Large language models (LLMs) with in-context learning have demonstrated remarkable capability in the text-to-SQL task. Previous research has prompted LLMs with various demonstration-retrieval strategies and intermediate reasoning steps to enhance the performance of LLMs. However, those works often employ varied strategies when constructing the prompt text for text-to-SQL inputs, such as databases and demonstration examples. This leads to a lack of comparability in both the prompt constructions and their primary contributions. Furthermore, selecting an effective prompt construction has emerged as a persistent problem for future research. To address this limitation, we comprehensively investigate the impact of prompt constructions across various settings and provide insights into prompt constructions for future text-to-SQL studies.

We train an object detector built from convolutional neural networks to count interference fringes in elliptical antinode regions in frames of high-speed video recordings of transient oscillations in Caribbean steelpan drums illuminated by electronic speckle pattern interferometry (ESPI). The annotations provided by our model aim to contribute to the understanding of time-dependent behavior in such drums by tracking the development of sympathetic vibration modes. The system is trained on a dataset of crowdsourced human-annotated images obtained from the Zooniverse Steelpan Vibrations Project. Due to the small number of human-annotated images and the ambiguity of the annotation task, we also evaluate the model on a large corpus of synthetic images whose properties have been matched to the real images by style transfer using a Generative Adversarial Network. Applying the model to thousands of unlabeled video frames, we measure oscillations consistent with audio recordings of these drum strikes. One unanticipated result is that sympathetic oscillations of higher-octave notes significantly precede the rise in sound intensity of the corresponding second harmonic tones; the mechanism responsible for this remains unidentified. This paper primarily concerns the development of the predictive model; further exploration of the steelpan images and deeper physical insights await its further application.

Gus, a 19-year-old homeschooled Christian from Joliet, Illinois, is trawling Facebook. He's just recovered from a debilitating bout of depression, and he's looking for someone to talk to. Through an online personality test, he finds a match: Jiyun, a 20-year-old from Korea, who moved to New York City with her family for her brother's cancer treatment. Gus messages her, and they begin chatting. "I started to fall for him when I saw these tagged videos on Facebook," Jiyun reveals in Nancy Schwartzman's short documentary, xoxosms.

Scanning an empty field that once housed a Shaker village in New Hampshire, Jesse Casana had come in search of the foundations of stone buildings, long-forgotten roadways and other remnants of this community dating to the 1790s. But instead of a trowel and shovel, Casana and his Dartmouth College colleague Chad Hill are using a drone equipped with a thermal imaging camera and mapping instruments. The camera can identify remnants of buildings and other structures up to several feet below the surface, since the temperatures of that brick or stone material is often warmer than the soil around it. Dartmouth's Chad Hill readies a drone to be flown over a site of a Shaker Village in Enfield, NH. The team was able to recognize traces of long-removed historic buildings and pathways at the Shaker Village in Enfield, N.H. The community once housed nearly 100 buildings but was sold in the 1920s and is now an outdoor history museum.

There is a widespread need for statistical methods that can analyze high-dimensional datasets with- out imposing restrictive or opaque modeling assumptions. This paper describes a domain-general data analysis method called CrossCat. CrossCat infers multiple non-overlapping views of the data, each consisting of a subset of the variables, and uses a separate nonparametric mixture to model each view. CrossCat is based on approximately Bayesian inference in a hierarchical, nonparamet- ric model for data tables. This model consists of a Dirichlet process mixture over the columns of a data table in which each mixture component is itself an independent Dirichlet process mixture over the rows; the inner mixture components are simple parametric models whose form depends on the types of data in the table. CrossCat combines strengths of mixture modeling and Bayesian net- work structure learning. Like mixture modeling, CrossCat can model a broad class of distributions by positing latent variables, and produces representations that can be efficiently conditioned and sampled from for prediction. Like Bayesian networks, CrossCat represents the dependencies and independencies between variables, and thus remains accurate when there are multiple statistical signals. Inference is done via a scalable Gibbs sampling scheme; this paper shows that it works well in practice. This paper also includes empirical results on heterogeneous tabular data of up to 10 million cells, such as hospital cost and quality measures, voting records, unemployment rates, gene expression measurements, and images of handwritten digits. CrossCat infers structure that is consistent with accepted findings and common-sense knowledge in multiple domains and yields predictive accuracy competitive with generative, discriminative, and model-free alternatives.