Reproduce “When Do Humans and Machines Truly Complement Each Other? Formal Conditions and Empirical Evidence for Human-AI Synergy” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Andrea Campagner, Federico Cabitza, Vincenzo Crupi
The authors examine how human–AI decision interactions affect accuracy by tracking whether the human, AI, and final decision are correct, and define Human and Algorithmic Correction. Across seven case studies, combined decisions beat both solo judgments in three; in spinal X-ray diagnosis, accuracy was 0.88 versus 0.79 for clinicians and 0.78 for AI. These observational results are not causal evidence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.