{"total":136,"rows":[{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2402.01781","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","created":"2024-02-01","cited_by_count":137,"area":null},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106,"area":null},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104,"area":null},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2403.07059","title":"Better than classical? The subtle art of benchmarking quantum machine learning models","created":"2024-03-11","cited_by_count":85,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2203.04592","title":"Mapping global dynamics of benchmark creation and saturation in artificial intelligence","created":"2022-03-09","cited_by_count":71,"area":null},{"id":"2109.03670","title":"YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimization","created":"2021-09-08","cited_by_count":62,"area":null},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2110.11403","title":"SCENIC: A JAX Library for Computer Vision Research and Beyond","created":"2021-10-18","cited_by_count":57,"area":null},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2406.10229","title":"Quantifying Variance in Evaluation Benchmarks","created":"2024-06-14","cited_by_count":54,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2405.02287","title":"Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models","created":"2024-05-03","cited_by_count":35,"area":"mllm"},{"id":"2503.07832","title":"RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code","created":"2025-03-10","cited_by_count":30,"area":"lr"},{"id":"2204.06815","title":"deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks","created":"2022-04-14","cited_by_count":28,"area":null},{"id":"2405.01719","title":"Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks","created":"2024-05-02","cited_by_count":28,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2206.09707","title":"The Role of Machine Learning in Cybersecurity","created":"2022-06-20","cited_by_count":22,"area":null},{"id":"2301.13195","title":"Adaptive Computation with Elastic Input Sequence","created":"2023-01-30","cited_by_count":22,"area":null},{"id":"2107.13098","title":"A Tale Of Two Long Tails","created":"2021-07-27","cited_by_count":19,"area":null},{"id":"2405.02200","title":"Position: Why We Must Rethink Empirical Research in Machine Learning","created":"2024-05-03","cited_by_count":19,"area":null},{"id":"2203.06498","title":"The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2303.08485","title":"Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML","created":"2023-03-15","cited_by_count":16,"area":null},{"id":"2205.08944","title":"SoK: The Impact of Unlabelled Data in Cyberthreat Detection","created":"2022-05-18","cited_by_count":15,"area":null},{"id":"2210.05769","title":"Vote'n'Rank: Revision of Benchmarking with Social Choice Theory","created":"2022-10-11","cited_by_count":15,"area":null},{"id":"2412.06745","title":"ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities","created":"2024-12-09","cited_by_count":15,"area":null},{"id":"2210.05043","title":"Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling","created":"2022-10-10","cited_by_count":14,"area":null},{"id":"2305.10284","title":"Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks","created":"2023-05-17","cited_by_count":14,"area":null},{"id":"2312.01082","title":"A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness","created":"2023-12-02","cited_by_count":14,"area":null},{"id":"2605.12673","title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","created":"2026-05-12","cited_by_count":14,"area":null},{"id":"2510.23191","title":"The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models","created":"2025-10-27","cited_by_count":13,"area":null},{"id":"2302.03788","title":"Toward a Theory of Causation for Interpreting Neural Code Models","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2605.12678","title":"No One Knows the State of the Art in Geospatial Foundation Models","created":"2026-05-12","cited_by_count":12,"area":null},{"id":"2206.11461","title":"Towards Better User Studies in Computer Graphics and Vision","created":"2022-06-23","cited_by_count":11,"area":null},{"id":"2508.12461","title":"Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models","created":"2025-08-17","cited_by_count":11,"area":"moe"},{"id":"2204.06251","title":"Experimental Standards for Deep Learning in Natural Language Processing Research","created":"2022-04-13","cited_by_count":10,"area":null},{"id":"2209.00692","title":"Making Intelligence: Ethical Values in IQ and ML Benchmarks","created":"2022-09-01","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":"2501.04234","title":"Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks","created":"2025-01-08","cited_by_count":10,"area":null},{"id":"2603.11337","title":"RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents","created":"2026-03-11","cited_by_count":10,"area":"agents"},{"id":"2112.01342","title":"How not to Lie with a Benchmark: Rearranging NLP Leaderboards","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2310.06167","title":"Predictable Artificial Intelligence","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2510.07575","title":"Benchmarking is Broken -- Don't Let AI be its Own Judge","created":"2025-10-08","cited_by_count":8,"area":null},{"id":"2407.12136","title":"Molecular Topological Profile (MOLTOP) -- Simple and Strong Baseline for Molecular Graph Classification","created":"2024-07-16","cited_by_count":7,"area":null},{"id":"2305.18575","title":"Search-Based Regular Expression Inference on a GPU","created":"2023-05-29","cited_by_count":6,"area":null},{"id":"2307.09191","title":"A benchmark of categorical encoders for binary classification","created":"2023-07-17","cited_by_count":6,"area":null},{"id":"2406.10366","title":"Improving the Validity and Practical Usefulness of AI/ML Evaluations