Library

Subject
Tags

4,737 matches · cs.DB

#
001A Structured Knowledge Infrastructure for Domain-Specific Data Asset DiscoveryarXivPaperMengdi Chen, Yuanxin Huang et al.Yesterday
002Fully Inductive Cardinality EstimationarXivPaperTim Schwabe et al.Yesterday
003A Graph-Native Bitemporal Memory Store for Conversational AI AgentsarXivPaperAlp Niksarli, Gopesh Baheti2 days ago
004Data Quality Profiling at Scale with Progressive Sampling: A Benchmark for Data-Centric AI PipelinesarXivPaperLaure Berti-Équille3 days ago
005MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based AgentsarXivPaperShuyue Wei, Chang Liu et al.3 days ago
006Messier: A High-Resolution Corpus for Cross-Benchmark Agent EvaluationarXivPaperStefan Krsteski, Charlotte Meyer et al.3 days ago
007WorkSurface-Bench: Benchmarking Enterprise Agents on Multi-Surface Knowledge RoutingarXivPaperHao Liang, Meiyi Qiang et al.3 days ago
008Beyond Scale and Generation: Understanding Language Model-based Entity MatchingarXivPaperZeyu Zhang, Xue Li et al.4 days ago
009Domain-Specific Data Quality Analysis Using Technology-Independent Query TemplatesarXivPaperArno Kesper, L. Hofmann et al.4 days ago
010ERUnderstand: Evaluating Vision-Language Models on Structured ER DiagramsarXivPaperAli Ansari, Yasmin Mohammadi et al.4 days ago
011TEmBed-T: A Multi-Dimensional Benchmark for Table-Level EmbeddingsarXivPaperAyeen Poostforoushan, Liane Vogel et al.4 days ago
012Extending Desbordante with Probabilistic Functional Dependency Discovery SupportarXivPaperIlia Barutkin, Maxim Fofanov et al.5 days ago
013Impute On-Demand: Adaptive Correlated Time Series Imputation for Changing EnvironmentsarXivPaperZhichen Lai, Huan Li et al.5 days ago
014Kalypso: Relational LLM ServingarXivPaperHojae Son, Md Ashraful Islam et al.5 days ago
015Order in Desbordante: Techniques for Efficient Implementation of Order Dependency Discovery AlgorithmsarXivPaperYakov Kuzin, D. Shcheka et al.5 days ago
016An Ontology for Machine Learning Interatomic PotentialsarXivPaperD. Hernández, Jong Hyun Jung et al.6 days ago
017Benchmarking Text-to-SQL under Role-Based Access ControlarXivPaperYang Fei, Yangfan Jiang et al.7 days ago
018DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations AgentsarXivPaperJunming Chen, Junyang Jiang et al.7 days ago
019Queryable Self-Organizing Maps: A Database Abstraction for Topology-Driven Data ExplorationarXivPaperD. Martins, G. Vossen7 days ago
020TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized ViewsarXivPaperA. Mangussi, Joana Cristo Santos et al.7 days ago
021Towards Trustworthy and Cost-Efficient Data Integration: From Naïve RAG to Agentic RAGarXivPaperChuangtao Ma, Arijit Khan7 days ago
022trasgoDP: An Open Source Framework for Releasing Noised Tabular Microdata under Local Differential PrivacyarXivPaperJudith Sáinz-Pardo Díaz, Álvaro López García7 days ago
023Chess\_db: A framework for working with large chess game datasetsarXivPaperNicos Angelopoulos, J. WielemakerJul 23
024MosaicJoin: Compact Semantic Sketches for Value-Level Join DiscoveryarXivPaperAbu Tyeb Azad, Fahim Ahmed et al.Jul 23
025Prompt as a Data Type: In-Database LLM Prompt Management and RewritingarXivPaperDebarshi Kundu, Swaroop Ghosh et al.Jul 23
026Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language ModelsarXivPaperYurong Liu, Yeye He et al.Jul 22
027Demonstrating GenDB: Instance-Optimized and Customized Query Processing Code Generation via LLM AgentsarXivPaperJiale Lao, Immanuel TrummerJul 22
028Plausibility-Driven Prioritization of Candidate Biomedical AnnotationsarXivPaperEmanuele Cavalleri, Miad Alavinezhad et al.Jul 22
029TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment AnalysisarXivPaperIsabel Xu Cynthia Xu Rachel Ren Cong Guo Jiacheng DingJul 22
030AgentTrails: Towards Trust and Reuse for Agentic TasksarXivPaperEden Wu, Sonia Castelo et al.Jul 21
