":"arxiv","version":2},"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":"sha256:1f993a815220f305f6f109bf097cc8d1e9c208e547e6fcfc60103580aafa59ba","target":"record","created_at":"2026-07-03T01:17:13Z","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":"ea68079f1774421382d279899a404773df55bd3704961b14182afbae058dbb84","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-10T16:28:43Z","title_canon_sha256":"181c804619f646f9528cede5a8412a45fcead5c6ee81289f8a72227fa2dc35bc"},"schema_version":"1.0","source":{"id":"2510.09517","kind":"arxiv","version":2}},"canonical_sha256":"6ae6e91edaa665cdd37e7e70b6681e41497e1a61aadd6d42d4a74bd189a3ca7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ae6e91edaa665cdd37e7e70b6681e41497e1a61aadd6d42d4a74bd189a3ca7c","first_computed_at":"2026-07-03T01:17:13.611624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:13.611624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uxtEr4ZLlzY+b6TAclKN+hf7c89EUbTpzuDCc7CSpBlQWfCMTNTiBlkQPLUNozWMc0moNhG6N74X00AEWs4lCw==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:13.612117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.09517","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f993a815220f305f6f109bf097cc8d1e9c208e547e6fcfc60103580aafa59ba","sha256:cb07740919aa77a78a26e3eec05a5dcbe8cdef0d0706dfc978512910e5eed906"],"state_sha256":"e9a65dba6ef46b0ffc9b06a25f40d355ce8f207dbc85a6506cf39c4c110c0724"}