sqpeWhat it contributes
Studies how repeated model decisions propagate into changing query answers and proposes reporting practices for reproducible evaluation.
How to read the evidence
October 2026 preprint. This is an evaluation study rather than a new engine; findings concern the tested models and workloads.
We checked the primary publication record and abstract. This profile summarizes author-reported work; it does not claim a full-paper audit, implementation audit, or independent reproduction.
Explore the connections
- The Stochastic Shift — Evaluation of SQL containing AI operators
- DocETL — Declarative pipelines
- SemBench — Benchmark workloads