The Pneuma Project: Reifying Information Needs as Relational Schemas to Automate Discovery, Guide Preparation, and Align Data with Intent
Summary: Reifies evolving information needs as relational schemas to iteratively steer LLM-powered discovery and data-prep toward fit-for-purpose artifacts. Combines context-specialization, a conductor-style planner, and shared-state convergence with RAG/agentic integration to automate discovery, guide preparation, and record institutional knowledge. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Muhammad Imam Luthfi Balaka (University of Chicago)
- 2. Raul Castro Fernandez (University of Chicago)
BibTeX Citation
@inproceedings{balaka_cidr26,
address = {Amsterdam, Netherlands},
series = {{CIDR} '26},
title = {{The Pneuma Project: Reifying Information Needs as Relational Schemas to Automate Discovery, Guide Preparation, and Align Data with Intent}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Balaka, Muhammad Imam Luthfi and Fernandez, Raul Castro},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 103 | DuckDB: an Embeddable Analytical Database | 2019 | SIGMOD | 0.00034161428 |
| 1,981 | ReAcTable: Enhancing ReAct for Table Question Answering | 2024 | VLDB | 9.3579557e-05 |
| 2,025 | Data Market Platforms: Trading Data Assets to Solve Data Problems | 2020 | VLDB | 9.2903125e-05 |
| 3,536 | How Large Language Models Will Disrupt Data Management | 2023 | VLDB | 7.3297343e-05 |
| 5,485 | Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System | 2025 | SIGMOD | 6.2013279e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,572 | Relational Deep Dive: Error-Aware Queries Over Unstructured Data | 2026 | VLDB |
| 2 | 10,736 | Sentence to Model: Cost-Effective Data Collection LLM Agent | 2025 | SIGMOD |
| 3 | 2,956 | The Design of an LLM-powered Unstructured Analytics System | 2025 | CIDR |
| 4 | 8,343 | An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models | 2024 | VLDB |
| 5 | 4,050 | Revisiting Prompt Engineering via Declarative Crowdsourcing | 2024 | CIDR |
| 6 | 9,293 | Intelligent Agents for Data Exploration | 2024 | VLDB |
| 7 | 11,186 | Unstructured Data Fusion for Schema and Data Extraction | 2024 | SIGMOD |
| 8 | 6,101 | LLM for Data Management | 2024 | VLDB |
| 9 | 10,190 | AgenticScholar: Agentic Data Management with Pipeline Orchestration for Scholarly Corpora | 2026 | SIGMOD |
| 10 | 5,485 | Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System | 2025 | SIGMOD |