We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and Models
Summary
Researchers built an AI tool called PROMETHEUS that reads through scientific studies, data, and code to map out cause-and-effect claims—like whether GLP-1 drugs actually cause weight loss, or whether resveratrol in red wine really benefits health—and flags where the evidence is strong, weak, or contradictory. This matters because health claims in the news often oversimplify messy science; this tool could help researchers (and eventually the public) see when "proven" health effects are actually shaky or based on conflicting studies. Notably, one test case applied this approach to a climate study on microplastics, showing the tool can also stress-
Large language models can extract local causal claims from text, but those claims become more useful when organized as persistent, navigable world models rather than as flat summaries. We introduce PROMETHEUS, a framework that turns retrieved literature, filings, reviews, reports, agent traces, source data, code, simulations, and scientific models into causal atlases: sheaf-like families of local causal predictive-state models over an explicit cover of a research substrate. Each local region contains causal episodes, structured claim tables, predictive tests, support statistics, and provenance; restriction maps compare overlapping regions; gluing diagnostics expose agreement, drift, contradiction, and underdetermination. The resulting Topos World Model is not a single universal graph. It is a research instrument for navigating what a corpus says, where it says it, how strongly it is supported, and where local claims fail to assemble into a coherent global view. Three literature-atlas case studies -- ocean-temperature impacts on marine populations, GLP-1 weight-loss evidence, and resveratrol/red-wine health-benefit claims -- illustrate deep causal research from text with explicit locality, evidence, persistent state, and gluing tension. Four grounded-counterfactual case studies -- a Nature Climate Change microplastics forcing paper, an Indus Valley hydrology paper with VIC-derived figure data and model code, the canonical Sachs protein-signaling study with single-cell perturbation data, and a Nature singing-mouse study with MAPseq projection matrices -- show a stronger mode: when a paper ships source data, simulation outputs, or code, PROMETHEUS can evaluate a counterfactual against that scientific substrate and then rebuild the sheaf world model around the