When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs
Paper • 2608.03506 • Published • 3
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
View all activity
Papers
Temporal Dynamics of Development Aid in Africa: Evidence from a Staggered Difference-in-Differences Study of China and World Bank Projects in Africa
Remote Auditing: Design-based Tests of Randomization, Selection, and Missingness with Broadly Accessible Satellite Imagery
cjerzak
submitted a
paper to Daily Papers 2 days ago
cjerzak
authored a
paper 2 days ago
cjerzak
updated a
dataset 3 days ago
cjerzak
updated a
Space about 1 month ago
cjerzak
updated a
dataset about 2 months ago
JFagerlind
updated a
dataset about 2 months ago
cjerzak
published a
dataset about 2 months ago
cjerzak
authored a
paper 2 months ago
cjerzak
submitted a
paper to Daily Papers 3 months ago
cjerzak
authored a
paper 3 months ago
cjerzak
authored a
paper 4 months ago
cjerzak
submitted a
paper to Daily Papers 4 months ago
cjerzak
updated a
dataset 4 months ago
cjerzak
published a
dataset 6 months ago
Post
809
Ethos: In our team at UT Austin, we train students to become full-stack researchers—and increasingly, designers of the systems that do research. Our students learn to carry projects end-to-end: from idea generation and theory to data creation, analysis, and iterative refinement across diverse subfields. Using modern AI (including agentic workflows) and scalable computation, students build reproducible pipelines that can ingest and update planetary-scale data—like satellite imagery and other high-dimensional sources. But the goal isn’t tool use for its own sake: students learn to set the objectives, constraints, and evaluation standards that guide these systems through large spaces of hypotheses, while grounding results in causal inference and careful measurement. The outcome is scholarship that can rigorously test policy counterfactuals and translate evidence into durable, responsible improvements in societal well-being.
We welcome students at every stage to engage with projects—from motivated high-schoolers to undergraduates, graduate students, and those from highly non-traditional backgrounds.
Join us! https://connorjerzak.com/students/
We welcome students at every stage to engage with projects—from motivated high-schoolers to undergraduates, graduate students, and those from highly non-traditional backgrounds.
Join us! https://connorjerzak.com/students/
- 2 replies
cjerzak
authored 2
papers 7 months ago
Post
2908
>>> We're writing a new book, <Planetary Causal Inference>, on how to model counterfactuals at planetary scale by combining satellite imagery + other global data with local studies and RCTs. Forthcoming in 2026+.
>>> Book info: https://planetarycausalinference.org/book-launch
>>> All datasets used in the book will be openly available on our lab’s Hugging Face hub:
theaidevlab
>>> Book info: https://planetarycausalinference.org/book-launch
>>> All datasets used in the book will be openly available on our lab’s Hugging Face hub:
cjerzak
authored 2
papers 10 months ago
Remote Auditing: Design-based Tests of Randomization, Selection, and Missingness with Broadly Accessible Satellite Imagery
Paper • 2510.00128 • Published
Chinese vs. World Bank Development Projects: Insights from Earth Observation and Computer Vision on Wealth Gains in Africa, 2002-2013
Paper • 2509.25648 • Published