{"total":233,"rows":[{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146,"area":null},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145,"area":null},{"id":"2102.13620","title":"Towards Robust and Reliable Algorithmic Recourse","created":"2021-02-26","cited_by_count":102,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2110.15073","title":"MMD Aggregated Two-Sample Test","created":"2021-10-28","cited_by_count":75,"area":null},{"id":"2111.00980","title":"Mixture Proportion Estimation and PU Learning: A Modern Approach","created":"2021-11-01","cited_by_count":52,"area":null},{"id":"2106.07258","title":"GitTables: A Large-Scale Corpus of Relational Tables","created":"2021-06-14","cited_by_count":45,"area":null},{"id":"2202.01034","title":"Diagnosing failures of fairness transfer across distribution shift in real-world medical settings","created":"2022-02-02","cited_by_count":45,"area":null},{"id":"2104.11408","title":"Neural Mean Discrepancy for Efficient Out-of-Distribution Detection","created":"2021-04-23","cited_by_count":42,"area":null},{"id":"2307.10236","title":"Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2110.06177","title":"Tracking the risk of a deployed model and detecting harmful distribution shifts","created":"2021-10-12","cited_by_count":40,"area":null},{"id":"2204.03719","title":"A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework","created":"2022-04-07","cited_by_count":39,"area":null},{"id":"2103.10292","title":"How I failed machine learning in medical imaging -- shortcomings and recommendations","created":"2021-03-18","cited_by_count":37,"area":null},{"id":"2209.09024","title":"Dataset Inference for Self-Supervised Models","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2208.12084","title":"Calibrated Selective Classification","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2206.14983","title":"A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms","created":"2022-06-30","cited_by_count":30,"area":null},{"id":"2101.10123","title":"Conditional Generative Models for Counterfactual Explanations","created":"2021-01-25","cited_by_count":28,"area":null},{"id":"2210.10275","title":"Towards Explaining Distribution Shifts","created":"2022-10-19","cited_by_count":26,"area":null},{"id":"2209.09125","title":"Operationalizing Machine Learning: An Interview Study","created":"2022-09-16","cited_by_count":25,"area":null},{"id":"2310.14838","title":"Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift","created":"2023-10-23","cited_by_count":25,"area":null},{"id":"2107.06929","title":"Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests","created":"2021-07-14","cited_by_count":24,"area":null},{"id":"2209.08378","title":"Linking Neural Collapse and L2 Normalization with Improved Out-of-Distribution Detection in Deep Neural Networks","created":"2022-09-17","cited_by_count":23,"area":null},{"id":"2403.18910","title":"A Geometric Explanation of the Likelihood OOD Detection Paradox","created":"2024-03-27","cited_by_count":22,"area":null},{"id":"2206.08843","title":"AutoML Two-Sample Test","created":"2022-06-17","cited_by_count":20,"area":null},{"id":"2202.00095","title":"Deconfounded Representation Similarity for Comparison of Neural Networks","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2209.08436","title":"Estimating and Explaining Model Performance When Both Covariates and Labels Shift","created":"2022-09-18","cited_by_count":19,"area":null},{"id":"2212.02742","title":"A Learning Based Hypothesis Test for Harmful Covariate Shift","created":"2022-12-06","cited_by_count":19,"area":null},{"id":"2210.10769","title":"\"Why did the Model Fail?\": Attributing Model Performance Changes to Distribution Shifts","created":"2022-10-19","cited_by_count":18,"area":null},{"id":"2107.09734","title":"Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions","created":"2021-07-20","cited_by_count":16,"area":null},{"id":"2110.06893","title":"Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance","created":"2021-10-13","cited_by_count":16,"area":null},{"id":"2406.17813","title":"Unsupervised Concept Drift Detection from Deep Learning Representations in Real-time","created":"2024-06-24","cited_by_count":16,"area":null},{"id":"2106.02597","title":"Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning","created":"2021-06-04","cited_by_count":15,"area":null},{"id":"2410.23144","title":"Public Domain 12M: A Highly Aesthetic Image-Text Dataset with Novel Governance Mechanisms","created":"2024-10-30","cited_by_count":15,"area":null},{"id":"2104.13621","title":"MLDemon: Deployment Monitoring for Machine Learning