{"total":42,"rows":[{"id":"2402.02364","title":"Loss Landscape Degeneracy and Stagewise Development in Transformers","created":"2024-02-04","cited_by_count":40,"area":null},{"id":"2505.03989","title":"An alignment safety case sketch based on debate","created":"2025-05-06","cited_by_count":16,"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":"2402.03698","title":"Estimating the Local Learning Coefficient at Scale","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2602.00693","title":"Topology and Geometry of the Learning Space of ReLU Networks: Connectivity and Singularities","created":"2026-01-31","cited_by_count":6,"area":null},{"id":"2410.05612","title":"A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints","created":"2024-10-08","cited_by_count":5,"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":"2603.01192","title":"A Basin-Selection Perspective on Grokking via Singular Learning Theory","created":"2026-03-01","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":"2412.15113","title":"Associative memory inspires improvements for in-context learning using a novel attention residual stream architecture","created":"2024-12-19","cited_by_count":3,"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":"2502.01739","title":"Grokking vs. Learning: Same Features, Different Encodings","created":"2025-02-03","cited_by_count":2,"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":"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":"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":"2506.09648","title":"Scaling Laws for Uncertainty in Deep Learning","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2602.11097","title":"Statistical Learning Analysis of Physics-Informed Neural Networks","created":"2026-02-11","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":"2409.04913","title":"NGD converges to less degenerate solutions than SGD","created":"2024-09-07","cited_by_count":0,"area":null},{"id":"2411.16396","title":"Statistical inference for quantum singular models","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2507.01414","title":"Decomposing Prediction Mechanisms for In-Context Recall","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2512.00686","title":"Using physics-inspired Singular Learning Theory to understand grokking & other phase transitions in modern neural networks","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2602.23219","title":"Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime","created":"2026-02-26","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":"2606.22389","title":"Noise-Debiased Thermodynamic Variance for Local Learning Coefficient Probes","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2606.28464","title":"Singular Learning and Occam's Razor in Deep Monomial Networks","created":"2026-06-26","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":"2608.11243","title":"The Off-Support Barrier: Why Semantic Safety Constraints Are Not Learning-Problem Invariants, and What Follows for Prior Design, Containment, and Verification","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.20183","title":"Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.30741","title":"Functional Degeneracy in Neural Networks: Measurement and Pruning","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.14663","title":"Symmetries and Singularities","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.15289","title":"Math for AI safety: an invitation for mathematicians","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.13123","title":"Why Heavy-Tailed Weight Spectra Predict Model Quality","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}