Lightnews — Scholar-powered news

Connor T. Jerzak @jerzakconnor.bsky.social · 1d

When on-the-ground data are scarce or outdated, satellites can keep the evidence flowing. Our guide shows how to turn data from satellites into useful causal claims, improving targeting + evaluation, avoiding common issues related to resolution mismatch / leakage / spatial dependence.

1 1

Reposted by Connor T. Jerzak

arxiv.stat.ME @arxiv-stat-me.bsky.social · 9d

Connor T. Jerzak, Adel Daoud
Remote Auditing: Design-based Tests of Randomization, Selection, and Missingness with Broadly Accessible Satellite Imagery
https://arxiv.org/abs/2510.00128

1 1

Reposted by Connor T. Jerzak

arXiv stat.AP Applications @statap-bot.bsky.social · 10d

Adel Daoud, Cindy Conlin, Connor T. Jerzak: Chinese vs. World Bank Development Projects: Insights from Earth Observation and Computer Vision on Wealth Gains in Africa, 2002-2013 https://arxiv.org/abs/2509.25648 https://arxiv.org/pdf/2509.25648 https://arxiv.org/html/2509.25648

2 2

Reposted by Connor T. Jerzak

Dan de Kadt @dandekadt.bsky.social · 26d

LSE's Department of Methodogy is searching for an Assistant Professor in Computational Social Science. Applicants from across the social sciences are very welcome!

Please reach out if you would like any more details.

Assistant Professor in Computational Social Science

Assistant Professor in Computational Social Science, , LSE is committed to building a diverse, equitable and truly inclusive university <p styl...

jobs.lse.ac.uk

44 39

Connor T. Jerzak @jerzakconnor.bsky.social · Aug 18

Fall schedule for the Political Methodology Seminar Series at the UT Austin Department of Government, AY25-26 is out! Event calendar links here: connorjerzak.com/methods-seri...

1 3

Reposted by Connor T. Jerzak

AI Firehose @ai-firehose.column.social · Mar 18

With a new Multi-Scale Representation Concatenation method, researchers enhance satellite imagery optimization for causal inference in anti-poverty programs by revealing treatment effect heterogeneity across scales, potentially amplifying impacts without extra costs. https://arxiv.org/abs/2411.02134

Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs

ArXiv link for Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs

arxiv.org

1 1

Reposted by Connor T. Jerzak

Anna Gunderson @annagunderson.bsky.social · Aug 12

Attention #polisky! Apply for
@utaustin.bsky.social LBJ School of Public Affairs with a focus on American Political Institutions. I'm on the committee, so please reach out with questions. See below: apply.interfolio.com/170943

Apply - Interfolio {{$ctrl.$state.data.pageTitle}} - Apply - Interfolio

apply.interfolio.com

5 7

Connor T. Jerzak @jerzakconnor.bsky.social · Aug 12

proceedings.mlr.press/v275/zhu25a....

1

Connor T. Jerzak @jerzakconnor.bsky.social · Aug 5

Paper breakdown: aidevlab.org/tweedie/

Debiasing ML Predictions - AI and Global Development Lab

>>>Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis [PDF] [.bib] Markus Pettersson | Connor...

aidevlab.org

1

Connor T. Jerzak @jerzakconnor.bsky.social · Aug 5

Paper breakdown: aidevlab.org/tweedie/

Debiasing ML Predictions - AI and Global Development Lab

>>>Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis [PDF] [.bib] Markus Pettersson | Connor...

aidevlab.org

Connor T. Jerzak @jerzakconnor.bsky.social · Aug 5

Paper breakdown: aidevlab.org/platonic/

Platonic Poverty Mapping - AI and Global Development Lab

>>>Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty? [PDF] [Data] [.bib] Satiyabooshan Murugaboopathy | Connor T. Jerzak | Adel Daoud Setting the St...

aidevlab.org

Connor T. Jerzak @jerzakconnor.bsky.social · Aug 5

Yes, definitely! We'll put some on YouTube and / or planetarycausalinference.org Will keep you posted.

Planetary Causal Inference

planetarycausalinference.org

1 1

Reposted by Connor T. Jerzak

arXiv stat.ML Machine Learning @statml-bot.bsky.social · Aug 5

Markus Pettersson, Connor T. Jerzak, Adel Daoud: Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven P... https://arxiv.org/abs/2508.01341 https://arxiv.org/pdf/2508.01341 https://arxiv.org/html/2508.01341

1 3 2

Reposted by Connor T. Jerzak

arxiv stat.ML @arxiv-stat-ml.bsky.social · Aug 5

Markus Pettersson, Connor T. Jerzak, Adel Daoud
Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis
https://arxiv.org/abs/2508.01341

1 2 3

Reposted by Connor T. Jerzak

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · Aug 5

Satiyabooshan Murugaboopathy, Connor T. Jerzak, Adel Daoud: Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty? https://arxiv.org/abs/2508.01109 https://arxiv.org/pdf/2508.01109 https://arxiv.org/html/2508.01109

1 2 2

Connor T. Jerzak @jerzakconnor.bsky.social · Aug 2

Excited to teach two grad courses @UTAustin Spring '26!

