Package: survinng
Title: Gradient-Based Feature Attribution for Survival Neural Networks
Version: 0.1.0
Authors@R: c(
    person("Niklas", "Koenen", , "niklas.koenen@gmail.com", role = c("aut", "cre"),
           comment = c(ORCID = "0000-0002-4623-8271")),
    person(c("Sophie", "Hanna"), "Langbein", role = "aut",
           comment = c(ORCID = "0000-0001-5629-2055"))
  )
Description: This package implements model-specific, gradient-based
        feature attribution methods for deep survival neural networks,
        including DeepHit, CoxTime, and DeepSurv. It accompanies the
        ICML 2025 paper "Gradient-based Explanations for Deep Learning
        Survival Models".
License: MIT + file LICENSE
Imports: checkmate, ggplot2, torch, dplyr, methods, utils
Suggests: data.table, keras, knitr, rmarkdown, simsurv, ggmap, cowplot,
        survminer, torchvision, survival, survivalmodels, patchwork,
        here, survex, SurvMetrics, tensorflow, testthat (>= 3.0.0)
Config/testthat/edition: 3
Encoding: UTF-8
Roxygen: list(markdown = TRUE)
RoxygenNote: 7.2.3
Config/Needs/website: rmarkdown
URL: https://bips-hb.github.io/survinng/
VignetteBuilder: knitr
Repository: https://bips-hb.r-universe.dev
Date/Publication: 2025-05-28 20:59:12 UTC
RemoteUrl: https://github.com/bips-hb/survinng
RemoteRef: HEAD
RemoteSha: 37e2ae011468f92544c10c6fa1398af92d922be9
NeedsCompilation: no
Packaged: 2026-06-09 05:58:59 UTC; root
Author: Niklas Koenen [aut, cre] (ORCID:
    <https://orcid.org/0000-0002-4623-8271>),
  Sophie Hanna Langbein [aut] (ORCID:
    <https://orcid.org/0000-0001-5629-2055>)
Maintainer: Niklas Koenen <niklas.koenen@gmail.com>
Depends: R (>= 4.1.0)