icse-seip2025-anomaly-detector-public - Version 1.0.2: README Updates for Enhanced Usability (22 January 2025)

This third release builds upon v1.0.1 and focuses on improving user experience by providing clearer documentation for execution using Docker containers and Virtual Machines. Key changes include:

README Updates: - Enhanced instructions for setting up and running the code using Docker containers. - Added detailed steps for executing the project in a Virtual Machine environment. - Improved clarity and structure for ease of use by both beginners and advanced users.

Backward Compatibility: This release is fully backward compatible with v1.0.1 and does not introduce any breaking changes.

Contributors to this release: @miranska @janakan2466 @msi-ru-cs

- Python
Published by msi-ru-cs about 1 year ago

icse-seip2025-anomaly-detector-public - Version 1.0.1: Snapshot with Reproducibility Enhancements (12 January 2025)

This second release incorporates minor updates to enhance usability and reproducibility. Key changes include:

Dockerfile: Added a Dockerfile to simplify environment setup and enhance reproducibility for users. Improved Documentation: Updated README with details on using the Dockerfile and running the code in a containerized environment.

This release maintains backward compatibility and builds upon the initial public release (v1.0.0).

Contributors to this release: @miranska @janakan2466 @msi-ru-cs

- Python
Published by msi-ru-cs about 1 year ago

icse-seip2025-anomaly-detector-public - ICSE SEIP 2025 Artifact: Anomaly Detection in Large-Scale Cloud Systems: An Industry Case and Dataset

This release accompanies the ICSE 2025 paper titled "Anomaly Detection in Large-Scale Cloud Systems: An Industry Case and Dataset." It includes:

• Source Code: Implementation of the anomaly detection framework discussed in the paper.
• Dataset: High-dimensional telemetry data from IBM Cloud, collected over 4.5 months from the IBM Cloud Console.
• Documentation: Detailed instructions on setup, usage, and replication of results.

Contributors to this release: - @miranska - @msi-ru-cs - @DrRakha - @janakan2466 - @WilliamPourmajidi

Researchers and practitioners can utilize this artifact to replicate our findings and apply the methods to similar large-scale cloud systems. For more information, refer to the included README.md and the published paper.

- Python
Published by msi-ru-cs about 1 year ago