📊 Gov 385La: Making Big Data – Learn web scraping, crowd-sourcing, & data curation to build high-quality datasets for social sci impact.

🌍 Gov 385Lb: Causal ML & EO for Social Sci – Deploy satellite data & ML for causal inf at planetary scale

1 2 3

Reposted by Connor T. Jerzak

arXiv stat.AP Applications @statap-bot.bsky.social · Jul 31

Connor T. Jerzak, Stephen A. Jessee: Attenuation Bias with Latent Predictors https://arxiv.org/abs/2507.22218 https://arxiv.org/pdf/2507.22218 https://arxiv.org/html/2507.22218

1 4

Connor T. Jerzak @jerzakconnor.bsky.social · Jul 24

Join a cool group at UC Berkeley, March 7-8, 2026, for "Clouds, Streams, and Ground (Truths)"—exploring methods to study algorithmic music ecosystems. Details: www.algorithmicmusicmethods.com

Algorithmic Music Methods Conference 2026 - Clouds, Streams, and Ground (Truths)

musicology, ethnomusicology, media studies, academic conference, AI, machine learning, algorithms, critical data studies, science and technology studies

www.algorithmicmusicmethods.com

1

Connor T. Jerzak @jerzakconnor.bsky.social · Jul 22

A First Course in Planetary Causal Inference: Confounding. Adel presents.

www.youtube.com/watch?v=oD7D...

A First Course in Planetary Causal Inference: Confounding - Adel Daoud at IC2S2 2025

YouTube video by Planetary Causal Inference - Academic Content

www.youtube.com

1 4

Reposted by Connor T. Jerzak

arxiv.stat.ME @arxiv-stat-me.bsky.social · Apr 29

Connor T. Jerzak, Priyanshi Chandra, Rishi Hazra
Selecting Optimal Candidate Profiles in Adversarial Environments Using Conjoint Analysis and Machine Learning
https://arxiv.org/abs/2504.19043

1 2

Reposted by Connor T. Jerzak

Oliver Eberle @eberleoliver.bsky.social · Jun 19

🚨 New preprint! Excited to share our work on extracting and evaluating the potentially many feature descriptions of language models

👉 arxiv.org/abs/2506.15538

Laura Kopf @lkopf.bsky.social · Jun 19

🔍 When do neurons encode multiple concepts?

We introduce PRISM, a framework for extracting multi-concept feature descriptions to better understand polysemanticity.

📄 Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework
arxiv.org/abs/2506.15538

🧵 (1/7)

4 18

Reposted by Connor T. Jerzak

arxiv cs.CL @arxiv-cs-cl.bsky.social · Jun 12

Nicolas Audinet de Pieuchon, Adel Daoud, Connor T. Jerzak, Moa Johansson, Richard Johansson
Benchmarking Debiasing Methods for LLM-based Parameter Estimates
https://arxiv.org/abs/2506.09627

1 3

Reposted by Connor T. Jerzak

Marc Keuschnigg @marckeuschnigg.bsky.social · May 13

We are hiring postdocs in Computational Social Science
📍SweCSS, Norrköping, Sweden
⏰Deadline June 3
🔗https://liu.se/en/work-at-liu/vacancies/26854
Please apply // help us spread the word

2 76 110

Connor T. Jerzak @jerzakconnor.bsky.social · May 11

For how long? 2-3 yr contract & flexible remote.

Where? Remote options possible; core mentor, Adel, based in Sweden.

AI & Global Dev Lab: aidevlab.org

AI & GLOBAL DEVELOPMENT LAB - AI and Global Development Lab

The AI & Global Development Lab fuses AI with Earth Observation to illuminate the causes and consequences of human development across time and space. Our interdisciplinary team—including data scientis...

aidevlab.org

1

Connor T. Jerzak @jerzakconnor.bsky.social · May 11

New postdoc position posted at the AI & Global Development Lab!

What would you do? Use ML & causal inference to evaluate African development programs—build remote-sensing pipelines for geo-temporal poverty estimates & impact evals, among other things.

Details: liu.se/en/work-at-l...

AI & GLOBAL DEVELOPMENT LAB - AI and Global Development Lab

The AI & Global Development Lab fuses AI with Earth Observation to illuminate the causes and consequences of human development across time and space. Our interdisciplinary team—including data scientis...

aidevlab.org

1 2 3