AI agents reproduce 72% of the human ideological gap in effect estimates from an immigration dataset and introduce the m-value plus Agentic Bootstrap to quantify a reported analysis's position in the multiverse of defensible paths.
Many ai analysts, one dataset: Navigating the agentic data science multiverse.arXiv preprint arXiv:2602.18710, 2026
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2representative citing papers
LLMs match original qualitative conclusions in 80% of 180 studies and effect sizes in 24%, performing similarly to humans in a tested subset, positioning them as a screening tool rather than a full replacement.
citing papers explorer
-
The Agentic Garden of Forking Paths
AI agents reproduce 72% of the human ideological gap in effect estimates from an immigration dataset and introduce the m-value plus Agentic Bootstrap to quantify a reported analysis's position in the multiverse of defensible paths.
-
Automated reproducibility assessments in the social and behavioral sciences using large language models
LLMs match original qualitative conclusions in 80% of 180 studies and effect sizes in 24%, performing similarly to humans in a tested subset, positioning them as a screening tool rather than a full replacement.