LLMs deployed for natural-language querying of analytical databases suffer from two intertwined failures - incorrect answers and confident hallucinations - both rooted in the same cause: the model is forced to infer business semantics that the schema does not encode. We test whether supplying those semantics as context closes the gap. We benchmark three frontier LLMs (Claude Opus 4.7, Claude Sonnet 4.6, GPT-5.4) on 100 natural-language questions over the Cleaned Contoso Retail Dataset in ClickHouse, using a paired single-shot protocol. Each model is evaluated twice: once given only the warehouse schema, and once given the schema plus a 4 KB hand-authored markdown document describing the dataset's measures, conventions, and disambiguation rules. Adding the document improves accuracy by +17 to +23 percentage points across all three models. With it, the three models are statistically indistinguishable (67.7-68.7%); without it, they are also indistinguishable (45.5-50.5%). Every cross-cluster comparison is significant at p < 0.01. The presence of the semantic-layer document accounts for essentially all of the significant variance; model choice within tier does not. We interpret this
Traditional database fuzzing techniques primarily focus on syntactic correctness and general SQL structures, leaving critical yet obscure DBMS features, such as system-level modes (e.g., GTID), programmatic constructs (e.g., PROCEDURE), advanced process commands (e.g., KILL), largely underexplored. Although rarely triggered by typical inputs, these features can lead to severe crashes or security issues when executed under edge-case conditions. In this paper, we present FuzzySQL, a novel LLM-powered adaptive fuzzing framework designed to uncover subtle vulnerabilities in DBMS special features. FuzzySQL combines grammar-guided SQL generation with logic-shifting progressive mutation, a novel technique that explores alternative control paths by negating conditions and restructuring execution logic, synthesizing structurally and semantically diverse test cases. To further ensure deeper execution coverage of the back end, FuzzySQL employs a hybrid error repair pipeline that unifies rule-based patching with LLM-driven semantic repair, enabling automatic correction of syntactic and context-sensitive failures. We evaluate FuzzySQL across multiple DBMSs, including MySQL, MariaDB, SQLite, Pos
The proliferation of unstructured data poses a fundamental challenge to traditional database interfaces. While Text-to-SQL has democratized access to structured data, it remains incapable of interpreting semantic or multi-modal queries. Concurrently, vector search has emerged as the de facto standard for querying unstructured data, but its integration with SQL-termed VectorSQL-still relies on manual query crafting and lacks standardized evaluation methodologies, creating a significant gap between its potential and practical application. To bridge this fundamental gap, we introduce and formalize Text2VectorSQL, a novel task to establish a unified natural language interface for seamlessly querying both structured and unstructured data. To catalyze research in this new domain, we present a comprehensive foundational ecosystem, including: (1) A scalable and robust pipeline for synthesizing high-quality Text-to-VectorSQL training data. (2) VectorSQLBench, the first large-scale, multi-faceted benchmark for this task, encompassing 12 distinct combinations across three database backends (SQLite, PostgreSQL, ClickHouse) and four data sources (BIRD, Spider, arXiv, Wikipedia). (3) Several nov
Traditional query processing relies on engines that are carefully optimized and engineered by many experts. However, new techniques and user requirements evolve rapidly, and existing systems often cannot keep pace. At the same time, these systems are difficult to extend due to their internal complexity, and developing new systems requires substantial engineering effort and cost. In this paper, we argue that recent advances in Large Language Models (LLMs) are starting to shape the next generation of query processing systems. We propose using LLMs to synthesize execution code for each incoming query, instead of continuously building, extending, and maintaining complex query processing engines. As a proof of concept, we present GenDB, an LLM-powered agentic system that generates instance-optimized and customized query execution code tailored to specific data, workloads, and hardware resources. We implemented an early prototype of GenDB that uses Claude Code Agent as the underlying component in the multi-agent system, and we evaluate it on OLAP workloads. We use queries from the well-known TPC-H benchmark and also construct a new benchmark designed to reduce potential data leakage from
In this study, we optimize SQL+ML queries on top of OpenMLDB, an open-source database that seamlessly integrates offline and online feature computations. The work used feature-rich synthetic dataset experiments in Docker, which acted like production environments that processed 100 to 500 records per batch and 6 to 12 requests per batch in parallel. Efforts have been concentrated in the areas of better query plans, cached execution plans, parallel processing, and resource management. The experimental results show that OpenMLDB can support approximately 12,500 QPS with less than 1 ms latency, outperforming SparkSQL and ClickHouse by a factor of 23 and PostgreSQL and MySQL by 3.57 times. This study assessed the impact of optimization and showed that query plan optimization accounted for 35% of the performance gains, caching for 25%, and parallel processing for 20%. These results illustrate OpenMLDB's capability for time-sensitive ML use cases, such as fraud detection, personalized recommendation, and time series forecasting. The system's modular optimization framework, which combines batch and stream processing without interference, contributes to its significant performance gain over
