Running Falsification logbook โ Evaluating Relational Reasoning in LLMs ๐ฌ Exact source-data falsification of all six REL claims
Running Reproduction: Newton Step and Influence Function Accuracy ๐งญ Exact logistic attribution audit
Running Reproduction: All ERMs Can Fail in Linear Dimension ๐ Direct ERM and GD lower-bound reproduction
Running Reproduction: Committed Q-learning for Reactive RL ๐งญ Direct native Committed Q-learning reproduction
Running Reproduction Efficient Preference Poisoning ๐ฏ Explore experiment logs and collaborate with an AI agent
Running Reproduction: Second-order Sequential Mean Testing ๐ Direct sequential KL-inf reproduction
Running Reproduction โ Language Generation with Replay ๐ Track and share experiment logs with an AI collaborator
Running Formal Problem-Solving Exact Audit ๐งฉ View and collaborate on a reproducible research logbook
Running Reproduction: Questioning the Coverage-Length Metric ๐ Direct PT coverage-length reproduction
Running Reproduction: Generalized Boundary FDR Control with Domino ๐งช Direct native Domino k-boundary FDR reproduction
Running Reproduction: Corruption-Tolerant Asynchronous Q-Learning ๐ก Direct native Robust Async-Q reproduction
Running Repro - Positive Distribution Shift Theorem Audit ๐ View and sync audit logbook with your coding agent
Running Reproduction: Efficient Stochastic Optimisation via SMC โ Native SOSMC theory and benchmark reproduction
Running Reproduction: SoftJAX & SoftTorch Informative Gradients ๐งฎ Native SoftJAX and SoftTorch reproduction
Running 1 Reproduction Gromov-Wasserstein at Scale ๐ฏ Explore a research logbook and collaborate with an AI agent
Running Reproduction - Exact Unlearning in Reinforcement Learning ๐ฏ Explore and collaborate on research logbooks
Running 5 Reproduction: Matroid Algorithms Under Size-Sensitive Independence Oracles ๐ Native size-sensitive matroid audit
Running 14 Reproduction: Mixed Synthetic Nearest Neighbors ๐งฉ Native mixed-anchor matrix-completion audit
Running Reproduction: DiscoGen Procedural Algorithm-Discovery Tasks ๐ชฉ Native DiscoGen task-space and benchmark audit
Running Reproduction: Optimal Regularization for Performative Learning ๐ Native performative ridge audit
Running High-Dimensional Gaussian and SGG Optimality โ Native Reproduction ๐ View and collaborate on experiment reproduction logbooks
Running Reproduction - Improved Algorithms for Nash Welfare in Linear Bandits ๐ฏ Explore research logs and collaborate with an AI agent
Running Reproduction - A Game-Theoretic Analysis of Attacks on Large Language Models via Compositional Skills ๐ฏ Track and share research experiment logs