Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism
Authors: Reda Marzouk, Shahaf Bassan, Guy Katz
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This is a theoretical work, so experimental reproducibility is not relevant. |
| Researcher Affiliation | Academia | Reda Marzouk LIRMM, UMR 5506, University of Montpellier, CNRS EMAIL Bassan* The Hebrew University of Jeursalem EMAIL Katz The Hebrew University of Jeursalem EMAIL |
| Pseudocode | Yes | Algorithm 1 The construction of the Marginal SHAP Tensor |
| Open Source Code | No | This is a theoretical work, so providing open access to data and code is not applicable. |
| Open Datasets | No | This is a theoretical work, so providing open access to data and code is not applicable. |
| Dataset Splits | No | This is a theoretical work, so experimental reproducibility is not relevant. |
| Hardware Specification | No | This is a theoretical work, so no details on computational resources are required. |
| Software Dependencies | No | This is a theoretical work, and no hyperparameter details are needed. |
| Experiment Setup | No | This is a theoretical work, and no hyperparameter details are needed. |