Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.22705

Data Provenance Aggregation and Structural Descriptors for Query-Template Identification

Paulo Pintor·Rogério Costa·José Moreira
View original source ↗Read source document ↗Export metadata ↓

Abstract

Runtime query similarity identification supports several activities, including workload analysis, identifying recurring behaviour, auditing, debugging, and anomaly detection. Existing methods for evaluating query similarity mostly rely on SQL text, execution plans, or result values but do not account for input data or how results are derived during query execution. This paper proposes a novel approach using data provenance for query-template identification. We construct query-level profiles that capture explicit data dependencies, occurrence frequencies, and structural properties by aggregating tuple-level Lineage and Why-provenance across entire query results. We also derive Provenance Structural Descriptors (PSD), which summarise these profiles using a small set of numerical features. We evaluate our proposals using these profiles to identify query templates over \(12{,}500\) distinct query instances generated from parametrised TPC-DS query templates. The experimental evaluation shows that query templates can be identified solely from their provenance footprints, and that accuracy improves as more historical data becomes available. It also shows that PSD achieve high classification accuracy with limited training history and low test-processing cost.

Explore related subjects

cs.DBcs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Paulo Pintor, Rogério Costa, José Moreira. 2026-10-15. Data Provenance Aggregation and Structural Descriptors for Query-Template Identification. https://arxiv.org/abs/2610.22705

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Contextual Utility of Quantization Moves in Extreme Low-Bit LLMs

Accurate measurements of isolated weight replacements need not predict their joint effect on a quantized model. We study this gap for legal replacements at a fixed bitrate, separating isolated pricing error, composition error, and changes in evaluation data. On Llama-3.2-1B and activation-ordered 3B GPTQ bases, option-KL composition residuals are 26x and 42x the sums of absolute midpoint pricing errors; large residuals remain with exact-singleton prices. Exhaustive Qwen3-0.6B lattices reveal context-dependent effects: six of eight moves in the stratified lattice have statistically resolved ARC-KL sign reversals, excluding an exact monotone additive representation. Pair measurements improve prediction of unqueried combinations on both Qwen and Llama. Their value for selection depends on the criterion: the stratified Qwen front retains a quality-coverage advantage after refitting, whereas the 3B additive and quadratic fronts are nearly equal in quality at a one-standard-error tolerance. Low-order endpoint structure leaves continuous gradient responses undetermined, and shared-midpoint prices can differ from those of the executed subset. Support-matched controls show that restricting the number of replacements curbs the failures of large combinations, while additional endpoint search gives bank-dependent NLL/ARC trade-offs.

cs.DB↗
arXiv2026

FuseRAG: Fusing Structure and Evidence into Inference for Cost-Efficient Graph-based RAG

Graph-based retrieval-augmented generation (RAG) exploits relationships among evidence to support multi-hop question answering. However, conveying retrieved graphs through non-unique linear textual contexts to Large Language Models (LLMs) leads to graph-structure degradation and inefficient KV-cache reuse. Meanwhile, graph-structure order optimization is already NP-hard, and the additional KV-cache reuse objective further complicates the search by introducing potentially conflicting orders. To tackle these issues, we propose FuseRAG, a cost-efficient graph-based RAG framework that shifts most retrieved evidence from explicit textual contexts to latent representations. Our main idea is to separate reusable evidence content from query-aware structural interactions in latent space, while retaining only a few explicit facts as semantic anchors. The resulting latent representations are injected into decoder self-attention, where they reshape attention over evidence and thereby influence hidden states and next-token probabilities. This design preserves graph structure through latent interactions, enables evidence reuse beyond exact token-prefix matching. Experiments on three multi-hop question-answering datasets with Llama-3-8B and Qwen3.5-9B show that FuseRAG improves answer quality while achieving up to 2.7x and 2.2x TTFT speedups over the fastest graph-based baseline, respectively.

cs.DB↗
arXiv2026

NL2SQL with Iterative Self-Refinement

Bridging the gap between human intent and machine logic remains a critical challenge in data access for non-technical users, yet Large Language Models (LLMs) remain unreliable: they hallucinate schema elements, generate syntactically invalid queries, or fail to capture user intent. These limitations are especially critical in domains such as insurance, where KPIs, regulatory constraints, and legacy relational systems demand high precision. We introduce a multi-agent, persona-driven NL2SQL framework that combines (1) domain relevance detection, (2) schema-grounded knowledge construction, (3) KPI-aware SQL synthesis, (4) syntax-level self-repair using sqlite execution feedback, and (5) semantic consistency checking via SQL-to-NL reverse engineering. Our system significantly reduces query hallucination and improves semantic fidelity compared to direct LLM prompting. Evaluated on 60 queries (50 from a HuggingFace text-to-SQL dataset and 10 custom domain queries), the system achieves 90% correctness using Mistral across seven coordinated LLM calls showing that this approach can substantially increase the reliability of NL2SQL pipelines in high-stakes environments.

cs.DB↗