Data assets associated with the Planetary Causal Inference research team. Includes EO, RCT, and observational sources.
AI & ML interests
Planetary causal inference // Text-based AI systems // Adversarial dynamics
Recent Activity
View all activity
Papers
Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs
Detecting and Mitigating Treatment Leakage in Text-Based Causal Inference: Distillation and Sensitivity Analysis
Organization Card
Jerzak Labs
Data, models, and methods for planetary-scale causal inference, text-based AI systems, and other interests. Led by Connor T. Jerzak, Assistant Professor at UT Austin.
Some Team Members on Hugging Face
Recent Team Tutorials
- Nicolas Audinet de Pieuchon presents: Benchmarking Debiasing Methods for LLM-based Parameter Estimates
- Nicolas Audinet de Pieuchon presents: Can Large Language Models (or Humans) Disentangle Text?
- Adel Daoud presents: A First Course in Planetary Causal Inference: Confounding (@IC2S2 2025)
- Adel Daoud presents: Planetary Causal Inference: Overview (@Yale)
- Connor Jerzak presents: Fast Rerandomization Using Accelerated Computing
- Connor Jerzak presents: Seeing Like a Satellite While Learning Across Scales: Remote Audits + Multi-Scale Optimization for Heterogeneity (@Columbia)
- Connor Jerzak presents: Selecting Optimal Candidate Profiles in Adversarial Environments (@UT Dallas & National Chung Hsing University)
- Richard Johansson presents: Conceptualizing Treatment Leakage in Text-based Causal Inference (@NAACL)
- Satiyabooshan Murugaboopathy presents: Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?
- Markus Pettersson presents: Debiasing ML Predictions for Causal Inference Without Additional Ground Truth Data
- Kazuki Sakamoto presents: A Scoping Review of Earth Observation and Machine Learning for Causal Inference
- Fucheng Warren Zhu presents: Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using EO and Computer Vision
Research Areas
Planetary Causal Inference
Harnessing Earth observation data, randomized control trials, and advanced modeling for global development and climate impact.Research Design
Rerandomization procedures, effect heterogeneity, and leveraging images (e.g., satellite) as data sources.Text-based AI Systems
Automated nonparametric text analysis, large language models, and language-based causal inferences.Descriptive Representation & Political Economy
Understanding group-level representation worldwide; analyzing policy impacts.
Featured Repositories
CausalImages
R Package for performing causal inference with images, including Earth observation and biomedical data.DescriptiveRepresentationCalculator
Tools for measuring descriptive representation across gender, ethnicity, religion, and more in global leadership data.readme2
Enhanced automated content analysis for social science text data (with paper).LinkOrgs
Linking organizational datasets using half-a-billion open-collaborated records.
For additional code packages, see Code Overview.
Data Assets
Explore large-scale data on Earth observation + RCTs, text-based sentiment disentanglement, organizational name-matching, and more:
Further details: Data Overview.
Contact
- Email: connor.jerzak@austin.utexas.edu
- Website: ConnorJerzak.com
- GitHub: GitHub.com/cjerzak
- Subscribe: Jerzak Labs YouTube
- Subscribe: Planetary Causal Inference
models 0
None public yet