Package: screenllm
Title: LLM-Assisted Title/Abstract Screening for Systematic Reviews
Version: 0.1.0
Authors@R: c(
    person("Scott", "Spillias", email = "scott.spillias@csiro.au",
           role = c("aut", "cre")),
    person("Laura", "Avila Turriago", role = "aut"),
    person("Christopher", "Brown", role = "aut"),
    person("Ariane", "Easton", role = "aut"),
    person("Jack", "Roberts", role = "aut"),
    person("Michael", "Sievers", role = "aut"),
    person("Steve", "Swearer", role = "aut"),
    person("Andrew", "Taylor", role = "aut"),
    person("Brigette", "Wright", role = "aut"),
    person("Valeriya", "Komyakova", role = "aut"))
Description: A turn-key workflow for LLM-assisted systematic-review screening.
    The package ranks a corpus of titles and abstracts with an ensemble of
    open-source large language models served locally by 'Ollama', then
    applies the SAFE stopping rule to identify the records a human should
    screen. Defaults match the four-LLM mean ensemble and the SAFE
    configuration recommended by Spillias et al. (2026). A companion 'Shiny'
    app walks the human reviewer through the records above the stopping
    point. Complementary to the 'AIscreenR' package of
    Vembye et al. (2025) <doi:10.1037/met0000769>, which targets cloud-hosted
    'GPT' models via the 'OpenAI' API; 'screenllm' targets locally-served
    open-weights ensembles with an integrated stopping rule.
License: MIT + file LICENSE
Encoding: UTF-8
Depends: R (>= 4.1.0)
Imports: cli, digest, fs, jsonlite, tibble, dplyr, rlang, httr2, glue
Suggests: shiny, bslib, DT, callr, later, writexl, readxl, testthat (>=
        3.0.0), knitr, rmarkdown, readr, withr, mockery, stringdist
Config/testthat/edition: 3
VignetteBuilder: knitr
URL: https://github.com/s-spillias/screenllm
BugReports: https://github.com/s-spillias/screenllm/issues
Config/roxygen2/version: 8.0.0
NeedsCompilation: no
Packaged: 2026-09-15 05:47:11 UTC; spi085
Author: Scott Spillias [aut, cre],
  Laura Avila Turriago [aut],
  Christopher Brown [aut],
  Ariane Easton [aut],
  Jack Roberts [aut],
  Michael Sievers [aut],
  Steve Swearer [aut],
  Andrew Taylor [aut],
  Brigette Wright [aut],
  Valeriya Komyakova [aut]
Maintainer: Scott Spillias <scott.spillias@csiro.au>
Repository: CRAN
Date/Publication: 2026-09-24 15:00:02 UTC
