{"total":23,"rows":[{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232,"area":null},{"id":"2511.04703","title":"Measuring what Matters: Construct Validity in Large Language Model Benchmarks","created":"2025-11-03","cited_by_count":119,"area":null},{"id":"2506.06541","title":"KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes","created":"2025-06-06","cited_by_count":33,"area":null},{"id":"2509.16198","title":"RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation","created":"2025-09-19","cited_by_count":19,"area":null},{"id":"2506.08140","title":"AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists","created":"2025-06-09","cited_by_count":11,"area":null},{"id":"2605.09636","title":"PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation","created":"2026-05-10","cited_by_count":8,"area":null},{"id":"2504.07421","title":"AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2602.24288","title":"DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science","created":"2026-02-27","cited_by_count":4,"area":null},{"id":"2510.13835","title":"ConDABench: Interactive Evaluation of Language Models for Data Analysis","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2511.04584","title":"Are We Asking the Right Questions? On Ambiguity in Natural Language Queries for Tabular Data Analysis","created":"2025-11-06","cited_by_count":3,"area":null},{"id":"2606.15300","title":"CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?","created":"2026-06-13","cited_by_count":3,"area":null},{"id":"2508.01222","title":"WebDS: An End-to-End Benchmark for Web-based Data Science","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2603.19005","title":"AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2606.09774","title":"Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2603.12483","title":"Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2507.19904","title":"CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2509.22768","title":"ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2512.18456","title":"SoK: Understanding (New) Security Issues Across AI4Code Use Cases","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2602.00307","title":"Autonomous Data Processing using Meta-Agents","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2609.30749","title":"ORCA: Evaluating LLMs on Data Science Code Translation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33192","title":"AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34228","title":"SleuthBench: Benchmarking Statistical LLM Evaluation Using Tabular Hidden Signals","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.02363","title":"ArrivalBench: Agent-Generated Data Pipelines Are Correct Once and Wrong Under Time","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}