# A Case for Computing on Unstructured Data

arXiv: https://arxiv.org/abs/2509.14601 · HTML: https://mlsanity.com/paper/2509.14601/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [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)
- [Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction](https://mlsanity.com/paper/2404.14215/) (2024)
- [Differentially Private SQL with Bounded User Contribution](https://mlsanity.com/paper/1909.01917/) (2019)
- [The Design of an LLM-powered Unstructured Analytics System](https://mlsanity.com/paper/2409.00847/) (2024)
- [Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems](https://mlsanity.com/paper/2507.01599/) (2025)
- [Visual Template Inference for Data Extraction from Documents](https://mlsanity.com/paper/2501.06659/) (2025)
- [SQUiD: Synthesizing Relational Databases from Unstructured Text](https://mlsanity.com/paper/2505.19025/) (2025)
- [AnDB: Breaking Boundaries with an AI-Native Database for Universal Semantic Analysis](https://mlsanity.com/paper/2502.13805/) (2025)

## Built on by (most cited first, 2 of 2)

- [Larch: Learned Query Optimization for Semantic Predicates](https://mlsanity.com/paper/2606.07923/) (2026)
- [Prints in the Magnetic Dust: Robust Similarity Search in Legacy Media Images Using Checksum Count Vectors](https://mlsanity.com/paper/2604.09657/) (2026)

## Abstract (arXiv)

Unstructured data, such as text, images, audio, and video, comprises the vast majority of the world's information, yet it remains poorly supported by traditional data systems that rely on structured formats for computation. We argue for a new paradigm, which we call computing on unstructured data, built around three stages: extraction of latent structure, transformation of this structure through data processing techniques, and projection back into unstructured formats. This bi-directional pipeline allows unstructured data to benefit from the analytical power of structured computation, while preserving the richness and accessibility of unstructured representations for human and AI consumption. We illustrate this paradigm through two use cases and present the research components that need to be developed in a new data system called MXFlow.