A recent study published on arXiv investigates the challenges of forecasting solar flares by analyzing time series data from the SWAN-SF dataset. The research applies a k-medoids clustering algorithm to evaluate various high-dimensional distance metrics, including advanced elastic distances, in identifying patterns within the data. Despite extensive optimization efforts, the findings reveal that none of these sophisticated elastic distance measures outperform the traditional Euclidean distance metric. This result suggests that, for the purpose of solar flare time series analysis, simpler distance metrics may remain more effective than more complex alternatives. The study contributes to ongoing discussions in the field of machine learning applied to astrophysical phenomena, highlighting the importance of benchmarking new methods against established baselines. These insights may inform future approaches to improving solar flare prediction models.