This paper describes the use of a trie data structure to enhance experiment efficiency in comparative pipeline experiments for cascading retrieval pipelines using PyTerrier, observing a 26% reduction…

The paper proposes an attestation-aware promotion gate to mitigate supply-chain risks in LLM pipelines by cryptographically verifying and enforcing claims about training and release artifacts before d…

The paper introduces DataOrchestra, a framework for example-specific processing of pretraining data for Large Language Models, achieving stable gains and reducing compute.

The paper introduces Sophrosyne, a system that moderates LLM agent exploration in relational data systems, significantly reducing over-exploration and boosting SQL generation accuracy by guiding the a…

The paper introduces a data-centric optimization pipeline to improve coding agents' ability to interact with a branching lakehouse, showing significant accuracy gains by treating agent evaluation as a…

This paper explores the integration of several extensions for Natural Language to SQL (NL2SQL) translation, including NatSQL representation, preprocessing, fine-tuning, and reranker model.

The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.

The paper proposes an evidence-driven protocol combining Deterministic Build Systems and Trusted Execution Environments to provide cryptographically verifiable guarantees of software artifact integrit…

This paper presents Vivace, a serverless system for exact temporal OLAP over interval histories, which addresses the issues of incomplete data and incorrect answers in serverless functions.

The paper presents Dyserve, a workflow-aware serving layer for agentic AI applications that compiles per-node model and verifier choices into an integer linear program, allowing for efficient model se…

The paper introduces 'dashi,' an open-source Python library that provides comprehensive tools for characterizing dataset shifts (covariate, prior, concept) to ensure robust and trustworthy AI developm…

This paper proposes Trellis, a data foundation that treats experience graphs from long-horizon agentic tasks as first-class, governed, queryable database state.

The paper presents an end-to-end LLM pipeline and interactive dashboard designed to automatically extract and structure topics from massive volumes of regulatory consultation submissions, ensuring ful…

This study benchmarks four local LLMs for natural-language-to-SQL querying in biopharma manufacturing, finding that general-purpose code-tuned models like Llama 3.1 8B and Qwen 2.5 Coder 7B outperform…

The paper proposes GovAI-Pipe, a novel four-layer governance pipeline that operationalizes high-level AI policies (like the EU AI Act) into auditable, technical checkpoints for deploying AI in large-s…

The paper introduces Autonomous Agentic Data Engineering, demonstrating that LLMs can autonomously plan and optimize end-to-end data curation pipelines, leading to substantial performance gains in spe…

BiJuTy is a user-friendly solution for executing complex big data processing workflows on high-performance computing systems within the Jupyter ecosystem.

SpecDB is a novel system that uses LLMs to synthesize highly customized, purpose-built relational databases, achieving performance comparable to commercial systems while significantly reducing code si…

The paper introduces DataGovBench, a benchmark for evaluating Large Language Models in real-world data analysis scenarios, revealing significant performance gaps with state-of-the-art models.