Nature study packages paper, demo, data and code for predicting social science results
RobbWiller · x · 2026-07-23
The authors released a Nature paper, a free manuscript, an interactive demo, and the underlying data/code for a study on whether large language models can predict the results of social science experiments.
The post encourages others to test the method’s boundaries, failure cases, and responsible uses. The attached image makes clear that the work is positioned as a reproducible research package rather than a simple announcement.
Related event: Nature Study: GPT-4 Can Predict Social Science Experiment Results(18 posts)→
More from Research
- Nature paper images cellular activity across all organs, revealing body-wide circuits — arjunrajlab · 2026-09-11
- SignNet 1M Dataset Released for Sign Language Research — ducha_aiki · 2026-09-11
- ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
- InFlux++ Method Released — ducha_aiki · 2026-09-11
- Skyfall GS Uses Flux to Refine Gaussian Splatting, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11
- Could 10k agents discover learning methods beyond backprop, or just tweak existing ones? — SeunghyunSEO7 · 2026-09-11