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..
CoNSoLe: Convex Neural Symbolic Learning
Authors: Haoran Li, Yang Weng, Hanghang Tong
NeurIPS 2022 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we demonstrate the superior performance of the CONSOLE framework over the state-of-the-art on a diverse set of datasets. 1 Introduction ...5 Experiments ...5.1 Settings ...5.2 Verification and 3-D Visualization of Convex Mechanisms ...5.3 Convexity Guarantees of CONSOLE to Learn Correct Equations ...5.4 Ablation Study: Exploration and Convex Search are Essential ...5.5 CONSOLE is Robust with Changing Noise Levels and Data Volume |
| Researcher Affiliation | Academia | Haoran Li Yang Weng Arizona State University Tempe, AZ, 85287 EMAIL Hanghang Tong University of Illinois Urbana-Champaign Champaign, IL, 61820 EMAIL |
| Pseudocode | Yes | The overview of our framework is in Appendix A.1, Algorithm 1. The specific algorithm is in Appendix A.2, Algorithm 2. |
| Open Source Code | No | The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | The paper describes creating its own synthetic datasets (Syn1, Syn2) and generating data through simulations using MATPOWER [39] for the Pow dataset and MATLAB for the Mas dataset. No concrete access information for publicly available datasets is provided. |
| Dataset Splits | No | The paper describes training and testing data splits (e.g., '2,000 samples for training... another 2,000 samples... for test'; 'first 8,760 points are used for training while the remaining samples are used for testing'), but does not explicitly mention a separate validation dataset split. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'MATPOWER' and 'MATLAB' for simulations, but does not provide specific version numbers for these or any other software dependencies required to replicate the experiments. |
| Experiment Setup | Yes | Finally, the hyper-parameter settings can be seen in Appendix A.7. |