Pith. sign in

REVIEW 12 cited by

DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.11501 v1 pith:NF5TMPVE submitted 2022-11-18 cs.SE cs.CL

DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation

classification cs.SE cs.CL
keywords benchmarkds-1000problemsthemcasescodedataevaluation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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 cases and surface-form constraints by restricting API usages or keywords. Finally, we proactively defend against memorization by slightly modifying our problems to be different from the original StackOverflow source; consequently, models cannot answer them correctly by memorizing the solutions from pre-training. The current best public system (Codex-002) achieves 43.3% accuracy, leaving ample room for improvement. We release our benchmark at https://ds1000-code-gen.github.io.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. KernelBench: Can LLMs Write Efficient GPU Kernels?

    cs.LG 2025-02 accept novelty 7.0

    KernelBench shows that even the best current LLMs generate correct and faster-than-baseline GPU kernels in fewer than 20 percent of realistic ML workloads.

  2. Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks

    cs.SE 2026-06 unverdicted novelty 6.0

    Empirical study finds instruction tuning on CodeLLMs improves instruction following at the expense of infilling performance, termed the Instruction-Tuning Tax.

  3. Compass: SLO-aware Query Planner for Compound AI Serving at Scale

    cs.DB 2025-04 unverdicted novelty 6.0

    Compass decomposes multi-query multi-SLO planning for compound AI serving, exploits plan similarities, uses selective profiling, and applies bipartite matching at runtime to deliver 2.4-5.1x higher goodput and 3.8-4.5...

  4. Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows

    cs.AI 2026-07 accept novelty 5.0

    Across 56 tasks, 9 model configurations, and 10,584 runs, LLM-generated skill files provided no reliable performance improvement over task-only prompting for data-science workflows.

  5. Trading Human Curation for Synthetic Augmentation in RLVR

    cs.LG 2026-06 conditional novelty 5.0

    Gated synthetic augmentations of a 10-task human base substitute for ~87 extra human RLVR tasks on aggregate held-out pass@1, with cost-adjusted trade rate ρ_cost in [1.4×, 11.6×].

  6. Qiskit QuantumKatas: Adapting Microsoft's Quantum Computing exercises for LLM evaluation

    quant-ph 2026-05 unverdicted novelty 5.0

    Adapts QuantumKatas to Qiskit yielding a 350-task benchmark across 26 categories and evaluates 16 LLMs in 39,200 runs, reporting performance gaps and prompting effects.

  7. Text Analytics Evaluation Framework: A Case Study on LLMs and Social Media

    cs.CL 2026-05 unverdicted novelty 5.0

    Presents a new question-based evaluation framework for LLMs on aggregated social media text and reports that performance declines with input scale, task complexity, and numerical operations beyond 500 instances.

  8. Business Utility of Large Language Models as Exploratory Data Analysis Agents

    cs.CY 2026-05 unverdicted novelty 5.0

    Evaluation of 15 LLM configurations across four conditions in a supply chain EDA benchmark finds most lack sufficient repeatability for autonomous deployment, with GPT-5.4 at extra-high reasoning effort scoring highes...

  9. AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation

    cs.SE 2025-06 unverdicted novelty 5.0

    AdaDec improves Pass@1 accuracy of LLM code generation by up to 20.9% over greedy decoding by triggering lookahead reranking only at high-uncertainty steps on HumanEval+, MBPP+, and DevEval.

  10. StarCoder: may the source be with you!

    cs.CL 2023-05 accept novelty 5.0

    StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.

  11. Trading Human Curation for Synthetic Augmentation in RLVR

    cs.LG 2026-06 unverdicted novelty 4.0

    Gated synthetic augmentations can substitute for additional human-authored RLVR tasks at a cost-adjusted trade rate of 1.4x-11.6x while retaining held-out generalization on ten benchmarks spanning code, instruction fo...

  12. An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models

    cs.SE 2026-04 unverdicted novelty 4.0

    Data-influence-score filtering using validation-set loss on downstream coding tasks improves Code-LLM performance, with the most beneficial training data varying significantly across different programming tasks.