These campaigns document Looptimum's use in simulation-mesh optimization and model training. Each includes the search method, measured outcomes, and limits of the available evidence.
A 21-trial search found a smaller mesh, then a separate solver pass checked flow and pressure against the fine reference.
Acceptance required a separate solver pass and mesh-independence checks.
Read the case study
Ten evaluations tested four training controls. The selected model had lower held-out loss and fewer parameters than the fixed baseline.
Anonymized campaign with one seed and a small evaluation budget.
Read the case studyA pilot focuses on one evaluation workflow, with agreed parameter bounds, a resource budget, and acceptance criteria.