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..
Context-based Unsupervised Data Fusion for Decision Making
Authors: Erfan Soltanmohammadi, Mort Naraghi-Pour, Mihaela Schaar
ICML 2015 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Numerical results show the dramatic improvement of the proposed method as compared with the state of the art approaches. In this section, first we use a system with up to 8 classifiers to evaluate the performance of the proposed approach. |
| Researcher Affiliation | Collaboration | Erfan Soltanmohammadi EMAIL Marvell Semiconductor, Inc., Santa Clara, CA, USA. Mort Naraghi-Pour EMAIL Louisiana State University, Baton Rouge, LA, USA. Mihaela van der Schaar EMAIL University of California, Los Angeles, CA, USA. |
| Pseudocode | Yes | Algorithm 1 Estimation of the parameter set and FC s decisions |
| Open Source Code | No | No statement about providing open-source code or a link to a code repository is found in the paper. |
| Open Datasets | Yes | In order to evaluate the performance of the proposed approach for real data, we used the Wisconsin breast cancer data set (Murphy & Aha, 1994). |
| Dataset Splits | No | The paper mentions "training and validation" in the context of other methods (e.g., "requires large training and validation data sets (Huang & Suen, 1995)") but does not specify train/validation/test splits for its own experimental setup for reproducibility. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory) used for running experiments are mentioned in the paper. |
| Software Dependencies | No | The paper mentions using "machine learning classifiers from Weka" and cites a book for detailed descriptions, but it does not provide specific version numbers for Weka or any other software dependencies required to replicate the experiment. |
| Experiment Setup | Yes | The parameter T is chosen to be 100. We initialize the EM algorithm with all the probabilities of false alarm equal to 0.2, all the probabilities of detection equal to 0.8, and φ1(t) = 0.6 for t = t0, t0 + 1, , T + t0 1. Here we set cik = c for all i = 0, 1 and k = 1, 2, , K. Three different values of c = 0.2, 1.7, 3.2 are used. for each i and k we set the Lipschitz constants cik = 0.058. |