Example of fitting resultsLeft: Corner plot of posterior distributions for the two power-law parameters that describe the relationship between the peak energy and isotropic luminosity. Right: Data-resolved spectroscopy of the Fermi/GBM data for GRB 200415A (black) and the posterior predictive distribution (orange). To compute the posterior predictive distribution, we simulated the data generation process by first picking a set of parameters ($({\{{\widehat{E}}_{p,i,k}\}}_{i=1}^N,{\alpha }_k,{\beta }_k)$) from the posterior, then generating random simulated values for L_iso, sim^* and E_p, sim^* using the TPN distribution. This figure shows 100 such simulated datasets and enables a convenient comparison of the performance of the model with the data.