splitcheck is an open-source CLI tool that detects row overlap and leakage between dataset splits, helping machine learning engineers maintain data integrity. It is useful for ensuring that training and test sets are properly separated to avoid data leakage in ML workflows.
In the LLM eval & observability space, splitcheck takes a focused approach. It focuses on preventing data leakage and ensuring proper separation between training and test datasets in machine learning workflows. It is built as an open-source project for machine learning engineers. splitcheck is open source under the MIT license. It runs on the command line.
It is developed by jmweb-org, and the product first shipped in 2026. Development happens publicly on GitHub with 13 commits in the last 90 days. Key capabilities include row overlap detection, leakage detection, and dataset split analysis.
Latest indexed changes and source events
Other apps tracked under the same category.
