Physics-Informed Self-Supervised Learning for Joint Wire Calibration and Interaction Position Reconstruction in Multi-Wire Parallel Plate Avalanche Counters

This paper presents a physics-informed self-supervised learning framework designed for multi-wire parallel plate avalanche counters (MWPPC). The framework jointly performs wire calibration and interaction position reconstruction without relying on dedicated calibration measurements or labeled reference data. By integrating physical constraints into the learning process, the method adapts to changing operating conditions and detector aging. The approach demonstrates improved reliability in converting detector signals into physical observables compared to conventional calibration procedures.