# A Configuration-First Framework for Reproducible, Low-Code Machine Learning: a Localization Use Case

arXiv: https://arxiv.org/abs/2510.25692 · HTML: https://mlsanity.com/paper/2510.25692/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 53 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [Accounting for Variance in Machine Learning Benchmarks](https://mlsanity.com/paper/2103.03098/) (2021)
- [Machine Learning Operations (MLOps): Overview, Definition, and Architecture](https://mlsanity.com/paper/2205.02302/) (2022)
- [Interpretable Scientific Discovery with Symbolic Regression: A Review](https://mlsanity.com/paper/2211.10873/) (2022)
- [Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence](https://mlsanity.com/paper/2002.04803/) (2020)
- [Reproducibility in Machine Learning-based Research: Overview, Barriers and Drivers](https://mlsanity.com/paper/2406.14325/) (2024)
- [Ludwig: a type-based declarative deep learning toolbox](https://mlsanity.com/paper/1909.07930/) (2019)
- [EasyFL: A Low-code Federated Learning Platform For Dummies](https://mlsanity.com/paper/2105.07603/) (2021)
- [Novel Massive MIMO Channel Sounding Data Applied to Deep Learning-based Indoor Positioning](https://mlsanity.com/paper/1810.04126/) (2018)
- [Good Enough Practices in Scientific Computing](https://mlsanity.com/paper/1609.00037/) (2016)
- [Localization as a key enabler of 6G wireless systems: A comprehensive survey and an outlook](https://mlsanity.com/paper/2302.02107/) (2023)
- [On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards](https://mlsanity.com/paper/2407.04065/) (2024)
- [Reasonable Scale Machine Learning with Open-Source Metaflow](https://mlsanity.com/paper/2303.11761/) (2023)
- [Massive MIMO Channel Measurements and Achievable Rates in a Residential Area](https://mlsanity.com/paper/2002.09452/) (2020)
- [ML-Quadrat & DriotData: A Model-Driven Engineering Tool and a Low-Code Platform for Smart IoT Services](https://mlsanity.com/paper/2107.02692/) (2021)
- [MLXP: A Framework for Conducting Replicable Experiments in Python](https://mlsanity.com/paper/2402.13831/) (2024)
- [Making sense of AI systems development](https://mlsanity.com/paper/2408.04311/) (2024)
- [Indoor Positioning with Wi-Fi Location: A Survey of IEEE 802.11mc/az/bk Fine Timing Measurement Research](https://mlsanity.com/paper/2509.03901/) (2025)

## Abstract (arXiv)

As machine learning underpins more critical applications, the value of a reported result depends on whether it can be compared and repeated. In practice, this remains difficult: research groups often assemble their own tools for configuration, execution, versioning, and evaluation, while also repeating the domain-specific work such as dataset preparation and baseline implementation. We present a configuration-first design for application-specific ML experimentation frameworks that addresses these sources of repeated effort. An experiment is declared in human-readable configuration files; a workflow orchestrator executes each stage as an isolated process that communicates only through explicit inputs and outputs; and code, data, configurations, environment specifications, and generated artifacts are versioned together, so that a recorded run can be inspected and repeated. We instantiate the design as LOCALIZE for radio-localization research, which supplies preconfigured datasets, processing stages, model-development procedures, and experiment templates while leaving the underlying pipeline open to modification. A qualitative comparison against five experimentation platforms, together with controlled quantitative studies against matched Jupyter notebook and Kedro implementations, shows that for the localization workflows studied, changes covered by LOCALIZE's supplied components require fewer codebase edits, while total wall-clock time and peak memory usage remain comparable. In a controlled scaling experiment at 1x, 5x, and 10x the base dataset volume, total CPU and wall time grew sublinearly over the tested sizes.