{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PUPDHDHAFJNNMUE7ADDXYX7LLI","short_pith_number":"pith:PUPDHDHA","schema_version":"1.0","canonical_sha256":"7d1e338ce02a5ad6509f00c77c5feb5a279cc76dcbb45711d4f1b73055bea7f4","source":{"kind":"arxiv","id":"2406.07815","version":2},"attestation_state":"computed","paper":{"title":"Are Large Language Models Good Statisticians?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boyan Li, Nan Tang, Shiyin Du, Yizhang Zhu, Yuyu Luo","submitted_at":"2024-06-12T02:23:51Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities across a range of scientific tasks including mathematics, physics, and chemistry. Despite their successes, the effectiveness of LLMs in handling complex statistical tasks remains systematically under-explored. To bridge this gap, we introduce StatQA, a new benchmark designed for statistical analysis tasks. StatQA comprises 11,623 examples tailored to evaluate LLMs' proficiency in specialized statistical tasks and their applicability assessment capabilities, particularly for hypothesis testing methods. We systematically expe"},"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":"2406.07815","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T02:23:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad03e16a86c8ff6666960baddf67636bc27041c14b5f6e073f72c5edd63fc6b3","abstract_canon_sha256":"bb5d600859fa9ea8e7dcf477dbd7c2a692575166deb52b52a7d7da398650b735"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:27.081701Z","signature_b64":"io+pDLICeATCtpu+Z4Ar81q/tOzUwq1f+3x4iATnse04OYtiXvaY8znrTK0TqhcBsyNhRimMlN5qOb3z2PCADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d1e338ce02a5ad6509f00c77c5feb5a279cc76dcbb45711d4f1b73055bea7f4","last_reissued_at":"2026-07-05T09:18:27.081215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:27.081215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Large Language Models Good Statisticians?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boyan Li, Nan Tang, Shiyin Du, Yizhang Zhu, Yuyu Luo","submitted_at":"2024-06-12T02:23:51Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities across a range of scientific tasks including mathematics, physics, and chemistry. Despite their successes, the effectiveness of LLMs in handling complex statistical tasks remains systematically under-explored. To bridge this gap, we introduce StatQA, a new benchmark designed for statistical analysis tasks. StatQA comprises 11,623 examples tailored to evaluate LLMs' proficiency in specialized statistical tasks and their applicability assessment capabilities, particularly for hypothesis testing methods. We systematically expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07815","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/2406.07815/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":"2406.07815","created_at":"2026-07-05T09:18:27.081267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07815v2","created_at":"2026-07-05T09:18:27.081267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07815","created_at":"2026-07-05T09:18:27.081267+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUPDHDHAFJNN","created_at":"2026-07-05T09:18:27.081267+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUPDHDHAFJNNMUE7","created_at":"2026-07-05T09:18:27.081267+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUPDHDHA","created_at":"2026-07-05T09:18:27.081267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00384","citing_title":"VESTA: Visual Exploration with Statistical Tool Agents","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUPDHDHAFJNNMUE7ADDXYX7LLI","json":"https://pith.science/pith/PUPDHDHAFJNNMUE7ADDXYX7LLI.json","graph_json":"https://pith.science/api/pith-number/PUPDHDHAFJNNMUE7ADDXYX7LLI/graph.json","events_json":"https://pith.science/api/pith-number/PUPDHDHAFJNNMUE7ADDXYX7LLI/events.json","paper":"https://pith.science/paper/PUPDHDHA"},"agent_actions":{"view_html":"https://pith.science/pith/PUPDHDHAFJNNMUE7ADDXYX7LLI","download_json":"https://pith.science/pith/PUPDHDHAFJNNMUE7ADDXYX7LLI.json","view_paper":"https://pith.science/paper/PUPDHDHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07815&json=true","fetch_graph":"https://pith.science/api/pith-number/PUPDHDHAFJNNMUE7ADDXYX7LLI/graph.json","fetch_events":"https://pith.science/api/pith-number/PUPDHDHAFJNNMUE7ADDXYX7LLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUPDHDHAFJNNMUE7ADDXYX7LLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUPDHDHAFJNNMUE7ADDXYX7LLI/action/storage_attestation","attest_author":"https://pith.science/pith/PUPDHDHAFJNNMUE7ADDXYX7LLI/action/author_attestation","sign_citation":"https://pith.science/pith/PUPDHDHAFJNNMUE7ADDXYX7LLI/action/citation_signature","submit_replication":"https://pith.science/pith/PUPDHDHAFJNNMUE7ADDXYX7LLI/action/replication_record"}},"created_at":"2026-07-05T09:18:27.081267+00:00","updated_at":"2026-07-05T09:18:27.081267+00:00"}