Correctness Firewalls for Synthesized Database Components
cs.DB
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/RyanMarcus/correctness-firewalls
Terminology
Sources
- Investigating Test Overfitting on SWE-bench
- JetStream: Generating Verified Query Accelerators for Existing Database Systems
- AutoPilot: Learning to Steer High Speed Robust BFT
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models
- Constraint Decay: The Fragility of LLM Agents in Backend Code Generation
- ALEX: An Updatable Adaptive Learned Index
- XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models
- EvilGenie: A Reward Hacking Benchmark
- Robust Plan Evaluation based on Approximate Probabilistic Machine Learning
- Learned Cardinalities: Estimating Correlated Joins with Deep Learning
- GenDB: The Next Generation of Query Processing -- Synthesized, Not Engineered
- SpecDB: LLM-Generated Customized Databases via Feature-Oriented Decomposition
- SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?
- Learning Scheduling Algorithms for Data Processing Clusters
- Exploring Next Token Prediction For Optimizing Databases
- Bounding the Last Mile: Efficient Learned String Indexing
- GenJoin: Conditional Generative Plan-to-Plan Query Optimizer that Learns from Subplan Hints
Related papers
- Beyond Overlap: Hierarchical Graph Abstraction for Out-of-Core Vector Search
- EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
- Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
- Samyama: A Unified Graph-Vector Database with In-Database Optimization, Agentic Enrichment, and Hardware Acceleration
- GenTUS: Table Union Search via Constrained Generation of Semantic Table Identifiers
- Common-Neighbor-Count-Based Representative Possible World Finding on Uncertain Graphs