Parnassus for the CLD Detector: A Generative Machine-Learning Surrogate for Detector Simulation and Reconstruction at the FCC-eeNew

The paper presents a Parnassus model for the CLD detector concept at the FCC-ee. It automatically tunes a conditional flow matching neural network to emulate full detector simulation and event reconstruction. The model is trained on electron-positron collision events involving Z-boson decay into a quark-antiquark pair, targeting computational bottlenecks in high-energy physics feasibility studies.