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 [1].

GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models Through Statistically-Guided Geo-Prototyping

Authors: Bang An, Xun Zhou, Zirui Zhou, Ronilo Ragodos, Zenglin Xu, Jun Luo

AAAI 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experiments and case studies on four real-world datasets demonstrate that Geo Pro Net provides better interpretability while still achieving competitive prediction performance compared with state-of-the-art baselines.
Researcher Affiliation Collaboration 1School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen 2Scheller College of Business, Georgia Institute of Technology 3Tippie College of Business, University of Iowa 4Artificial Intelligence Innovation and Incubation Institute, Fudan University 5Logistics and Supply Chain Multi Tech R&D Centre
Pseudocode No The paper describes the methodology in narrative text and mathematical equations, and provides an architectural diagram (Figure 1), but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statement about releasing source code for the described methodology, nor does it provide a link to a code repository.
Open Datasets Yes We perform comprehensive experiments using four real-world traffic accident and crime datasets from Chicago1 and New York City2. 1https://data.cityofchicago.org/Transportation/Traffic-Crashes-Crashes/85ca-t3if 2https://opendata.cityofnewyork.us/
Dataset Splits Yes For the Chicago dataset, the time frame spans from 2019 to 2021, with the initial 18 months serving as the training set and the entirety of 2021 as the testing set.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions various models and statistical tests, but does not provide specific version numbers for any software dependencies, libraries, or frameworks used for implementation or experimentation.
Experiment Setup No The paper defines the objective function including regularization terms and mentions that K is a hyperparameter, but it does not specify concrete values for hyperparameters such as learning rate, batch size, number of epochs, optimizer settings, or the values for the regularization coefficients (λ1, λ2, λ3) used in the experiments.