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..
IPSI: Enhancing Structural Inference with Automatically Learned Structural Priors
Authors: Zhongben Gong, Xiaoqun Wu, Mingyang Zhou
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on synthetic datasets of physical systems demonstrate that IPSI significantly enhances the performance of structural inference models such as Neural Relational Inference (NRI). Ablation studies reveal that feature and structural prior inputs to the joint module offer complementary improvements from representational and generative perspectives. |
| Researcher Affiliation | Academia | Zhongben Gong Xiaoqun Wu Mingyang Zhou College of Computer Science and Software Engineering, Shenzhen University EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper only describes the methodology using text and mathematical equations, and provides a pipeline illustration (Figure 2), but does not include any explicitly labeled 'Pseudocode' or 'Algorithm' block. |
| Open Source Code | Yes | Code is available at https://github.com/blackbird1729/IPSI. |
| Open Datasets | Yes | To evaluate the effectiveness of the two supervision strategies, we focus on the three synthetic physical systems proposed in [8] the spring, charged particle, and Kuramoto oscillator systems as our synthetic meta-datasets are constructed based on the spring and charged particle systems. |
| Dataset Splits | Yes | The data is split into training, validation, and test sets with a 5:1:1 ratio. |
| Hardware Specification | Yes | The details of the computational resources used in the experiment are described in the supplementary materials |
| Software Dependencies | No | The paper does not explicitly state specific software dependencies with version numbers in the main text. It mentions algorithms like GRU [3] and the Adam optimizer but not the software environment or libraries used with versions. |
| Experiment Setup | No | The paper states, 'Section 5 and supplementary materials detail the the training and test details.' However, specific hyperparameters such as learning rate, batch size, or number of epochs are not explicitly provided in the main text. |