ALT Digital contact tracing tools, such as those leveraging Bluetooth or Wi-Fi colocation networks, intended for automated infectious disease surveillance are increasingly common. However, these systems bring concerns of privacy when collecting diagnostic and personal data. Additionally, many of these systems have also been known to report superfluous epidemiologically irrelevant contacts, thus reducing usage and reliability. Building reliable, privacy-driven, real-time digital contact tracing systems can better prepare individuals and institutions for future infectious disease outbreaks. Leveraging a robust multimodal dataset (demographics, contact tracing, Wi-Fi based colocation data, viral genomic sequencing of clinical specimens) collected at Colorado Mesa University during the 2020-2021 academic year, applying an ensemble of white box statistical tools produces a sparsified network, pruned based on normalized behavioral tendency between individuals. This new network representation dra