Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Certifiable Robustness to Graph Perturbations
Authors: Aleksandar Bojchevski, Stephan Günnemann
NeurIPS 2019 | Venue PDF | LLM Run Details | Input Tokens: 19,529 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,801 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 | We demonstrate our claims on two publicly available datasets: Cora-ML (N = 2, 995, |E| = 8, 416, D = 2, 879, K = 7) [4, 30] and Citeseer (N = 3, 312, |E| = 4, 715, D = 3, 703, K = 6) [37] with further experiments on Pubmed (N = 19, 717, |E| = 44, 324, D = 500, K = 3) [37] in the appendix. |
| Researcher Affiliation | Academia | Aleksandar Bojchevski Technical University of Munich EMAIL Stephan Günnemann Technical University of Munich EMAIL |
| Pseudocode | Yes | Algorithm 1 POLICY ITERATION WITH LOCAL BUDGET |
| Open Source Code | Yes | the code is provided for reproducibility1. Footnote 1: Code, data, and supplementary material available at https://www.daml.in.tum.de/graph-cert |
| Open Datasets | Yes | We demonstrate our claims on two publicly available datasets: Cora-ML (N = 2, 995, |E| = 8, 416, D = 2, 879, K = 7) [4, 30] and Citeseer (N = 3, 312, |E| = 4, 715, D = 3, 703, K = 6) [37] with further experiments on Pubmed (N = 19, 717, |E| = 44, 324, D = 500, K = 3) [37] in the appendix. |
| Dataset Splits | Yes | We select 20 nodes per class for the train/validation set and use the rest for the test set. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory amounts) were found. The paper does not mention any specific hardware used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies, libraries, or solvers used in the experiments. |
| Experiment Setup | Yes | We configure π-PPNP with one hidden layer of size 64 and set α = 0.85. |