031D-NOVA: In-Storage Retrieval Accelerator via Dual-Bound 3D NAND-Optimized Similarity Search with Vector AdaptationarXivPaperChang Eun Song, Sumukh Pinge et al.Jul 20
032EVOLVE: Efficient Learned Volume Compression with Variable-Rate Encoding on a Cross-Domain DatabasearXivPaperKaiyuan Tang, Maizhe Yang et al.Jul 20
033FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 MatchesarXivPaperJiachen Ding, Congyu Guo et al.Jul 20
034Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query GenerationarXivPaperB. Fitch, Cato Elia KurtzJul 20
035Panache: One-Pass Motif Discovery at Every Window LengtharXivPaperTejas RanadeJul 20
036An Explicit World Model Based on Data-First Ontology: DaoQL Multimodal Storage Validation and Counterfactual Reasoning EvaluationarXivPaperZhanbo Li, Shifeng Wu et al.Jul 19
037SAGA: Synthetic Agentic Graph Architecture for Temporal Benchmark GenerationarXivPaperJiacheng Ding, Xiaofei ZhangJul 19
038Efficient and Effective In-place Graph-based Vector Index UpdatesarXivPaperHaotian Liu, Yujun He et al.Jul 17
039ReBound: Reuse-Aware Privacy For Interactive Decision SupportarXivPaperNada Lahjouji, Shufan Zhang et al.Jul 15
040Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI AgentsarXivPaperRichmond Alake, Cesare Bernardis et al.Jul 14
041Policy-Conditioned Constrained Decoding for Column-Level Access Control in Text-to-SQLarXivPaperRyoto Miyamoto, Xin Fan et al.Jul 14
042Cost-Governed RAG: Unified Per-Tenant Cost Attribution Across Retrieval and Generation in Multi-Tenant LLM SystemsarXivPaperNavnit ShuklaJul 13
043FAIR GraphRAG: A Retrieval-Augmented Generation Approach for Semantic Data AnalysisarXivPaperMarlena Flüh, Soo-Yon Kim et al.Jul 13
044Lightning Fast Matching Dependency Discovery with DesbordantearXivPaperAlexey Shlyonskikh, Michael Sinelnikov et al.Jul 12
045The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their InteractionsarXivPaperFilip Klubicka, Vasudevan Nedumpozhimana et al.Jul 12
046Confining Nondeterminism: AI-Driven Research Systems as DBMSs for Reliable, Non-Wasteful, Transparent, and Collaborative Research [Vision]arXivPaperKyoungmin Kim, Anastasia AilamakiJul 11
047TSAI-MetaFraud: A Benchmark Dataset for Financial Fraud Transaction and Behavioral Risk Detection in Metaverse EcosystemsarXivPaperRefat Ishrak Hemel, Ehsan Hallaji et al.Jul 10
048DocMaster: A Hierarchical Structure-Aware System for Document AnalysisarXivPaperZiqi Chen, Yingli Zhou et al.Jul 9
049GitLake: Git-for-data for the agentic lakehousearXivPaperWeiming Sheng, Jinlang Wang et al.Jul 9
050A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous drivingarXivPaperHeye Huang, Jingguang Li et al.Jul 8
051Agentic Data EnvironmentsarXivPaperElaine Ang, Chenxi Huang et al.Jul 8
052Breaking Database Lock-in: Agentic Regeneration of High Performance Storage Readers for Database BypassarXivPaperVictor Giannakouris, Immanuel TrummerJul 8
053Structural Adversarial Attacks on Relational Deep Learning under Integrity ConstraintsarXivPaperAlan Gany, Bogdan Cautis et al.Jul 8
054Discovering Frequent Closed Embedded Sub-DAGs in Spatio-Temporal Event DataarXivPaperPiotr S. MacikagJul 7
055Industry Classification of GitHub Repositories Using the North American Industry Classification System (NAICS)arXivPaperKevin Xu, Alexander QuispeJul 7
056Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL WorkflowsarXivPaperTianyang Liu, Canwen Xu et al.Jul 7
057BatteryLake: Agentic, Physics-Grounded Curation of Heterogeneous Battery Aging Data and BenchmarkingarXivPaperTianwen Zhu, Hao Wang et al.Jul 6
058Identifiability of Relational Queries in Multi-View PretrainingarXivPaperRatan Bahadur Thapa, Daniel HernándezJul 6
059A Fair Benchmarking of Deep Relational Database Learning ModelsarXivPaperK. F. Akhter, Bharath Ajendla et al.Jul 4
060Efficient Discovery of Conditional Dependencies with DesbordantearXivPaperI. Kozhukov, D. Fedoseev et al.Jul 4

Showing 60 of 4,737 documents · scroll for more