{"total":73,"rows":[{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194,"area":null},{"id":"2412.00568","title":"The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning","created":"2024-11-30","cited_by_count":145,"area":null},{"id":"2406.09624","title":"DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks","created":"2024-06-13","cited_by_count":75,"area":null},{"id":"2406.09639","title":"TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs","created":"2024-06-14","cited_by_count":36,"area":null},{"id":"2406.07954","title":"Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition","created":"2024-06-12","cited_by_count":20,"area":null},{"id":"2605.10865","title":"BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD","created":"2026-05-11","cited_by_count":15,"area":null},{"id":"2410.12974","title":"BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks","created":"2024-10-16","cited_by_count":10,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2501.10727","title":"In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review","created":"2025-01-18","cited_by_count":8,"area":null},{"id":"2508.14006","title":"ResPlan: A Large-Scale Vector-Graph Dataset of 17,000 Residential Floor Plans","created":"2025-08-19","cited_by_count":8,"area":null},{"id":"2506.01789","title":"Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2505.22778","title":"Machine Learning Models Have a Supply Chain Problem","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2605.09228","title":"ProactBench: Beyond What The User Asked For","created":"2026-05-09","cited_by_count":4,"area":null},{"id":"2601.09966","title":"A Sustainable AI Economy Needs Data Deals That Work for Generators","created":"2026-01-15","cited_by_count":3,"area":null},{"id":"2407.04158","title":"ELCC: the Emergent Language Corpus Collection","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2506.12231","title":"CheMixHub: Datasets and Benchmarks for Chemical Mixture Property Prediction","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2607.27263","title":"DoTime: A Synthetic Benchmark Generator for Interventional and Counterfactual Time Series","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2406.04378","title":"TIDMAD: Time Series Dataset for Discovering Dark Matter with AI Denoising","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2410.02230","title":"Mitigating Downstream Model Risks via Model Provenance","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2411.16277","title":"FinML-Chain: A Blockchain-Integrated Dataset for Enhanced Financial Machine Learning","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2504.11200","title":"Mutual Understanding between People and Systems via Neurosymbolic AI and Knowledge Graphs","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2505.15657","title":"LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.16619","title":"Open and Sustainable AI: challenges, opportunities and the road ahead in the life sciences (October 2025 -- Version 2)","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.22084","title":"MObyGaze: a film dataset of multimodal objectification densely annotated by experts","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.22358","title":"AI Model Passport: Data and System Traceability Framework for Transparent AI in Health","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2507.19559","title":"Towards Sustainability Model Cards","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2508.16604","title":"WHAR Datasets: An Open Source Library for Wearable Human Activity Recognition","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2508.20115","title":"Flexible metadata harvesting for ecology using large language models","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2509.23577","title":"ML-Asset Management: Curation, Discovery, and Utilization","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2511.02885","title":"AgentSLA : Towards a Service Level Agreement for AI Agents","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2602.15968","title":"From Reflection to Repair: A Scoping Review of Dataset Documentation Tools","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.07792","title":"Dual-Metric Evaluation of Social Bias in Large Language Models: Evidence from an Underrepresented Nepali Cultural Context","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2605.15597","title":"CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.06895","title":"Blockchain Infrastructure for Intelligent Cyber--Physical--Social Systems:Post-Quantum Security, Interoperability, and Trustworthy Data Economies in the Era of Embodied AI","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.08256","title":"Traxia: A Framework for Verifiable, Agent-Native Scientific Publishing","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2606.31004","title":"Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.30896","title":"Rad-R: A Raw-ADC Radar Dataset and Capture-Invariant SSM for Hardware-Fault Diagnosis","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2610.02293","title":"HakemBench: A Turkish Benchmark of Typed Decisions","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2501.04014","title":"AICat: An AI Cataloguing Approach to Support the EU AI Act","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2505.13343","title":"MRM3: Machine Readable ML Model Metadata","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2505.17841","title":"TEDI: Trustworthy and Ethical Dataset Indicators to Analyze and Compare Dataset Documentation","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.02914","title":"AutoExpert: Automating 3D LiDAR Annotation from Expert-Crafted Guidelines","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2509.10432","title":"Standards in the Preparation of Biomedical Research Metadata: A Bridge2AI Perspective","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2512.04120","title":"Towards Contextual Sensitive Data Detection","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.16455","title":"AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2601.14429","title":"Measuring the State of Open Science in Transportation Using Large Language Models","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2604.01344","title":"IDEA2: Expert-in-the-loop competency question elicitation for collaborative ontology engineering","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.21093","title":"TRAVELFRAUDBENCH: A Configurable Evaluation Framework for GNN Fraud Ring Detection in Travel Networks","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.06136","title":"BUILD-AND-FIND: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.07919","title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.09676","title":"ChaosNetBench: Benchmarking Spatio-Temporal Graph Neural Networks on Chaotic Lattice Dynamics","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.14040","title":"Physics-R1: An Audited Olympiad Corpus and Released Verifiers for Visual Physics Reasoning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.15079","title":"Croissant Baker: Metadata Generation for Discoverable, Governable, and Reusable ML Datasets","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.19765","title":"GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.29786","title":"Croissant Tasks: A Metadata Format for Reproducible Machine Learning Evaluations","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.22166","title":"Rebuttals Move Peer-Review Scores, but Initial-Review Structure Bounds the Movement","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.28856","title":"Building AI-Ready Data Systems for Space Life Sciences, Aerospace Medicine, and Deep Space Exploration","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.10057","title":"Quantum Circuit Vision: Cost-Aware Evaluation of Visual AI Agents for Quantum Code Generation","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.18254","title":"Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.21471","title":"Future Rendering $\\neq$ Future Surface: A Benchmark and Dataset for Dynamic Surface Reconstruction Beyond the Observed Window","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.02949","title":"On the missing data layer and a potential solution","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.11022","title":"Workflow Cards: Structured Summaries of Workflow Executions Using Provenance Data","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.17997","title":"Traceable Trust for action-ready artificial intelligence in bioscience","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.19625","title":"Scientific Data Skills: Enabling Agent-Ready Scientific Data Services at Scale","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.20106","title":"OenoBench: A Wine-Domain Benchmark for Knowledge-Grounded Evaluation of Large Language Models","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.20391","title":"ImmigrationReason: A Structured Dataset of U.S. Immigration Appeals for Legal Reasoning Research","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.19640","title":"A Policy Profile for Croissant: Refusal as a Property of the Dataset","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22259","title":"Which Part of the Context Layer Does the Work? Separating Semantic Content from Retrieval Scaffolding in Text-to-SQL Agents","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.23659","title":"ETH-TraceBench: A Large-Scale Event-Stream Benchmark for Ethereum DeFi under Temporal, Protocol, and Contract Shift","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.33505","title":"When Evidence Changes the Subject: Subject-Typed Claim Licensing for Learned Routing","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.40356","title":"ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00952","title":"A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.18771","title":"The Federated Tumor Segmentation and Classification (FeTS++) Challenge","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}