Skill UI

Privileged applier that lands user-approved meta-optimize patches into the skill corpus. Runs a fresh cross-model jury on each staged diff at landing time, enforces author/reviewer family separation, and refuses any KILL verdict.

A detailed guide for authors submitting theoretical machine learning papers (like COLT) regarding the appropriate inclusion and design of numerical simulations. It emphasizes that numerics should only visualize proved bounds, phase transitions, or separations, maintaining the focus on theoretical proofs rather than empirical data. Provides rules for plotting, reporting variability, and maintaining academic honesty.

This guide assists researchers in determining the optimal venue for their theoretical machine learning contributions. It provides a framework for evaluating whether a result is best suited for COLT, or if it belongs in other top-tier conferences (e.g., NeurIPS, ICML) or journals (e.g., JMLR). It emphasizes differentiating between rigorous mathematical proofs (bounds, separations) and purely empirical findings.