SG P: A Sorghum Genotype Phenotype Prediction Dataset and Benchmark

A.1 Additional Metadata For all RGB and 3D scanner images used in the SG P Benchmark, we provide additional metadata that Benchmark participants are encouraged to explore using in their approaches. This metadata includes: filepath (str): The full filepath for the file in the dataset. A sorghum subpopulation refers to a distinct and identifiable group within the larger sorghum plant species (Sorghum bicolor) that exhibits specific genetic, morphological, or ecological characteristics setting it apart from other groups within the same species. These characteristics can include variations in traits such as plant height, grain color, flowering time, disease resistance, and adaptations to specific environmental conditions, and participants in the SGxP Benchmark may want to incorporate this information in their methodology or analysis. A cultivar, short for "cultivated variety," is a distinct and deliberately bred cultivated plant variety that exhibits specific characteristics such as growth habits, yield potential, disease resistance, and other desirable traits. Cultivars are developed through selective breeding or genetic manipulation to enhance certain features, making them wellsuited for particular agricultural or horticultural purposes.