AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: “One Map, Many Trials” in Satellite-Driven Poverty Analysis

Markus B. Pettersson, Connor Thomas Jerzak, Adel Daoud

AAAI 2026 · Probabilistic and scientific modeling › Treatment effects · approach: Proximal and deep causal effect estimation · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply Tweedie's correction instead of naive predictionsML wealth predictions · Simulated treatment-effect estimationMAE: 0.48 -> 0.04Improved
apply Tweedie's correction instead of naive predictionsML wealth predictions · Simulated treatment-effect estimationcalibration slope: 0.535 -> 0.995Improved
apply LCC instead of naive predictionsML wealth predictions · Simulated treatment-effect estimationcalibration slope: 0.535 -> 1.008Improved
train with Ratledge loss instead of naive MSEResNet-50 predictions · Simulated treatment-effect estimationcalibration slope: 0.535 -> 0.641Mixed
apply Tweedie's correction instead of naiveML wealth predictions · DHS ADM2 region meansMAE: 2.67 -> 2.39Improved
restrict to regions with at least 100 clusters (ablation)Tweedie's correction · DHS ADM2 region meanscalibration slope: 0.83 to 0.90 -> 0.99Improved
apply Tweedie's correction instead of naiveML wealth predictions · Aid intervention ATE (DHS)correlation with ground-truth ATE: 0.958 -> 0.998Improved
apply Tweedie's correction instead of naiveML wealth predictions · Aid intervention ATE (DHS)MAE: 0.69 -> 0.57Improved
add PPI with 10% fresh downstream datanaive predictions · Aid intervention ATE (DHS)correlation with ground-truth ATE: 0.958 -> 0.981Improved
increase fresh downstream data for PPI (ablation)PPI · Aid intervention ATE (DHS)MAEImproved
shuffle more training/calibration labels (0 -> 0.30) (ablation)naive predictions · Aid ATE (label shuffling)MAE: 0.69 -> 3.91Hurt
shuffle more training/calibration labels (0 -> 0.30) (ablation)Tweedie's correction · Aid ATE (label shuffling)MAE: 0.57 -> 1.32Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy