tpc-h-54f4bbc7·2 events·first seen Aliases: TPC-H
Researchers present Jailbreak, a system that uses LLMs to synthesize storage readers that bypass database drivers (JDBC/ODBC) entirely by reading PostgreSQL and MySQL storage files directly and materializing data as Apache Arrow columnar buffers. The approach leverages LLMs to ingest database source code and documentation and regenerate format-specific parsing logic without human engineering. Evaluated against TPC-H benchmarks, the generated readers achieve up to 27x speedup over driver-based baselines and produce output consumable by DuckDB, Apache Spark, cuDF, and Spark RAPIDS. The paper argues this methodology generalizes to any database system whose file format is documented or open-source.
MLSkip introduces data skipping techniques for ML-based filter predicates in databases, a problem not addressed by traditional min-max pruning methods. The approach leverages Parquet's existing min-max metadata combined with neural network verification techniques to prune non-qualifying row groups. On TPC-H and TPC-DS benchmarks with ReLU architectures, the method achieves 27.4% average pruning effectiveness for low-selectivity filters, improving to 38.31% with a proposed 2D convex hull metadata structure, yielding a 1.07× end-to-end speedup in DuckDB over PyTorch.