sqpeWhat it contributes
Studies failures of exact-result scoring for SQL with stochastic AI operators. Proposes evaluating relational logic and semantic operations separately, with experiments on BigQuery and ThalamusDB.
How to read the evidence
An evaluation framework rather than a general-purpose workload benchmark. Reported validation accuracy applies to the tested query sets and judging protocol, not all SQL translations or semantic predicates.
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
- Same Query, Different Answer — Repeated benchmark executions
- DocETL — Declarative pipelines
- SemBench — Benchmark workloads