# MLSkip: Data Skipping for ML Filters via Lightweight Metadata

arXiv: https://arxiv.org/abs/2606.03946 · HTML: https://mlsanity.com/paper/2606.03946/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 45 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks](https://mlsanity.com/paper/1702.01135/) (2017)
- [Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification](https://mlsanity.com/paper/2103.06624/) (2021)
- [Introduction to Neural Network Verification](https://mlsanity.com/paper/2109.10317/) (2021)
- [Provably Bounding Neural Network Preimages](https://mlsanity.com/paper/2302.01404/) (2023)
- [The 6th International Verification of Neural Networks Competition (VNN-COMP 2025): Summary and Results](https://mlsanity.com/paper/2512.19007/) (2025)
- [Extending Relational Query Processing with ML Inference](https://mlsanity.com/paper/1911.00231/) (2019)
- [Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB](https://mlsanity.com/paper/2504.01157/) (2025)
- [Query Processing on Tensor Computation Runtimes](https://mlsanity.com/paper/2203.01877/) (2022)
- [Cortex AISQL: A Production SQL Engine for Unstructured Data](https://mlsanity.com/paper/2511.07663/) (2025)
- [Reachable Polyhedral Marching (RPM): An Exact Analysis Tool for Deep-Learned Control Systems](https://mlsanity.com/paper/2210.08339/) (2022)
- [Terabyte-Scale Analytics in the Blink of an Eye](https://mlsanity.com/paper/2506.09226/) (2025)
- [100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models](https://mlsanity.com/paper/2603.15970/) (2026)
- [SQL4NN: Validation and expressive querying of models as data](https://mlsanity.com/paper/2502.14745/) (2025)

## Abstract (arXiv)

Database vendors recently released AI functions that can be used in filter predicates. As such functions often rely on costly, black-box ML models, they unveil new data management challenges. Concretely, traditional data skipping techniques for integer and string data fail to be applicable to the new filter type. Indeed, there is no known mechanism for pruning non-qualifying row groups, e.g., when reading files from blob storage. In this work, we initiate the study of data skipping techniques for ML filters. We make the case that Parquet's default min-max metadata is enough to enable pruning. To this end, we draw connections to two lines of research: (i) the recently proposed query language for ML models and (ii) neural network verification. Our preliminary results on ReLU architectures show that on tables from TPC-H and TPC-DS, the average pruning effectiveness for filters of selectivity below 0.1% amounts to 27.4%. Finally, inspired by research on spatial joins, we propose an enhanced metadata structure: a size-bounded 2D convex hull that verification tools can make better use of, increasing the pruning effectiveness to 38.31%, while occupying at most 45 bytes per row group and column pair. We observe an end-to-end speedup of 1.07× over PyTorch in DuckDB.