Sensitivity Analysis of Linear Structural Causal Models

Authors: Carlos Cinelli, Daniel Kumor, Bryant Chen, Judea Pearl, Elias Bareinboim

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We have performed an exhaustive study of all possible queries in 3 and 4-node models, which are essentially the largest instances computer algebra methods can solve through brute force.7
Researcher Affiliation Collaboration 1Depts. of Statistics and Computer Science, University of California, Los Angeles, California, USA. 2Dept. of Computer Science, Purdue University, West Lafayette, IN, USA. 3Brex, San Francisco, CA, USA. Most of this work was conducted while at IBM Research AI.
Pseudocode Yes Algorithm 1 CID(G, Σ, D, B)
Open Source Code No The paper does not contain an explicit statement about releasing the source code for the methodology described, nor does it provide a direct link to a code repository.
Open Datasets No The paper describes experiments on '3 and 4-node models' and 'numerical simulation', which appear to be synthetic graph structures rather than conventional public datasets, and does not provide any access information (link, citation, or repository) for data used in the experiments.
Dataset Splits No The paper does not provide specific details on training, validation, or test dataset splits, as its computational experiments involve synthetic models and identifiability checks rather than machine learning dataset splits.
Hardware Specification No The paper does not explicitly describe the specific hardware (e.g., GPU models, CPU types, memory amounts) used to run its computational experiments.
Software Dependencies Yes The Sage Developers. Sage Math, the Sage Mathematics Software System (Version 8.5), 2018. https://www.sagemath.org.
Experiment Setup No The paper describes the scope and methodology of its computational experiments (e.g., 'exhaustive study of all possible queries in 3 and 4-node models', 'using algebraic methods to determine ground-truth identification') but does not provide specific hyperparameter values, training configurations, or system-level settings typically found in experimental setups.