GPT-Based Fast Simulation of CLAS12 Detector Hits via Conditional Autoregressive Generation
For high-energy physics experiments requiring fast, high-fidelity detector simulation, this work offers a practical deep generative alternative to computationally expensive Monte-Carlo methods.
This work applies a GPT-style autoregressive transformer as a fast surrogate model for the CLAS12 calorimeter, achieving inference rates over 700 events per second on a single GPU while faithfully reproducing hit multiplicity, spatial distributions, energy deposits, and energy-momentum response, providing substantial speedup over Geant4 simulations.
Modern particles physics experiments have demonstrated an increasing need for fast, high-fidelity detector simulation as detector components have improved and subsequent computational requirements approach the limits of available resources. Recently, deep generative models have emerged as a promising alternative to traditional Monte-Carlo methods, with recent works drawing inspiration from large language models (LLMs) and self-supervised next-token prediction methods. In this work, we present an application of a GPT-style autoregressive transformer as a fast surrogate model for the calorimeter inside the CLAS12 experiment at the Thomas Jefferson National Accelerator Facility. The model is conditioned on incident momentum and generates realistic detector hits autoregressively across all nine calorimeter layers as sequences of strip, ADC, and TDC tokens. We demonstrate that the model faithfully reproduces hit multiplicity, spatial distributions, energy deposits, and the energy-momentum response of the electromagnetic calorimeter. The generator achieves inference rates exceeding 700 events per second on a single GPU, providing a substantial speedup over traditional Geant4-based simulations while maintaining physics fidelity essential for high-luminosity experimental programs.