# ------------------------------------------------
# CITATION.cff file created with {cffr} R package
# See also: https://docs.ropensci.org/cffr/
# ------------------------------------------------
 
cff-version: 1.2.0
message: 'To cite package "neuralsbi" in publications use:'
type: software
license: MIT
title: 'neuralsbi: Neural Simulation-Based Inference'
version: 0.6.83
doi: 10.32614/CRAN.package.neuralsbi
abstract: 'A native R implementation of neural simulation-based inference (SBI) methods.
  Given a prior over parameters and a simulator, ''neuralsbi'' trains a conditional
  neural density estimator for likelihood-free Bayesian inference: Neural Posterior
  Estimation approximates the posterior directly and samples it in a forward pass,
  Neural Likelihood Estimation learns a surrogate likelihood that is sampled with
  MCMC, handles repeated independent observations, and can be exported as ''Stan''
  code for use inside a larger model, and Neural Ratio Estimation trains a classifier
  for the likelihood-to-evidence ratio instead of either density. Neural estimators
  run on the ''torch'' back end. This package is developed for applied researchers
  who want an R-native approachable SBI interface with sensible defaults and built-in
  posterior diagnostics.'
authors:
- family-names: Lima
  given-names: Pedro
  name-particle: Nascimento de
  email: plima@rand.org
  orcid: https://orcid.org/0000-0001-9057-198X
repository: https://pedroliman.r-universe.dev
repository-code: https://github.com/pedroliman/neuralsbi
commit: 48817e3e98c089337dccea58f6612fcf5e64d10b
url: https://neuralsbi.pedrodelima.com/
date-released: '2026-10-10'
contact:
- family-names: Lima
  given-names: Pedro
  name-particle: Nascimento de
  email: plima@rand.org
  orcid: https://orcid.org/0000-0001-9057-198X