Remote Auditing: Design-based Tests of Randomization, Selection, and Missingness with Broadly Accessible Satellite Imagery
Paper
•
2510.00128
•
Published
AI & ML interests
We're creating a causal atlas of global well-being---combining satellite imagery, AI agent swarms, traditional machine learning, and causal methods to track and test human development at scale
Recent Activity
Papers
Remote Auditing: Design-based Tests of Randomization, Selection, and Missingness with Broadly Accessible Satellite Imagery
Chinese vs. World Bank Development Projects: Insights from Earth Observation and Computer Vision on Wealth Gains in Africa, 2002-2013
cjerzak
authored
2
papers
22 days ago
Post
262
Excited to share LinkOrgs Online, a web app hosted here on HF for embedding and linking organization names using character-level Transformer encoder models trained on half a billion scraped LinkedIn records.
Upload CSVs or paste text, generate 1024D embeddings (v1–v4), PCA viz, and download results!
Try it: cjerzak/LinkOrgs_Online
Details/paper: https://connorjerzak.com/linkorgs-summary/
Training/inference code: https://github.com/cjerzak/LinkOrgs-software
Upload CSVs or paste text, generate 1024D embeddings (v1–v4), PCA viz, and download results!
Try it: cjerzak/LinkOrgs_Online
Details/paper: https://connorjerzak.com/linkorgs-summary/
Training/inference code: https://github.com/cjerzak/LinkOrgs-software
cjerzak
updated
a
Space
2 months ago
Post
369
Just dropped IWI-Africa: 69k DHS clusters linked with satellite imagery + agent/LLM text so you can predict wealth from space and the web. Poke the vision-language-agentic convergence yourself.
Hugging Face: theaidevlab/IWI-Africa-Multimodal
Paper: https://arxiv.org/abs/2508.01109.
Hugging Face: theaidevlab/IWI-Africa-Multimodal
Paper: https://arxiv.org/abs/2508.01109.
cjerzak
updated
a
collection
3 months ago
cjerzak
updated
a
dataset
3 months ago
cjerzak
authored
3
papers
3 months ago
Attenuation Bias with Latent Predictors
Paper
•
2507.22218
•
Published
•
1
Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?
Paper
•
2508.01109
•
Published
•
3
Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis
Paper
•
2508.01341
•
Published
•
1
cjerzak
published
a
dataset
3 months ago
Post
265
Global Leadership Project v1 dataset released: 50k+ political elites, 156 countries, hand-coded. v2 in progress.
HF link: cjerzak/GlobalLeadershipProject_v1
HF link: cjerzak/GlobalLeadershipProject_v1
Post
2353
Dropped a dataset on here for linking org data: half a billion records scraped from LinkedIn networks. Positive/negative matches, bipartite graphs, Markov clusters – all the goods to train models that actually work on fuzzy company names.
NegMatches, PosMatches, holdouts for eval.
Check it out: cjerzak/LinkOrgs
NegMatches, PosMatches, holdouts for eval.
Check it out: cjerzak/LinkOrgs
cjerzak
authored
a
paper
5 months ago
Priyanshi-28
authored
a
paper
6 months ago
cjerzak
authored
a
paper
6 months ago
Post
519
Scaling laws for multi‐scale dynamics: stacking resolutions uncovers hidden structure and drives predictable performance gains. Multi‐scale works because it blends coarse and fine contexts into a unified representation.
Dive into the math and experiments here: https://planetarycausalinference.org/scaling-laws-for-multi-scale/
Dive into the math and experiments here: https://planetarycausalinference.org/scaling-laws-for-multi-scale/
cjerzak
authored
a
paper
10 months ago
cjerzak
authored
a
paper
11 months ago
cjerzak
authored
a
paper
about 1 year ago