# Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?

arXiv: https://arxiv.org/abs/2508.01109 · HTML: https://mlsanity.com/paper/2508.01109/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 1 Aug 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)
- [Using satellite imagery to understand and promote sustainable development](https://mlsanity.com/paper/2010.06988/) (2020)
- [Inverse Scaling in Test-Time Compute](https://mlsanity.com/paper/2507.14417/) (2025)
- [Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Models](https://mlsanity.com/paper/2412.03801/) (2024)
- [Sat2Cap: Mapping Fine-Grained Textual Descriptions from Satellite Images](https://mlsanity.com/paper/2307.15904/) (2023)
- [Agentic AI Needs a Systems Theory](https://mlsanity.com/paper/2503.00237/) (2025)
- [Statistical modeling: the three cultures](https://mlsanity.com/paper/2012.04570/) (2020)
- [Conceptualizing Treatment Leakage in Text-based Causal Inference](https://mlsanity.com/paper/2205.00465/) (2022)
- [Understanding Intrinsic Socioeconomic Biases in Large Language Models](https://mlsanity.com/paper/2405.18662/) (2024)
- [Poverty Mapping Using Convolutional Neural Networks Trained on High and Medium Resolution Satellite Images, With an Application in Mexico](https://mlsanity.com/paper/1711.06323/) (2017)
- [Integrating Earth Observation Data into Causal Inference: Challenges and Opportunities](https://mlsanity.com/paper/2301.12985/) (2023)
- [Fairness and representation in satellite-based poverty maps: Evidence of urban-rural disparities and their impacts on downstream policy](https://mlsanity.com/paper/2305.01783/) (2023)
- [Harnessing the Synergy between LLM Agents and Knowledge Graphs for Urban Socioeconomic Prediction](https://mlsanity.com/paper/2411.00028/) (2024)
- [Benchmarking Debiasing Methods for LLM-based Parameter Estimates](https://mlsanity.com/paper/2506.09627/) (2025)
- [A Scoping Review of Earth Observation and Machine Learning for Causal Inference: Implications for the Geography of Poverty](https://mlsanity.com/paper/2406.02584/) (2024)
- [Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs](https://mlsanity.com/paper/2411.02134/) (2024)
- [Can Large Language Models (or Humans) Disentangle Text?](https://mlsanity.com/paper/2403.16584/) (2024)
- [GeoSEE: Regional Socio-Economic Estimation With a Large Language Model](https://mlsanity.com/paper/2406.09799/) (2024)
- [A High Resolution Urban and Rural Settlement Map of Africa Using Deep Learning and Satellite Imagery](https://mlsanity.com/paper/2411.02935/) (2024)
- [Analyzing Poverty through Intra-Annual Time-Series: A Wavelet Transform Approach](https://mlsanity.com/paper/2411.02855/) (2024)
- [Leveraging ChatGPT's Multimodal Vision Capabilities to Rank Satellite Images by Poverty Level: Advancing Tools for Social Science Research](https://mlsanity.com/paper/2501.14546/) (2025)

## Built on by (most cited first, 1 of 1)

- [Representation Alignment Rests on Linear Structure](https://mlsanity.com/paper/2605.28870/) (2026)

## Abstract (arXiv)

We investigate whether socioeconomic indicators, like household wealth, leave recoverable informational imprints in both satellite imagery (capturing features like buildings and roads) and Internet-sourced text (reflecting historical, cultural, and narratives of neighborhoods). Using DHS data from African neighborhoods (clusters), we pair high-resolution Landsat images with textual descriptions generated by LLMs conditioned on location/year, plus text retrieved by an LLM-driven AI Search Agent from web sources. We develop a multimodal framework that predicts household wealth (International Wealth Index; IWI) via five pipelines: (i) a vision model on satellite images, (ii) an LLM using only location and year, (iii) an AI agent that searches and synthesizes web text, (iv) a joint image-text encoder, and (v) an ensemble of all signals. Our framework yields three contributions. First, evaluations show that fusing vision and agent/LLM-generated text improves on vision-only baselines in wealth prediction (e.g., R-squared of 0.77 vs. 0.63 on out-of-sample splits), with LLM-internal knowledge (artificial neural memory) proving surprisingly predictive in out-of-country/time generalization. Second, we find suggestive evidence of partial representational alignment: fused embeddings from vision and language modalities correlate moderately (median cosine similarity across modalities of about 0.60 after alignment). This pattern is broadly consistent with the Platonic Representation Hypothesis, but does not by itself establish convergence to a single shared latent representation. Because agent-retrieved data yields only marginal and unstable gains across splits, our evidence for the Agent-Induced Novelty Hypothesis is limited. Third, we release a large-scale multimodal dataset of about 60,000 DHS clusters, each linked to satellite images, LLM-generated descriptions, and AI-agent-retrieved texts.