{"total":47,"rows":[{"id":"2206.01653","title":"Metrics reloaded: Recommendations for image analysis validation","created":"2022-06-03","cited_by_count":195,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2205.15466","title":"Data Banzhaf: A Robust Data Valuation Framework for Machine Learning","created":"2022-05-30","cited_by_count":132,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2311.17295","title":"Elo Uncovered: Robustness and Best Practices in Language Model Evaluation","created":"2023-11-29","cited_by_count":61,"area":null},{"id":"2106.11872","title":"Randomness In Neural Network Training: Characterizing The Impact of Tooling","created":"2021-06-22","cited_by_count":59,"area":null},{"id":"2506.09501","title":"Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference","created":"2025-06-11","cited_by_count":53,"area":null},{"id":"2209.05310","title":"On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models","created":"2022-09-12","cited_by_count":34,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2408.05148","title":"Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applications","created":"2024-08-09","cited_by_count":24,"area":null},{"id":"2304.01910","title":"On the Variance of Neural Network Training with respect to Test Sets and Distributions","created":"2023-04-04","cited_by_count":22,"area":null},{"id":"2202.04598","title":"Reproducibility in Optimization: Theoretical Framework and Limits","created":"2022-02-09","cited_by_count":21,"area":null},{"id":"2307.14517","title":"The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers","created":"2023-07-26","cited_by_count":15,"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":"2303.00586","title":"FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling","created":"2023-03-01","cited_by_count":11,"area":null},{"id":"2302.07778","title":"Measuring the Instability of Fine-Tuning","created":"2023-02-15","cited_by_count":7,"area":null},{"id":"2205.10070","title":"On the Prediction Instability of Graph Neural Networks","created":"2022-05-20","cited_by_count":6,"area":null},{"id":"2303.12797","title":"An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters","created":"2023-02-27","cited_by_count":6,"area":null},{"id":"2211.10828","title":"Instability in clinical risk stratification models using deep learning","created":"2022-11-20","cited_by_count":3,"area":null},{"id":"2202.06499","title":"Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations","created":"2022-02-14","cited_by_count":2,"area":null},{"id":"2212.01744","title":"Statistical Physics of Deep Neural Networks: Initialization toward Optimal Channels","created":"2022-12-04","cited_by_count":2,"area":null},{"id":"2305.14122","title":"Transferring Learning Trajectories of Neural Networks","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2312.03886","title":"On The Fairness Impacts of Hardware Selection in Machine Learning","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2510.09180","title":"RepDL: Bit-level Reproducible Deep Learning Training and Inference","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2606.03938","title":"q0: Primitives for Hyper-Epoch Pretraining","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2310.00541","title":"Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks","created":"2023-10-01","cited_by_count":1,"area":null},{"id":"2406.08307","title":"Measuring training variability from stochastic optimization using robust nonparametric testing","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2503.17173","title":"Robustness of deep learning classification to adversarial input on GPUs: asynchronous parallel accumulation is a source of vulnerability","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2508.04401","title":"Why are LLMs' abilities emergent?","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2511.10909","title":"Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2601.22983","title":"PIDSMaker: Building and Evaluating Provenance-based Intrusion Detection Systems","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2606.15959","title":"Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2608.11541","title":"Robust Ambiguity Detection (RAD) From Model- and Feature-Space Consistency","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2110.06435","title":"Dropout Prediction Uncertainty Estimation Using Neuron Activation Strength","created":"2021-10-13","cited_by_count":0,"area":null},{"id":"2309.05256","title":"Examining the Effect of Pre-training on Time Series Classification","created":"2023-09-11","cited_by_count":0,"area":null},{"id":"2408.02825","title":"The Impact of Environment Configurations on the Stability of AI-Enabled Systems","created":"2024-08-05","cited_by_count":0,"area":null},{"id":"2506.04241","title":"Improving Out-of-Distribution Detection with Markov Logic Networks","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2510.05606","title":"Fractal basin geometry and the limits to predictability and reproducibility in deep learning","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.15060","title":"A solution to generalized learning from small training sets found in infants repeated visual experiences of individual objects","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.19427","title":"Revisiting the Relation Between Robustness and Universality","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2511.11590","title":"Embedding Explainable AI in NHS Clinical Safety: The Explainability-Enabled Clinical Safety Framework (ECSF)","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2601.00578","title":"Learning to be Reproducible: Custom Loss Design for Robust Neural Networks","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2604.27987","title":"Dynamic Scaled Gradient Descent for Stable Fine-Tuning for Classifications","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.22917","title":"GRAIN: Group Aggregation via Min-Norm Objective","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.05113","title":"Rating the Pitch, Not the Product: User Evaluations of LLMs Reflect Expectations More Than Performance","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.31796","title":"Same Probe, Different Numbers: Are Activation Probes Robust to Inference-Time Numerical Non-Determinism?","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.05854","title":"TurboPairFormer: Fast and Stable Protein Folding Model Training with an Optimized Triangle Attention Kernel","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}