Revealing the underlying causal mechanisms in the real world is the key to the development of science. Despite the progress in the past decades, traditional causal discovery approaches (CDs) mainly rely on high-quality measured variables, usually given by human experts, to find causal relations. The lack of well-defined high-level variables in many real-world applications has already been a longstanding roadblock to a broader application of CDs. To this end, this paper presents Causal representatiOn AssistanT (COAT) that introduces large language models (LLMs) to bridge the gap. LLMs are trained on massive observations of the world and have demonstrated great capability in extracting key information from unstructured data. Therefore, it is natural to employ LLMs to assist with proposing useful high-level factors and crafting their measurements.

"How to Train Your Dragon: The Hidden World" breathed some fire into a slumping box office with a franchise-best $55.5 million debut over Oscar weekend. Writer-director Dean DeBlois' third and supposedly final installment in the "How to Train Your Dragon" series notched the best opening of the year in U.S. and Canadian theaters. Going into the weekend, overall ticket sales for 2019 were down 18 percent, according to Comscore, throwing cold water on the record box office of 2018. But as Hollywood was set to gather for the Academy Awards on Sunday, "The Hidden World" lent the industry some good news -- albeit not a hint at all of the magnitude of what that was in theaters last Oscar weekend when "Black Panther" was the top film. Made for $129 million, "The Hidden World" rode good reviews (91 percent fresh on Rotten Tomatoes) and warm audience reaction (an A CinemaScore) to exceed the $43.7 million opening of the 2010 original (which ultimately made $494.9 million worldwide) and the $49 million opening of the 2014 sequel (which amassed $621.5 million).