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..
Intelligent Virtual Machine Provisioning in Cloud Computing
Authors: Chuan Luo, Bo Qiao, Xin Chen, Pu Zhao, Randolph Yao, Hongyu Zhang, Wei Wu, Andrew Zhou, Qingwei Lin
IJCAI 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments show that UAHS performs much better than state-of-the-art competitors on two public datasets and an industrial dataset. UAHS has been successfully applied in Microsoft Azure and brought practical benefits in real-world applications. |
| Researcher Affiliation | Collaboration | Chuan Luo1 , Bo Qiao1 , Xin Chen1 , Pu Zhao1 , Randolph Yao2 , Hongyu Zhang3 , Wei Wu4 , Andrew Zhou5 and Qingwei Lin1, 1Microsoft Research, China 2Microsoft Azure, United States 3The University of Newcastle, Australia 4University of Technology Sydney, Australia 5Microsoft Office, China |
| Pseudocode | Yes | Algorithm 1: Algorithm for searching configuration Algorithm 2: Function Predict Algorithm 3: Function Optimize |
| Open Source Code | No | The paper does not provide a direct link to the source code for the described methodology or explicitly state that the code is open-source. It provides a link to public datasets. |
| Open Datasets | Yes | To study the performance of UAHS, we conduct extensive experiments on two public datasets5 [Cortez et al., 2017] collected from Microsoft Azure, dubbed Azure-2017 and Azure-2019. [...] 5https://github.com/Azure/Azure Public Dataset |
| Dataset Splits | No | The paper describes how instances are constructed from the datasets: 'we construct 42 instances by taking all sub-time series in length of 139 (i.e., 180 42 + 1) time stamps using the sliding window based time series analysis approach [Box et al., 2015], each of which has the demand on the last time stamp as label.' However, it does not specify a distinct training, validation, and test split for the overall UAHS system's evaluation, but rather evaluates performance 'across all instances'. |
| Hardware Specification | Yes | In this work, all experiments were conducted on a machine with Intel Xeon E5-2673 CPU and 256 GB memory, running GNU/Linux. |
| Software Dependencies | No | The paper mentions the operating system ('GNU/Linux') but does not provide specific version numbers for other key software dependencies like programming languages, libraries, or frameworks used in the experiments. |
| Experiment Setup | Yes | For UAHS, the hyper-parameter settings of max_iter and prob are set to 50 and 0.9, respectively. The effects of different hyper-parameter settings of max_iter and prob are discussed in Section 5.4. |