A leaner statistical model unlocks more power from photometric supernovae

Photometric supernova surveys classify Type Ia events without spectra, introducing contamination that standard analyses handle with a computationally expensive two-component mixture model. This work proposes instead to absorb that contamination as a redshift-dependent shift in the mean of a single Gaussian likelihood. Tested against DES-Dovekie data with two independent classifiers, the simplified model is strongly preferred by Bayes factor comparisons across all probability-cut configurations. The result suggests that photometric samples can deliver tighter cosmological constraints without the overhead of the full BEAMS framework.