Luminary reports an out-of-distribution confidence score on SHIFT-Wing: 0.99 in distribution, 0.13 for an SUV

Luminary Cloud's Aashwin Mishra and Dheeraj Vemula describe Luminary-OOD, a detector that projects the incoming geometry and parameters into an embedding space and returns a confidence score before the physics model runs. Tested on the SHIFT-Wing dataset with the Luminary-SMART model, the mean score is 0.99 for in-distribution inputs, 0.92 for a slight shift in Mach number, 0.82 for a large one, 0.57 for the NASA CRM (a slight geometric shift, an extra tail section) and 0.13 for an SUV geometry. The post puts Monte Carlo dropout at about 50 times the inference cost and deep ensembles at about 5 times the training and inference cost, and calls its own overhead negligible, without a figure.

Share on LinkedIn, X or Bluesky, or copy the link.