MLSkip: Data Skipping for ML Filters via Lightweight Metadata

arXiv:2606.03946 · cs.DB, cs.LG, cs.LO · Submitted 2026-06-02 · Read on arXiv

cs.DB, cs.LG, cs.LO

Submitted: 2026-06-02

Updated: 2026-09-23

Comments: 7th International Workshop on Applied AI for Database Systems and Applications (AIDB 2026)

Code: https://github.com/mlskip/mlskip

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verification — 30× in this paper · explained in 2 episodes
• Pruning — 26× in this paper · explained in 4 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Activation Function — 2× in this paper · explained in 1 episode
• Robustness — 2× in this paper · explained in 5 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Analyzer — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Conference on Innovative Database Research — 1× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cylindrical Algebraic Decomposition — 1× in this paper
• Embeddings — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes
• SMT solver — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Cortex AISQL: A Production SQL Engine for Unstructured Data
• Introduction to Neural Network Verification
• 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
• Extending Relational Query Processing with ML Inference
• The 6th International Verification of Neural Networks Competition (VNN-COMP 2025): Summary and Results
• Semantic Operators: A Declarative Model for Rich, AI-based Data Processing
• Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations

Related papers

• Cost-Aware Mixture-of-Experts Coordination for Model Markets
• Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries
• Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering
• MetaJoin: Adaptive Join Selections for Heterogeneous Tables
• Bridging Business Intent and Data: A Benchmark for Automatic Relational Data Product Generation
• DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation