{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PXIZRUEAPIXKILAPFJ5G2QVNRK","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":"bdc782d5b6efac9e85c943971a4539c57e8e00e3e660c810912da475a2d214cd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2025-02-18T18:37:15Z","title_canon_sha256":"5578a3309866193d9e8a07b091334e1b52deaf1991b0176766aa9f64f96f7ec8"},"schema_version":"1.0","source":{"id":"2502.13117","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13117","created_at":"2026-07-05T10:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13117v1","created_at":"2026-07-05T10:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13117","created_at":"2026-07-05T10:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"PXIZRUEAPIXK","created_at":"2026-07-05T10:16:29Z"},{"alias_kind":"pith_short_16","alias_value":"PXIZRUEAPIXKILAP","created_at":"2026-07-05T10:16:29Z"},{"alias_kind":"pith_short_8","alias_value":"PXIZRUEA","created_at":"2026-07-05T10:16:29Z"}],"graph_snapshots":[{"event_id":"sha256:3876490ad68c5e2bb557c7ef32f7eda93f4a8dd1060946910465a00537ce37e8","target":"graph","created_at":"2026-07-05T10:16:29Z","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/2502.13117/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The programming capabilities of large language models (LLMs) have revolutionized automatic code generation and opened new avenues for automatic statistical analysis. However, the validity and quality of these generated codes need to be systematically evaluated before they can be widely adopted. Despite their growing prominence, a comprehensive evaluation of statistical code generated by LLMs remains scarce in the literature. In this paper, we assess the performance of LLMs, including two versions of ChatGPT and one version of Llama, in the domain of SAS programming for statistical analysis. Ou","authors_text":"Hao He, Haoran He, Jared M. Clark, Jie Min, Kexin Xie, Lina Lee, Ruizhe Chen, Simin Zheng, Xinlei Zhang, Xinwei Deng, Xinyi Song, Yili Hong, Zhiyang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2025-02-18T18:37:15Z","title":"Performance Evaluation of Large Language Models in Statistical Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13117","kind":"arxiv","version":1},"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":"sha256:345d6f348a3430573a30c7ebc7175bc574176deb138376c10e015077a60af03b","target":"record","created_at":"2026-07-05T10:16:29Z","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":"bdc782d5b6efac9e85c943971a4539c57e8e00e3e660c810912da475a2d214cd","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2025-02-18T18:37:15Z","title_canon_sha256":"5578a3309866193d9e8a07b091334e1b52deaf1991b0176766aa9f64f96f7ec8"},"schema_version":"1.0","source":{"id":"2502.13117","kind":"arxiv","version":1}},"canonical_sha256":"7dd198d0807a2ea42c0f2a7a6d42ad8a86ae28fccddfaba2f99369aaaf427b72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dd198d0807a2ea42c0f2a7a6d42ad8a86ae28fccddfaba2f99369aaaf427b72","first_computed_at":"2026-07-05T10:16:29.683171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:29.683171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yzb5ZdahUNsSVeTVvgDNdLKT6a4U7stHK43/RO4dvlYapFffpn1K2/f1bMMut6q/AOtbqASU4npUxUgVHzKQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:29.683708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13117","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:345d6f348a3430573a30c7ebc7175bc574176deb138376c10e015077a60af03b","sha256:3876490ad68c5e2bb557c7ef32f7eda93f4a8dd1060946910465a00537ce37e8"],"state_sha256":"d27bd6c8c06123f23f959d1413bfd816d86d7d4ecf5378004cd78f77b32e366b"}