{"total":34,"rows":[{"id":"2506.20790","title":"Stochastic Parameter Decomposition","created":"2025-06-25","cited_by_count":16,"area":null},{"id":"2506.15872","title":"Hidden Breakthroughs in Language Model Training","created":"2025-06-18","cited_by_count":15,"area":null},{"id":"2501.17745","title":"Dynamics of Transient Structure in In-Context Linear Regression Transformers","created":"2025-01-29","cited_by_count":14,"area":null},{"id":"2509.26544","title":"Bayesian Influence Functions for Hessian-Free Data Attribution","created":"2025-09-30","cited_by_count":14,"area":null},{"id":"2509.26537","title":"The Loss Kernel: A Geometric Probe for Deep Learning Interpretability","created":"2025-09-30","cited_by_count":9,"area":null},{"id":"2509.17196","title":"Evolution of Concepts in Language Model Pre-Training","created":"2025-09-21","cited_by_count":8,"area":null},{"id":"2510.12071","title":"Influence Dynamics and Stagewise Data Attribution","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2507.21449","title":"From Global to Local: A Scalable Benchmark for Local Posterior Sampling","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2510.12077","title":"Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2508.00331","title":"Embryology of a Language Model","created":"2025-08-01","cited_by_count":4,"area":null},{"id":"2603.29805","title":"From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2501.18812","title":"Estimating the Probability of Sampling a Trained Neural Network at Random","created":"2025-01-31","cited_by_count":3,"area":null},{"id":"2504.18048","title":"Modes of Sequence Models and Learning Coefficients","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2606.19491","title":"Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2503.22478","title":"Almost Bayesian: The Fractal Dynamics of Stochastic Gradient Descent","created":"2025-03-28","cited_by_count":2,"area":null},{"id":"2603.03993","title":"Specialization of softmax attention heads: insights from the high-dimensional single-location model","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2605.07980","title":"Susceptibilities and Patterning: A Primer on Linear Response in Bayesian Learning","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.20441","title":"Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2606.21158","title":"Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity","created":"2026-06-19","cited_by_count":2,"area":null},{"id":"2504.11830","title":"Emergence of Computational Structure in a Neural Network Physics Simulator","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2509.18762","title":"When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2603.12785","title":"Upper Bounds for Local Learning Coefficients of Three-Layer Neural Networks","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2605.07970","title":"Linear Response Estimators for Singular Statistical Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2606.05957","title":"Dead Directions: Geometric Singular Learning","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.26050","title":"Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2510.04285","title":"Probing Geometry of Next Token Prediction Using Cumulant Expansion of the Softmax Entropy","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2602.07077","title":"CALM: Class-Conditional Sparse Attention Vectors for Large Audio-Language Models","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.14087","title":"Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.27432","title":"The Geometric Cost of Normalization: Affine Bounds on the Bayesian Complexity of Neural Networks","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2606.01302","title":"Structure and Scale in Simplicial Sequence Modelling","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.22389","title":"Noise-Debiased Thermodynamic Variance for Local Learning Coefficient Probes","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.00603","title":"Measuring Dead Directions: Decomposing and Classifying Singular Structure off Canonical Alignment","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.09840","title":"Langevin dynamics along the zero set of real-analytic potentials","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.14663","title":"Symmetries and Singularities","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}