Reproduce “teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data” 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
Qiwei Li, Jorge Ortiz
teLLMe turns dashcam annotations into event-level variables and uses a learned graph and natural-language questions to form adjusted comparisons. For clear-weather highway windows, it compares peak with off-peak traffic density, defined as detected vehicles per minute. Its OLS estimate is 0.024, with a 95% confidence interval of 0.014 to 0.034. This observational estimate is not a definitive causal finding.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.