# SODIUM: From Open Web Data to Queryable Databases

arXiv: https://arxiv.org/abs/2603.18447 · HTML: https://mlsanity.com/paper/2603.18447/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 62 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows](https://mlsanity.com/paper/2411.07763/) (2024)
- [Semantic Operators: A Declarative Model for Rich, AI-based Data Processing](https://mlsanity.com/paper/2407.11418/) (2024)
- [Text2SQL is Not Enough: Unifying AI and Databases with TAG](https://mlsanity.com/paper/2408.14717/) (2024)
- [KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes](https://mlsanity.com/paper/2506.06541/) (2025)
- [Automatic Metadata Extraction for Text-to-SQL](https://mlsanity.com/paper/2505.19988/) (2025)
- [Continual Learning for Generative Retrieval over Dynamic Corpora](https://mlsanity.com/paper/2308.14968/) (2023)
- [Multi-Objective Agentic Rewrites for Unstructured Data Processing](https://mlsanity.com/paper/2512.02289/) (2025)
- [LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data](https://mlsanity.com/paper/2501.03892/) (2025)
- [CoddLLM: Empowering Large Language Models for Data Analytics](https://mlsanity.com/paper/2502.00329/) (2025)

## Abstract (arXiv)

During research, domain experts often ask analytical questions whose answers require integrating data from a wide range of web sources. Thus, they must spend substantial effort searching, extracting, and organizing raw data before analysis can begin. We formalize this process as the SODIUM task, where we conceptualize open domains such as the web as latent databases that must be systematically instantiated to support downstream querying. Solving SODIUM requires (1) conducting in-depth and specialized exploration of the open web, which is further strengthened by (2) exploiting structural correlations for systematic information extraction and (3) integrating collected information into coherent, queryable database instances. To quantify the challenges in automating SODIUM, we construct SODIUM-Bench, a benchmark of 105 tasks derived from published academic papers across 6 domains, where systems are tasked with exploring the open web to collect and aggregate data from diverse sources into structured tables. Existing systems struggle with SODIUM tasks: we evaluate 6 advanced AI agents on SODIUM-Bench, with the strongest baseline achieving only 46.5% accuracy. To bridge this gap, we develop SODIUM-Agent, a multi-agent system composed of a web explorer and a cache manager. Powered by our proposed ATP-BFS algorithm and optimized through principled management of cached sources and navigation paths, SODIUM-Agent conducts deep and comprehensive web exploration and performs structurally coherent information extraction. SODIUM-Agent achieves 91.1% accuracy on SODIUM-Bench, outperforming the strongest baseline by approximately 2 times and the weakest by up to 73 times.