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..
Noisy Adaptation Generates Lévy Flights in Attractor Neural Networks
Authors: Xingsi Dong, Tianhao Chu, Tiejun Huang, Zilong Ji, Si Wu
NeurIPS 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We have included the code for reproducing the main results in the supplemental material. |
| Researcher Affiliation | Academia | 1, School of Psychology and Cognitive Sciences, Peking Univerisity. 2, IDG/Mc Govern Institute for Brain Research, Peking University. 3, PKU-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University. 4, School of Electronics Engineering and Computer Science, Peking University. |
| Pseudocode | No | The paper describes mathematical models and equations but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | We have included the code for reproducing the main results in the supplemental material. |
| Open Datasets | No | The paper mentions and models phenomena observed in human free memory retrieval based on a previous study [11]. However, it does not state that it uses a publicly available dataset for its *own* experiments or provides access information for such a dataset. |
| Dataset Splits | No | The paper describes theoretical analyses and simulations but does not specify dataset splits (e.g., training, validation, test) in the context of typical data-driven experiments. |
| Hardware Specification | No | We do not use GPU or CPU clusters. It is sufficient to run our code on a laptop. This statement indicates that specific hardware (like GPUs/CPUs) was not a focus, and does not provide any specific model numbers or detailed specifications of the 'laptop' used. |
| Software Dependencies | No | The paper does not list specific software names with version numbers for reproducibility (e.g., Python, PyTorch, or other libraries/solvers with their versions). |
| Experiment Setup | No | The paper states 'For the setting of hyperparameters, please see SI.4 in the Supplementary Information.' indicating that these details are not in the main text of the paper. |