# SQL4NN: Validation and expressive querying of models as data

arXiv: https://arxiv.org/abs/2502.14745 · HTML: https://mlsanity.com/paper/2502.14745/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Builds on (most cited first, 9 of 9)

- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Algorithms for Verifying Deep Neural Networks](https://mlsanity.com/paper/1903.06758/) (2019)
- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Introduction to Neural Network Verification](https://mlsanity.com/paper/2109.10317/) (2021)
- [Foundations of Symbolic Languages for Model Interpretability](https://mlsanity.com/paper/2110.02376/) (2021)
- [Management of Machine Learning Lifecycle Artifacts: A Survey](https://mlsanity.com/paper/2210.11831/) (2022)
- [A Uniform Language to Explain Decision Trees](https://mlsanity.com/paper/2310.11636/) (2023)
- [Declarative Data Analytics: a Survey](https://mlsanity.com/paper/1902.01304/) (2019)

## Built on by (most cited first, 2 of 2)

- [Recursive querying of neural networks via weighted structures](https://mlsanity.com/paper/2601.03201/) (2026)
- [MLSkip: Data Skipping for ML Filters via Lightweight Metadata](https://mlsanity.com/paper/2606.03946/) (2026)

## Abstract (arXiv)

We consider machine learning models, learned from data, to be an important, intensional, kind of data in themselves. As such, various analysis tasks on models can be thought of as queries over this intensional data, often combined with extensional data such as data for training or validation. We demonstrate that relational database systems and SQL can actually be well suited for many such tasks.