Using an Estimands Framework","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2508.08883","title":"Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption","created":"2025-08-12","cited_by_count":6,"area":null},{"id":"2208.06028","title":"Gaussian Process Surrogate Models for Neural Networks","created":"2022-08-11","cited_by_count":5,"area":null},{"id":"2607.26587","title":"The Implementation Lottery: Auditing Idea Reliability in Automated Research","created":"2026-07-29","cited_by_count":5,"area":null},{"id":"2608.12875","title":"The Embedder's Dilemma: LLMs Are Better, but at What Cost?","created":"2026-08-13","cited_by_count":5,"area":"lr"},{"id":"2407.06483","title":"Composable Interventions for Language Models","created":"2024-07-09","cited_by_count":4,"area":"safety"},{"id":"2604.16279","title":"Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design","created":"2026-04-17","cited_by_count":4,"area":null},{"id":"2605.18229","title":"Are Sparse Autoencoder Benchmarks Reliable?","created":"2026-05-18","cited_by_count":4,"area":"mechinterp"},{"id":"2205.11134","title":"Please, Don't Forget the Difference and the Confidence Interval when Seeking for the State-of-the-Art Status","created":"2022-05-23","cited_by_count":3,"area":null},{"id":"2305.10740","title":"A benchmark for computational analysis of animal behavior, using animal-borne tags","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2501.14809","title":"Evaluation of Seismic Artificial Intelligence with Uncertainty","created":"2025-01-15","cited_by_count":3,"area":null},{"id":"2604.03244","title":"AI Evaluation Should Require Standardized Item-Level Data Releases","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2411.05224","title":"Beyond the Numbers: Transparency in Relation Extraction Benchmark Creation and Leaderboards","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2506.11604","title":"VLM@school -- Evaluation of AI image understanding on German middle school knowledge","created":"2025-06-13","cited_by_count":2,"area":"lr"},{"id":"2511.16655","title":"Solving Spatial Supersensing Without Spatial Supersensing","created":"2025-11-20","cited_by_count":2,"area":"wm"},{"id":"2603.23527","title":"Compression Method Matters: Benchmark-Dependent Output Dynamics in LLM Prompt Compression","created":"2026-03-06","cited_by_count":2,"area":"inference"},{"id":"2604.15579","title":"Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents","created":"2026-04-16","cited_by_count":2,"area":"safety"},{"id":"2606.00135","title":"On Effectiveness and Efficiency of Agentic Tool-calling and RL Training","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2607.02587","title":"The Moving Target: A Longitudinal Audit of Trust-Benchmark Score Drift Across Open-Source Chat LLM Release Lines","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2608.00355","title":"CurveShift: Is Agent Progress Scalar? Separating Level from Shape","created":"2026-07-31","cited_by_count":2,"area":"agents"},{"id":"2608.14425","title":"Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations","created":"2026-08-14","cited_by_count":2,"area":null},{"id":"2608.21601","title":"K-Bench: measuring model performance on real scientific agent requests","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2609.03966","title":"Interface-Induced Trajectory Censoring","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2609.04518","title":"Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence","created":"2026-09-03","cited_by_count":2,"area":"lr"},{"id":"2609.06107","title":"DataFlex-RL: An Evaluation Platform for RLVR Data Policies","created":"2026-09-05","cited_by_count":2,"area":null},{"id":"2207.11211","title":"Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentation","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2404.19485","title":"IID Relaxation by Logical Expressivity: A Research Agenda for Fitting Logics to Neurosymbolic Requirements","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2501.15431","title":"Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?","created":"2025-01-26","cited_by_count":1,"area":null},{"id":"2509.22612","title":"Beyond statistical significance: Quantifying uncertainty and statistical variability in multilingual and multitask NLP evaluation","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2602.07593","title":"Beyond Arrow: From Impossibility to Possibilities in Multi-Criteria Benchmarking","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.21297","title":"Robust AI Evaluation through Maximal Lotteries","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.03493","title":"Quantifying Ranking Instability Across Evaluation Protocol Axes in Gene Regulatory Network Benchmarking","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2604.23102","title":"Unstable Rankings in Bayesian Deep Learning Evaluation","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2604.23114","title":"A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2605.02442","title":"Measuring AI Reasoning: A Guide for Researchers","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2605.18663","title":"GIM: Evaluating models via tasks that integrate multiple cognitive domains","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.23628","title":"How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.29335","title":"Rethinking FID Through the Geometry of the Reference Dataset","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.19704","title":"Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2606.27997","title":"Benchmarking on Tasks That Matter: Dataset Selection for Preserving Model Rankings","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2606.29159","title":"What a Pooled Leaderboard Does Not Say: Auditing the Scope and Provenance of Method Comparisons in Microservice RCA Benchmarks","created":"2026-06-28","cited_by_count":1,"area":null}],"next_cursor":"100"}