{"total":30,"rows":[{"id":"2411.18704","title":"Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits","created":"2024-11-27","cited_by_count":71,"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":"2103.04514","title":"Nondeterminism and Instability in Neural Network Optimization","created":"2021-03-08","cited_by_count":48,"area":null},{"id":"2102.03349","title":"On the Reproducibility of Neural Network Predictions","created":"2021-02-05","cited_by_count":29,"area":null},{"id":"2207.07483","title":"A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendation","created":"2022-07-15","cited_by_count":22,"area":null},{"id":"2303.12922","title":"Revisiting the Fragility of Influence Functions","created":"2023-03-22","cited_by_count":20,"area":null},{"id":"2105.10488","title":"Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery","created":"2021-05-17","cited_by_count":18,"area":null},{"id":"2308.09543","title":"Latent State Models of Training Dynamics","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2110.06256","title":"Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective","created":"2021-10-12","cited_by_count":15,"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":"2503.07329","title":"Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models","created":"2025-03-10","cited_by_count":10,"area":null},{"id":"2205.09460","title":"Why only Micro-F1? Class Weighting of Measures for Relation Classification","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2302.12691","title":"Reproducibility of Machine Learning: Terminology, Recommendations and Open Issues","created":"2023-02-24","cited_by_count":8,"area":null},{"id":"2206.12353","title":"Quantifying Inherent Randomness in Machine Learning Algorithms","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2111.09612","title":"How Emotionally Stable is ALBERT? Testing Robustness with Stochastic Weight Averaging on a Sentiment Analysis Task","created":"2021-11-18","cited_by_count":5,"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":"2308.02537","title":"ALE: A Simulation-Based Active Learning Evaluation Framework for the Parameter-Driven Comparison of Query Strategies for NLP","created":"2023-08-01","cited_by_count":2,"area":null},{"id":"2506.07871","title":"Can Hessian-Based Insights Support Fault Diagnosis in Attention-based Models?","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2201.01815","title":"An Evaluation Study of Generative Adversarial Networks for Collaborative Filtering","created":"2022-01-05","cited_by_count":1,"area":null},{"id":"2606.03365","title":"Link Prediction or Perdition: the Seeds of Instability in Knowledge Graph Embeddings","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2305.11808","title":"Pseudo-Label Training and Model Inertia in Neural Machine Translation","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2305.12125","title":"A Framework for Provably Stable and Consistent Training of Deep Feedforward Networks","created":"2023-05-20","cited_by_count":0,"area":null},{"id":"2505.14204","title":"Beginning with You: Perceptual-Initialization Improves Vision-Language Representation and Alignment","created":"2025-05-20","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":"2510.21966","title":"ArchISMiner: A Framework for Automatic Mining of Architectural Issue-Solution Pairs from Online Developer Communities","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2512.24145","title":"When Does Pairing Seeds Reduce Variance? Evidence from a Multi-Agent Economic Simulation","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2603.00192","title":"Diagnostics for Individual-Level Prediction Instability in Machine Learning for Healthcare","created":"2026-02-27","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}],"next_cursor":null}