MetaHunt: Privacy-Preserving Meta-Analysis via Low-Rank Basis Hunting

Tools for privacy-preserving meta-analysis of function-valued quantities across heterogeneous studies. Implements the 'MetaHunt' pipeline, including the denoised functional Successive Projection Algorithm (d-fSPA) for basis hunting, constrained weight estimation, Dirichlet regression of weights on study-level covariates, target prediction, and split/cross conformal prediction intervals. Operates on aggregate-level function evaluations, so individual-level data from source studies are not required. Methodology described in Shi, Imai, and Zhang (2026) <doi:10.48550/arXiv.2604.23847>.

Version:	0.1.0
Depends:	R (≥ 4.0)
Imports:	quadprog, DirichletReg, stats, graphics, grDevices, withr
Suggests:	grf, knitr, rmarkdown, testthat (≥ 3.0.0)
Published:	2026-05-12
DOI:	10.32614/CRAN.package.MetaHunt
Author:	Wenqi Shi [aut, cre], Kosuke Imai [aut], Yi Zhang [aut]
Maintainer:	Wenqi Shi <wenqishi18 at gmail.com>
BugReports:	https://github.com/WShi18/MetaHunt/issues
License:	MIT + file LICENSE
URL:	https://github.com/WShi18/MetaHunt, https://wshi18.github.io/MetaHunt/, https://arxiv.org/abs/2604.23847
NeedsCompilation:	no
Citation:	MetaHunt citation info
Materials:	README, NEWS
CRAN checks:	MetaHunt results

Documentation:

Reference manual:

MetaHunt.html , MetaHunt.pdf

Vignettes:

Choosing K and the denoising parameters (source, R code) Conformal prediction with different choices (source, R code) Preparing your data: from fitted models to F_hat (source, R code) Get started with MetaHunt (source, R code) Understanding grid_weights and the L2(mu) norm (source, R code) An introduction to MetaHunt (source, R code) When to prefer minmax_regret (source, R code) Scalar summaries with wrapper (source, R code)

Downloads:

Package source:	MetaHunt_0.1.0.tar.gz
Windows binaries:	r-devel: MetaHunt_0.1.0.zip, r-release: MetaHunt_0.1.0.zip, r-oldrel: MetaHunt_0.1.0.zip
macOS binaries:	r-release (arm64): MetaHunt_0.1.0.tgz, r-oldrel (arm64): MetaHunt_0.1.0.tgz, r-release (x86_64): MetaHunt_0.1.0.tgz, r-oldrel (x86_64): MetaHunt_0.1.0.tgz

Linking:

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