Self-Validated Ensemble Models with Lasso and Relaxed Elastic Net Regression R package SVEMnet version 3.2.3 Tools for fitting self-validated ensemble models (SVEM; Lemkus et al. (2021) <doi:10.1016/j.chemolab.2021.104439>) in small-sample design-of-experiments and related workflows, using elastic net and relaxed elastic net regression via 'glmnet' (Friedman et al. (2010) <doi:10.18637/jss.v033.i01>). Fractional random-weight bootstraps with anti-correlated validation copies are used to tune penalty paths by validation-weighted AIC/BIC. Supports Gaussian and binomial responses, deterministic expansion helpers for shared factor spaces, prediction with bootstrap uncertainty, and a random-search optimizer that respects mixture constraints and combines multiple responses via desirability functions. Also includes a permutation-based whole-model test for Gaussian SVEM fits (Karl (2024) <doi:10.1016/j.chemolab.2024.105122>). The package and its workflows are described in Karl (2026) <doi:10.1016/j.chemolab.2026.105660>. Package code was drafted with assistance from generative AI tools. Software Depends: R (>= 4.0.0) Imports: glmnet (>= 4.1-6), stats, cluster, ggplot2, lhs, foreach, doParallel, parallel, gamlss, gamlss.dist, utils Suggests: covr, knitr, rmarkdown, testthat (>= 3.0.0), withr, vdiffr, RhpcBLASctl Andrew T. Karl <akarl@asu.edu> Comprehensive R Archive Network (CRAN) Andrew T. Karl [cre, aut] (ORCID: <https://orcid.org/0000-0002-5933-8706>) GPL-2 GPL-3 2026-07-02 application/tgz https://CRAN.R-project.org/package=SVEMnet doi:10.32614/CRAN.package.SVEMnet