Reachability-Based Primitives for Graphical Causal Inference

Provides a framework for specifying and running flexible linear-time reachability-based algorithms for graphical causal inference. Rule tables are used to encode and customize the reachability algorithm to typical causal and probabilistic reasoning tasks such as finding d-connected nodes or more advanced applications. For more information, see Wienöbst, Weichwald and Henckel (2025) .

ciflyr

ciflyr is the R interface to the CIfly framework for designing efficient causal inference algorithms based on reductions to graph reachability specified by rule tables. For more information on CIfly, see our website and our paper.

Installation

install.packages("ciflyr")

Note that if the package is build from source on your system, as is the case for Linux distributions, the Rust toolchain needs to be installed.

Usage

As a basic example, we show how to test d-separation with CIfly. The CIfly algorithm specified by the rule table in the variable dsepTable returns all nodes d-connected to the set of nodes X given set Z. Based on this information, testing d-separation reduces to checking membership in a vector.

library(ciflyr)

dsepTable <- "
EDGES --> <--
SETS X, Z
START <-- AT X
OUTPUT ...

--> | <-- | current in Z
... | ... | current not in Z
"

test_dsep <- function(G, x, y, Z) {
      R <- reach(G, list("X" = x, "Z" = Z), dsepTable, tableAsString=TRUE)
      return (!(y %in% R))
}
# for graph 1 -> 2 -> 3, test whether 1 is d-separated from 3 by 2
print(test_dsep(list("-->" = rbind(c(1, 2), c(2, 3))), 1, 3, c(2)))
#> [1] TRUE