Systems","created":"2021-04-28","cited_by_count":14,"area":null},{"id":"2206.15007","title":"GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language","created":"2022-06-30","cited_by_count":14,"area":null},{"id":"2211.05764","title":"DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systems","created":"2022-11-09","cited_by_count":14,"area":null},{"id":"2207.05685","title":"PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners","created":"2022-07-12","cited_by_count":13,"area":null},{"id":"2203.11317","title":"The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error","created":"2022-03-21","cited_by_count":12,"area":null},{"id":"2302.03505","title":"OPORP: One Permutation + One Random Projection","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2405.05160","title":"Selective Classification Under Distribution Shifts","created":"2024-05-08","cited_by_count":12,"area":null},{"id":"2407.05375","title":"Online Drift Detection with Maximum Concept Discrepancy","created":"2024-07-07","cited_by_count":12,"area":null},{"id":"2202.00254","title":"Active Learning Over Multiple Domains in Natural Language Tasks","created":"2022-02-01","cited_by_count":11,"area":null},{"id":"2201.11676","title":"Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap","created":"2022-01-27","cited_by_count":9,"area":null},{"id":"2203.08644","title":"Context-Aware Drift Detection","created":"2022-03-16","cited_by_count":9,"area":null},{"id":"2211.09283","title":"Active Learning with Expected Error Reduction","created":"2022-11-17","cited_by_count":9,"area":null},{"id":"2308.08187","title":"Endogenous Macrodynamics in Algorithmic Recourse","created":"2023-08-16","cited_by_count":9,"area":null},{"id":"2401.08348","title":"Estimating Model Performance Under Covariate Shift Without Labels","created":"2024-01-16","cited_by_count":9,"area":null},{"id":"2504.17921","title":"Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts","created":"2025-04-24","cited_by_count":9,"area":null},{"id":"2202.09486","title":"Suitability of Different Metric Choices for Concept Drift Detection","created":"2022-02-19","cited_by_count":8,"area":null},{"id":"2407.08649","title":"Confidence-based Estimators for Predictive Performance in Model Monitoring","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2411.00186","title":"Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments","created":"2024-10-31","cited_by_count":8,"area":null},{"id":"2505.14903","title":"When to retrain a machine learning model","created":"2025-05-20","cited_by_count":8,"area":null},{"id":"2506.05701","title":"Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital Health","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2104.08952","title":"Failing Conceptually: Concept-Based Explanations of Dataset Shift","created":"2021-04-18","cited_by_count":7,"area":null},{"id":"2202.02833","title":"CheXstray: Real-time Multi-Modal Data Concordance for Drift Detection in Medical Imaging AI","created":"2022-02-06","cited_by_count":7,"area":null},{"id":"2205.06905","title":"Perspectives on Incorporating Expert Feedback into Model Updates","created":"2022-05-13","cited_by_count":7,"area":null},{"id":"2205.08340","title":"A unified framework for dataset shift diagnostics","created":"2022-05-17","cited_by_count":7,"area":null},{"id":"2210.12369","title":"Explanation Shift: Detecting distribution shifts on tabular data via the explanation space","created":"2022-10-22","cited_by_count":7,"area":null},{"id":"2302.10341","title":"DC4L: Distribution Shift Recovery via Data-Driven Control for Deep Learning Models","created":"2023-02-20","cited_by_count":7,"area":null},{"id":"2304.06968","title":"Domain shifts in dermoscopic skin cancer datasets: Evaluation of essential limitations for clinical translation","created":"2023-04-14","cited_by_count":7,"area":null},{"id":"2306.03511","title":"Curriculum-Based Augmented Fourier Domain Adaptation for Robust Medical Image Segmentation","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2310.15826","title":"One or Two Things We know about Concept Drift -- A Survey on Monitoring Evolving Environments","created":"2023-10-24","cited_by_count":7,"area":null},{"id":"2108.12510","title":"Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing","created":"2021-08-27","cited_by_count":6,"area":null},{"id":"2208.06648","title":"Imputation Strategies Under Clinical Presence: Impact on Algorithmic Fairness","created":"2022-08-13","cited_by_count":6,"area":null},{"id":"2210.06776","title":"Improving the Reliability for Confidence Estimation","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2211.09916","title":"Online Distribution Shift Detection via Recency Prediction","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2303.08081","title":"Explanation