Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing

ArXi:2503.07823v2 Announce Type: replace-cross Graph-based techniques relying on neural networks and embeddings have gained attention as a way to develop Recommender Systems (RS) with several papers on the topic presented at SIGIR 2022 and 2023. Given the importance of ensuring that published research is methodologically sound and reproducible, in this paper we analyze 10 graph-based RS papers, most of which were Our analysis reveals several critical points that require attention: (i) the prevalence of bad practices, such as erroneous data splits or information leakage between.