We introduce Toto, a time series forecasting foundation model with 151 million parameters. Toto uses a modern decoder-only architecture coupled with architectural innovations designed to account for specific challenges found in multivariate observability time series data. Toto's pre-training corpus is a mixture of observability data, open datasets, and synthetic data, and is 4-10$\times$ larger than those of leading time series foundation models. Additionally, we introduce BOOM, a large-scale benchmark consisting of 350 million observations across 2,807 real-world time series. For both Toto and BOOM, we source observability data exclusively from our own telemetry and internal observability metrics. Extensive evaluations demonstrate that Toto achieves state-of-the-art performance on both BOOM and on established general purpose time series forecasting benchmarks. Toto's model weights, inference code, and evaluation scripts, as well as BOOM's data and evaluation code, are all available as open source under the Apache 2.0 License.

Motivational interviewing (MI) is a counseling approach that aims to increase intrinsic motivation and commitment to change. Despite its effectiveness in various disorders such as addiction, weight loss, and smoking cessation, publicly available annotated MI datasets are scarce, limiting the development and evaluation of MI language generation models. We present MI-TAGS, a new annotated dataset of MI therapy sessions written in English collected from video recordings available on public sources. The dataset includes 242 MI demonstration transcripts annotated with the MI Treatment Integrity (MITI) 4.2 therapist behavioral codes and global scores, and Client Language EAsy Rating (CLEAR) 1.0 tags for client speech. In this paper we describe the process of data collection, transcription, and annotation, and provide an analysis of the new dataset. Additionally, we explore the potential use of the dataset for training language models to perform several MITI classification tasks; our results suggest that models may be able to automatically provide utterance-level annotation as well as global scores, with performance comparable to human annotators.

The well documented mental health crisis among preteens and teenagers worldwide is often believed to be intertwined with the increasing ubiquity of social media services, a belief borne out by numerous findings in the literature. However, the literature has not kept pace with recent developments in the social-media sphere, such as the rise of TikTok and the decision by Instagram to pivot to video. This paper aims to help alleviate this deficiency, examining whether a correlation exists between college students' social media usage and mental health concerns. Using a random sample of 254 undergraduate college students at a mid-Atlantic university, we find (as evidenced by Spearman's rank correlation coefficients) that while there is a correlation between "fear of missing out (FoMO)" and social media use, the correlation is not strong, suggesting that social media use alone cannot explain observed mental health outcomes. We support previous literature regarding correlations between personality and social media use and extend it with additional measures of use to include FoMO and loneliness. We find that loneliness is weekly and inversely correlated with Instagram and Snapchat use and personality traits moderate use. We speculate that the shift in social media from peer-to-peer text to short video may be driving divergence from previous findings in the literature, lessening risk, but suggesting that additional research is needed to confirm our conclusions.