Explore Run

When you want to run quick experiments on a deep learning repo without committing to full training runs, this handles the planning and execution of exploratory trials like small-subset validation, short-cycle probes, or batch sweeps. It ranks candidate runs by cost, success rate, and expected gain, then writes structured summaries to explore_outputs/ with fair-comparison caveats so you don't accidentally overstate results. The boundary is clear: this is for explicit exploratory work only, not trusted baselines or production training. It pairs well with minimal-run-and-audit for actual execution and keeps experiment state isolated from your main research branch.