Running Reproduction logbook — Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing Approach 🔬 NAMMD theory, benchmark contradiction, and case-study audit
Running Reproduction logbook — Learning Randomized Reductions 🔬 Official CSV reaggregation of the Agentic Bitween claim
Running 1 Reproduction logbook — Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models 🔬 Official reproduction of fine-tuning in linear attention.
Running Reproduction Efficiently Learning Drifting Halfspaces 🎯 Explore experiment logs for the drifting halfspaces paper
Running Falsification logbook — Deep Networks Learn to Parse 🔬 Exact arithmetic audit of six registered claims
Running Reproduction logbook — Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers 🔬 CPU audit of six theoretical and empirical claims
Running Repro - Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos 🎯 Explore a research logbook and collaborate with an AI agent
Running Reproduction - Expressivity-Efficiency Hybrid Sequence Models 📐 Six claims audited, arXiv 2603.08859
Running Repro - A Unifying View of Variational Generative Wasserstein Flows 🚀 Show a customizable static webpage for your Space
Running Reproduction: Statistical Early Stopping for Reasoning Models 🎯 Display a simple static welcome page
Running Reproduction: A Perturbation Approach to Unconstrained Linear Bandits 🎯 Create and customize a simple static web page
Running ICML 2026 reproduction — Optimal and Scalable MAPF 🎯 Explore reproducibility results for optimal MAPF research
Running Reproduction: Generalization and Forgetting in In-Context Continual Learning 🧠 Native in-context continual-learning reproduction
Running Reproduction: Incentivized Exploration with Stochastic Covariates 🧭 Native RCB and public IWPC reproduction
Running Reproduction logbook — VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models 🔬 Two magnitudes falsified against the paper's own tables
Running Falsification logbook — CodeTaste: Can LLMs Generate Human-Level Code Refactorings? 🔬 Recomputed from the authors' released artifact and dashboard
Running Reproduction logbook — A Graphop Analysis of GNNs on Sparse Graphs 🔬 Corollary 5.3 contradicted at L=0 and by Figure 1
Running Reproduction - Epistemic Uncertainty in Overparameterized ReLU Networks 🧭 Exact posterior orbit, variance split, and Dirichlet moments
Running Falsification logbook — Accelerating Regression Tasks with Quantum Algorithms 🔬 Theorems omit a precondition required by their proof
Running Reproduction: Optimal Transport under Group Fairness Constraints ⚖ Native Fair OT group-constraint reproduction