AIGENIE: Automatic Item Generation and Validation via Network-Integrated Evaluation

Automated psychological scale development and structural validation using large language models (LLMs) and network psychometric methods. Implements the AI-GENIE framework (Automatic Item Generation and Validation via Network-Integrated Evaluation) to generate candidate items, compute embedding representations, and estimate dimensional structure using Exploratory Graph Analysis (EGA). Item quality is evaluated using Unique Variable Analysis to identify redundant items and Bootstrap EGA to assess item and dimension stability. Supports both fully automated item generation and analysis of user-provided item sets, facilitating efficient, theory-informed measurement development prior to empirical data collection.

Version:	2.1.2
Depends:	R (≥ 3.6.0), EGAnet (≥ 2.4.0)
Imports:	reticulate, ggplot2, igraph, patchwork, jsonlite
Suggests:	testthat (≥ 3.0.0), tictoc, knitr, rmarkdown
Published:	2026-09-08
DOI:	10.32614/CRAN.package.AIGENIE (may not be active yet)
Author:	Lara Russell-Lasalandra [aut, cph], Alexander Christensen [aut, cph], Hudson Golino [aut, cre, cph]
Maintainer:	Hudson Golino <hfg9s at virginia.edu>
BugReports:	https://github.com/laralee/AIGENIE/issues
License:	AGPL (≥ 3)
URL:	https://laralee.github.io/AIGENIE/, https://github.com/laralee/AIGENIE
NeedsCompilation:	no
Citation:	AIGENIE citation info
CRAN checks:	AIGENIE results

Documentation:

Reference manual:	AIGENIE.html , AIGENIE.pdf
Vignettes:	Understanding the AIGENIE / GENIE Filtering Audit (source, R code)

Downloads:

Package source:	AIGENIE_2.1.2.tar.gz
Windows binaries:	r-devel: not available, r-release: AIGENIE_2.1.2.zip, r-oldrel: AIGENIE_2.1.2.zip
macOS binaries:	r-release (arm64): not available, r-oldrel (arm64): not available, r-release (x86_64): AIGENIE_2.1.2.tgz, r-oldrel (x86_64): AIGENIE_2.1.2.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=AIGENIE to link to this page.