Shift: How Did the Distribution Shift Impact the Model?","created":"2023-03-14","cited_by_count":6,"area":null},{"id":"2305.07772","title":"Monitoring and Adapting ML Models on Mobile Devices","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2310.04565","title":"Binary Quantification and Dataset Shift: An Experimental Investigation","created":"2023-10-06","cited_by_count":6,"area":null},{"id":"2409.03632","title":"Beyond Model Interpretability: Socio-Structural Explanations in Machine Learning","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2506.17442","title":"Keeping Medical AI Healthy and Trustworthy: A Review of Detection and Correction Methods for System Degradation","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2107.02990","title":"Test for non-negligible adverse shifts","created":"2021-07-07","cited_by_count":5,"area":null},{"id":"2112.03057","title":"Thinking Beyond Distributions in Testing Machine Learned Models","created":"2021-12-06","cited_by_count":5,"area":null},{"id":"2203.08492","title":"Resilient Neural Forecasting Systems","created":"2022-03-16","cited_by_count":5,"area":null},{"id":"2211.06239","title":"A monitoring framework for deployed machine learning models with supply chain examples","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2303.01577","title":"DeepLens: Interactive Out-of-distribution Data Detection in NLP Models","created":"2023-03-02","cited_by_count":5,"area":null},{"id":"2303.06269","title":"DEPLOYR: A technical framework for deploying custom real-time machine learning models into the electronic medical record","created":"2023-03-11","cited_by_count":5,"area":null},{"id":"2306.01751","title":"Differential Privacy with Random Projections and Sign Random Projections","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2312.06254","title":"Modyn: Data-Centric Machine Learning Pipeline Orchestration","created":"2023-12-11","cited_by_count":5,"area":null},{"id":"2402.14254","title":"A hierarchical decomposition for explaining ML performance discrepancies","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2411.07940","title":"Automatic dataset shift identification to support safe deployment of medical imaging AI","created":"2024-11-12","cited_by_count":5,"area":null},{"id":"2505.23027","title":"Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2509.17874","title":"Deep Hierarchical Learning with Nested Subspace Networks for Large Language Models","created":"2025-09-22","cited_by_count":5,"area":null},{"id":"2106.15453","title":"Critically examining the Domain Generalizability of Facial Expression Recognition models","created":"2021-06-29","cited_by_count":4,"area":null},{"id":"2210.07777","title":"LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2311.13806","title":"AdaTyper: Adaptive Semantic Column Type Detection","created":"2023-11-23","cited_by_count":4,"area":null},{"id":"2402.08208","title":"Inherent Diverse Redundant Safety Mechanisms for AI-based Software Elements in Automotive Applications","created":"2024-02-13","cited_by_count":4,"area":null},{"id":"2408.13648","title":"Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance","created":"2024-08-24","cited_by_count":4,"area":null},{"id":"2505.22356","title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2510.21332","title":"Weak-to-Strong Generalization under Distribution Shifts","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2606.28725","title":"DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation","created":"2026-06-27","cited_by_count":4,"area":null},{"id":"2106.12893","title":"Partial Wasserstein and Maximum Mean Discrepancy distances for bridging the gap between outlier detection and drift detection","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2106.12894","title":"InFlow: Robust outlier detection utilizing Normalizing Flows","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2111.08165","title":"RapidRead: Global Deployment of State-of-the-art Radiology AI for a Large Veterinary Teleradiology Practice","created":"2021-11-09","cited_by_count":3,"area":null},{"id":"2205.09974","title":"Diagnosis and Prognosis of COVID-19 Disease Using Routine Blood Values and LogNNet Neural Network","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2206.11116","title":"StaDRe and StaDRo: Reliability and Robustness Estimation of ML-based Forecasting using Statistical Distance Measures","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2207.11290","title":"TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2211.06409","title":"Capabilities for Better ML Engineering","created":"2022-11-11","cited_by_count":3,"area":null}],"next_cursor":"100"}