Arize Experiment Skill — flags accept a space name (e.g., ) or a base64 space ID (e.g., ). Find yours with . Concepts - Experiment = a named evaluation run against a specific dataset version, containing one run per example - Experiment Run = the result of processing one dataset example -- includes the model output, optional evaluations, and optional metadata - Dataset = a versioned collection of examples; every experiment is tied to a dataset and a specific dataset version - Evaluation = a named metric attached to a run (e.g., , ), with optional label, score, and explanation The typical flow:…