Confidence-weighted integration of human and machine judgments for superior decision-making

Code for running analyses in paper https://arxiv.org/abs/2403.03230

Raw results and plotting scripts for paper https://arxiv.org/abs/2403.03230

Source code for <Matching domain experts by training from scratch on domain knowledge>

Code for fine-tuning on 20 years of Neuroscience using LoRA for paper https://arxiv.org/abs/2403.03230

Source code for <Large language models surpass human experts in predicting neuroscience results>

Testcases for paper https://arxiv.org/abs/2403.03230

Participant data for paper https://arxiv.org/abs/2403.03230