{"total":21,"rows":[{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2504.16430","title":"MAGIC: Near-Optimal Data Attribution for Deep Learning","created":"2025-04-23","cited_by_count":22,"area":null},{"id":"2404.00498","title":"94% on CIFAR-10 in 3.29 Seconds on a Single GPU","created":"2024-03-30","cited_by_count":16,"area":null},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2502.17356","title":"Random Scaling of Emergent Capabilities","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2308.00404","title":"Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis","created":"2023-08-01","cited_by_count":3,"area":null},{"id":"2305.14122","title":"Transferring Learning Trajectories of Neural Networks","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2510.12327","title":"Simple Projection Variants Improve ColBERT Performance","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2606.20536","title":"The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation","created":"2026-06-18","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":"2507.19408","title":"On Arbitrary Predictions from Equally Valid Models","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2512.14439","title":"VICTOR: Dataset Copyright Auditing in Video Recognition Systems","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2602.23360","title":"Model Agreement via Anchoring","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2504.16948","title":"Intrinsic Barriers to Explaining Deep Foundation Models","created":"2025-04-21","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":"2510.10510","title":"f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2601.00577","title":"Adversarial Samples Are Not Created Equal","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2601.13303","title":"On the Extreme Variance of Certified Local Robustness Across Model Seeds","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2603.28040","title":"Bit-Identical Medical Deep Learning via Structured Orthogonal Initialization","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2609.01397","title":"Measuring consistency via ensemble margin and local prediction variability: Auditing decision systems in the presence of predictive multiplicity","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}