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 Shift Toward Open and Reproducible AI Research," Under Review, 2026. doi: 10.48550/arXiv.2606.16974..
Expressive probabilistic sampling in recurrent neural networks
Authors: Shirui Chen, Linxing Jiang, Rajesh PN Rao, Eric Shea-Brown
NeurIPS 2023 | Venue PDF | LLM Run Details | Input Tokens: 25,776 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,419 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 4 Experimental results |
| Researcher Affiliation | Academia | Shirui Chen Department of Applied Mathematics University of Washington, Seattle EMAIL Linxing Preston Jiang Paul G. Allen School of Computer Science & Engineering University of Washington, Seattle EMAIL Rajesh P. N. Rao Paul G. Allen School of Computer Science & Engineering and Center for Neurotechnology University of Washington, Seattle EMAIL Eric Shea-Brown Department of Applied Mathematics Computational Neuroscience Center University of Washington, Seattle EMAIL |
| Pseudocode | Yes | Algorithm 1: Training RSN |
| Open Source Code | Yes | All code is available on Github |
| Open Datasets | Yes | MNIST dataset [32] |
| Dataset Splits | No | The paper mentions using MNIST and CIFAR-10 datasets and training for a certain number of iterations/epochs, but does not explicitly provide the train/validation/test dataset splits with percentages or sample counts. |
| Hardware Specification | Yes | All experiments were run on one NVIDIA Quadro RTX 6000 GPU. |
| Software Dependencies | No | The paper mentions using the Adam optimizer but does not provide specific version numbers for software dependencies or libraries used in the experiments. |
| Experiment Setup | Yes | The learning rate was 0.0001, and the batch size was 128. |