{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NF5TMPVETZZXZOUXCJNQ6OKXVU","short_pith_number":"pith:NF5TMPVE","schema_version":"1.0","canonical_sha256":"697b363ea49e737cba97125b0f3957ad2b0e66629d1095085f567309ae960471","source":{"kind":"arxiv","id":"2211.11501","version":1},"attestation_state":"computed","paper":{"title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Chengxi Li, Daniel Fried, Luke Zettlemoyer, Ruiqi Zhong, Scott Wen-tau Yih, Sida Wang, Tao Yu, Tianyi Zhang, Yiming Wang, Yuhang Lai","submitted_at":"2022-11-18T17:20:27Z","abstract_excerpt":"We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas. Compared to prior works, DS-1000 incorporates three core features. First, our problems reflect diverse, realistic, and practical use cases since we collected them from StackOverflow. Second, our automatic evaluation is highly specific (reliable) -- across all Codex-002-predicted solutions that our evaluation accept, only 1.8% of them are incorrect; we achieve this with multi-criteria metrics, checking both functional correctness by running test case"},"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":"2211.11501","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-11-18T17:20:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4f82110e7726f67336cd5103f71003e823ed9c1a133b2d468b483a2a4ae6d403","abstract_canon_sha256":"f36cda2ce95e0e3083feb531bcbb6e6b2898dc9a440265ebda1b0dad7af33bee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:54.267503Z","signature_b64":"ZxwuMWc4qB29kxauNCe+arqTX0qJwjyGb7px3rcUQi3aIYH2SP+BXld8nS7L+xPhL+690RkQsv8/j6GvOjIyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"697b363ea49e737cba97125b0f3957ad2b0e66629d1095085f567309ae960471","last_reissued_at":"2026-07-05T05:17:54.267061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:54.267061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Chengxi Li, Daniel Fried, Luke Zettlemoyer, Ruiqi Zhong, Scott Wen-tau Yih, Sida Wang, Tao Yu, Tianyi Zhang, Yiming Wang, Yuhang Lai","submitted_at":"2022-11-18T17:20:27Z","abstract_excerpt":"We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas. Compared to prior works, DS-1000 incorporates three core features. First, our problems reflect diverse, realistic, and practical use cases since we collected them from StackOverflow. Second, our automatic evaluation is highly specific (reliable) -- across all Codex-002-predicted solutions that our evaluation accept, only 1.8% of them are incorrect; we achieve this with multi-criteria metrics, checking both functional correctness by running test case"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11501","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/2211.11501/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":"2211.11501","created_at":"2026-07-05T05:17:54.267129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11501v1","created_at":"2026-07-05T05:17:54.267129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11501","created_at":"2026-07-05T05:17:54.267129+00:00"},{"alias_kind":"pith_short_12","alias_value":"NF5TMPVETZZX","created_at":"2026-07-05T05:17:54.267129+00:00"},{"alias_kind":"pith_short_16","alias_value":"NF5TMPVETZZXZOUX","created_at":"2026-07-05T05:17:54.267129+00:00"},{"alias_kind":"pith_short_8","alias_value":"NF5TMPVE","created_at":"2026-07-05T05:17:54.267129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07504","citing_title":"Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08676","citing_title":"Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03800","citing_title":"Trading Human Curation for Synthetic Augmentation in RLVR","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00051","citing_title":"Business Utility of Large Language Models as Exploratory Data Analysis Agents","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27210","citing_title":"Qiskit QuantumKatas: Adapting Microsoft's Quantum Computing exercises for LLM evaluation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2504.16397","citing_title":"Compass: SLO-aware Query Planner for Compound AI Serving at Scale","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21338","citing_title":"Text Analytics Evaluation Framework: A Case Study on LLMs and Social Media","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08980","citing_title":"AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2502.10517","citing_title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07769","citing_title":"An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06161","citing_title":"StarCoder: may the source be with you!","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NF5TMPVETZZXZOUXCJNQ6OKXVU","json":"https://pith.science/pith/NF5TMPVETZZXZOUXCJNQ6OKXVU.json","graph_json":"https://pith.science/api/pith-number/NF5TMPVETZZXZOUXCJNQ6OKXVU/graph.json","events_json":"https://pith.science/api/pith-number/NF5TMPVETZZXZOUXCJNQ6OKXVU/events.json","paper":"https://pith.science/paper/NF5TMPVE"},"agent_actions":{"view_html":"https://pith.science/pith/NF5TMPVETZZXZOUXCJNQ6OKXVU","download_json":"https://pith.science/pith/NF5TMPVETZZXZOUXCJNQ6OKXVU.json","view_paper":"https://pith.science/paper/NF5TMPVE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11501&json=true","fetch_graph":"https://pith.science/api/pith-number/NF5TMPVETZZXZOUXCJNQ6OKXVU/graph.json","fetch_events":"https://pith.science/api/pith-number/NF5TMPVETZZXZOUXCJNQ6OKXVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NF5TMPVETZZXZOUXCJNQ6OKXVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NF5TMPVETZZXZOUXCJNQ6OKXVU/action/storage_attestation","attest_author":"https://pith.science/pith/NF5TMPVETZZXZOUXCJNQ6OKXVU/action/author_attestation","sign_citation":"https://pith.science/pith/NF5TMPVETZZXZOUXCJNQ6OKXVU/action/citation_signature","submit_replication":"https://pith.science/pith/NF5TMPVETZZXZOUXCJNQ6OKXVU/action/replication_record"}},"created_at":"2026-07-05T05:17:54.267129+00:00","updated_at":"2026-07-05T05:17:54.267129+00:00"}