Large language models (LLMS) have shown increasing effectiveness in Text-to-SQL tasks. However, another closely related problem, Cross-System SQL Translation (a.k.a., SQL-to-SQL), which adapts a query written for one database system (e.g., MySQL) into its equivalent one for another system (e.g., ClickHouse), is of great practical importance but remains underexplored. Existing SQL benchmarks are not well-suited for SQL-to-SQL evaluation, which (1) focus on a limited set of database systems (often just SQLite) and (2) cannot capture many system-specific SQL dialects (e.g., customized functions, data types, and syntax rules). Thus, in this paper, we introduce PARROT, a Practical And Realistic BenchmaRk for CrOss-System SQL Translation. PARROT comprises 598 translation pairs from 38 open-source benchmarks and real-world business services, specifically prepared to challenge system-specific SQL understanding (e.g., LLMS achieve lower than 38.53% accuracy on average). We also provide multiple benchmark variants, including PARROT-Diverse with 28,003 translations (for extensive syntax testing) and PARROT-Simple with 5,306 representative samples (for focused stress testing), covering 22 prod
This paper presents an open-source software application for analyzing traffic camera footage, focusing on vehicle behavior and braking events at signalized urban highways. The core innovation is a robust ground-plane homography estimation that links fixed traffic camera views to satellite orthoimagery. This process rectifies the camera's oblique perspective, ensuring that pixel distances accurately represent real-world distances. This enables the acquisition of features such as vehicle trajectory, speed, deceleration, and braking severity without the need for camera calibration. The pipeline employs the MAGSAC++ estimator to build the homography, converting YOLO11 object detections into a rectified top-down coordinate system. All detection and trajectory data are stored in a ClickHouse database for subsequent analysis. A real-world case study at two signalized intersections in Key West, Florida, showcased the system's capabilities. Across two days of daytime footage, braking activity at the higher-volume intersection peaked around 4 PM at approximately 57.5 events per hour, while the second intersection peaked around 10 AM at roughly 15.5 events per hour. The spatial analysis revea
This paper presents a benchmarking suite designed for the evaluation and comparison of time series databases for high-frequency data, with a focus on financial applications. The proposed suite comprises of four specialized databases: ClickHouse, InfluxDB, kdb+ and TimescaleDB. The results from the suite demonstrate that kdb+ has the highest performance amongst the tested databases, while also highlighting the strengths and weaknesses of each of the databases. The benchmarking suite was designed to provide an objective measure of the performance of these databases as well as to compare their capabilities for different types of data. This provides valuable insights into the suitability of different time series databases for different use cases and provides benchmarks that can be used to inform system design decisions.
Time-series data has an increasingly growing usage in Industrial Internet of Things (IIoT) and large-scale scientific experiments. Managing time-series data needs a storage engine that can keep up with their constantly growing volumes while providing an acceptable query latency. While traditional ACID databases favor consistency over performance, many time-series databases with novel storage engines have been developed to provide better ingestion performance and lower query latency. To understand how the unique design of a time-series database affects its performance, we design SciTS, a highly extensible and parameterizable benchmark for time-series data. The benchmark studies the data ingestion capabilities of time-series databases especially as they grow larger in size. It also studies the latencies of 5 practical queries from the scientific experiments use case. We use SciTS to evaluate the performance of 4 databases of 4 distinct storage engines: ClickHouse, InfluxDB, TimescaleDB, and PostgreSQL.
With disks and networks providing gigabytes per second, parsing decimal numbers from strings becomes a bottleneck. We consider the problem of parsing decimal numbers to the nearest binary floating-point value. The general problem requires variable-precision arithmetic. However, we need at most 17 digits to represent 64-bit standard floating-point numbers (IEEE 754). Thus we can represent the decimal significand with a single 64-bit word. By combining the significand and precomputed tables, we can compute the nearest floating-point number using as few as one or two 64-bit multiplications. Our implementation can be several times faster than conventional functions present in standard C libraries on modern 64-bit systems (Intel, AMD, ARM and POWER9). Our work is available as open source software used by major systems such as Apache Arrow and Yandex ClickHouse. The Go standard library has adopted a version of our approach.
"We believe that a capture of Swift, an attempted capture of Swift, is very much in the cards
Researchers have found a way to build much larger “twisted” oxide materials while precisely controlling how their atomic layers line up。 Because these materials can be made over large areas and transferred onto different surfaces, the technique could help turn twistronics from a laboratory curiosity into a practical platform for next-generation ele
Scientists have identified LHAASO J1912+1014u as a cosmic accelerator that can push protons beyond one quadrillion electron volts。 The finding may help reveal where the Milky Way’s most energetic cosmic rays come from and how they influence the galaxy
A new chemical process can transform three of the most common plastics into high-purity hydrogen without sorting them first。 The technique operates at much lower temperatures than traditional gasification and captures most of the plastic’s carbon in solid or liquid forms instead of releasing it as carbon dioxide
Christopher Nolan's impressionistic remix of Homer's epic poem finds the man behind the myth
A new analysis suggests the Sun holds far more silver than earlier estimates indicated。 More advanced models of the solar atmosphere raised the calculated amount by 55 percent, bringing it into much closer agreement with ancient meteorites。 The technique may also help scientists track the cosmic origins of silver and other heavy elements
At $25,305, you won't find many new cars for less。 But you get what you pay for
Look at chemistry of batteries and motors shows big opportunity for recycling
Primordial black holes may occasionally pass through white dwarf stars and trigger enormous Type Ia supernova explosions。 Researchers found that these events could explain chemical patterns seen in supernova remnants, nearby explosions, and stars across the Milky Way