(Machta et al., 2013): Explains why complicated microscopic processes often result in simple macroscopic behavior. Core Concepts of "Sloppy" Research
: Researchers use the FIM to measure how distinguishable models are based on their predictions. In sloppy models, FIM eigenvalues are distributed roughly evenly over many decades.
The primary foundational paper for this concept is , which provides a comprehensive review of the framework. Key Scientific Papers on Sloppiness sloppy
(Waterfall et al., 2006): Proposes that sloppy models belong to a common "universality class" with eigenvalue spectra that are roughly constant on a logarithmic scale.
(Transtrum et al., 2015): A definitive review describing the information theoretic framework based on the Fisher Information Matrix (FIM). (Machta et al
: A few parameter combinations ("stiff") tightly constrain model behavior, while others ("sloppy") can vary by orders of magnitude without changing the output.
In scientific literature, a "sloppy" model refers to a complex multiparameter system where model behavior is highly sensitive to only a few "stiff" parameter combinations, while the majority of "sloppy" directions in parameter space have almost no effect on model predictions. The primary foundational paper for this concept is
Below are several major papers and resources that define the field: