Counterfactual Compression

–– dmx

KOPLIK, Gary, BORGGREN, Nathan, VOISIN, Sam, ANGELORO, Gabrielle, HINEMAN, Jay, JOHNSON, Tessa and BENDICH, Paul, 2023. Topological Simplification of Signals for Inference and Approximate Reconstruction. In: 2023 IEEE Aerospace Conference. Online. IEEE. 2023. p. 1–11. Available from: https://ieeexplore.ieee.org/abstract/document/10115654/ [Accessed 28 December 2025].

Counterfactual compression is the experimental method used in Koplik et al. (2023) to validate their topological signal compression (TSC) method. It is not an algorithm, but a falsification harness: they run multiple compression methods (Opus, DFT, PAA, Random) on the same signal to answer "What would happen if we used a different compression rule?" This directly operationalizes the S/H/I framework's requirement that habits must support counterfactual tests.