Causal Identification under Markov equivalence: Calculus, Algorithm, and Completeness

Authors: Amin Jaber, Adele Ribeiro, Jiji Zhang, Elias Bareinboim

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental An empirical evaluation of CIDP is provided in the full report [Jaber et al., 2022]. Code is available at https://github.com/Causal AILab/PAGId
Researcher Affiliation Academia Amin Jaber Purdue University jaber0@purdue.edu Adèle H. Ribeiro Columbia University adele@cs.columbia.edu Jiji Zhang Hong Kong Baptist University zhangjiji@hkbu.edu.hk Elias Bareinboim Columbia University eb@cs.columbia.edu
Pseudocode Yes Algorithm 1 IDP(P, x, y) and Algorithm 2 CIDP(P, x, y, z) are clearly labeled algorithm blocks.
Open Source Code Yes Code is available at https://github.com/Causal AILab/PAGId
Open Datasets No The paper refers to an 'observational distribution P(V)' and 'observational data' but does not specify any particular datasets used for training models in the main text. An empirical evaluation is mentioned as being in a separate full report.
Dataset Splits No The paper does not explicitly provide training/validation/test dataset splits. While an empirical evaluation is mentioned, the details of data splits are not provided in this paper.
Hardware Specification No The paper does not specify any hardware used for running experiments.
Software Dependencies No The paper does not provide specific version numbers for software dependencies.
Experiment Setup No The paper does not contain specific details about experimental setup, such as hyperparameters or system-level training settings.