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..
Negative Flux Aggregation to Estimate Feature Attributions
Authors: Xin Li, Deng Pan, Chengyin Li, Yao Qiang, Dongxiao Zhu
IJCAI 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Both qualitative and quantitative experiments demonstrate a superior performance of Ne FLAG in generating more faithful attribution maps than the competing methods. |
| Researcher Affiliation | Academia | Xin Li , Deng Pan , Chengyin Li , Yao Qiang and Dongxiao Zhu Department of Computer Science, Wayne State University, USA EMAIL |
| Pseudocode | Yes | Algorithm 1 Ne FLAG(f, x, n, Sx, ϵ, m) |
| Open Source Code | Yes | Our code is available at https://github.com/xinli0928/Ne FLAG. |
| Open Datasets | Yes | Dataset. The Image Net [Deng et al., 2009] dataset is used for all of our experiments. |
| Dataset Splits | Yes | We randomly select 5,000 samples from Image Net validation dataset with 5 samples from each class as a good representation of the classes. |
| Hardware Specification | No | The paper does not provide specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running its experiments. |
| Software Dependencies | No | The paper mentions using 'captum' but does not provide any specific version numbers for software dependencies or libraries. |
| Experiment Setup | Yes | The Ne FLAG is configured as follows: ϵ-sphere radius is set to ϵ = 0.1, and the number of random negative flux point x is n = 20. (...) For AGI, we adopt the default parameter settings reported in [Pan et al., 2021], i.e., step size ϵ = 0.05, number of false classes n = 20. |