Is the Rat War Over? In New York, a rat czar and new methods have brought down complaints. We may even be ready to appreciate the creatures. Rats were leaving Manhattan, hurrying across the bridges in single-file lines. Some went to Westchester, some to Brooklyn. It was the pandemic, and the rats, which had been living off the nourishing trash of New York's densest borough for generations, were as panicked about the closure of restaurants as we were. People were eating three meals a day at home, and the rats were hungry. At least that was the story going around.

Extracting sections from clinical notes is crucial for downstream analysis but is challenging due to variability in formatting and labor-intensive nature of manual sectioning. While proprietary large language models (LLMs) have shown promise, privacy concerns limit their accessibility. This study develops a pipeline for automated note sectioning using open-source LLMs, focusing on three sections: History of Present Illness, Interval History, and Assessment and Plan. We fine-tuned three open-source LLMs to extract sections using a curated dataset of 487 progress notes, comparing results relative to proprietary models (GPT-4o, GPT-4o mini). Internal and external validity were assessed via precision, recall and F1 score. Fine-tuned Llama 3.1 8B outperformed GPT-4o (F1=0.92). On the external validity test set, performance remained high (F1= 0.85). Fine-tuned open-source LLMs can surpass proprietary models in clinical note sectioning, offering advantages in cost, performance, and accessibility.

Large language models (LLMs) have shown promise in safety-critical applications such as healthcare, yet the ability to quantify performance has lagged. An example of this challenge is in evaluating a summary of the patient's medical record. A resulting summary can enable the provider to get a high-level overview of the patient's health status quickly. Yet, a summary that omits important facts about the patient's record can produce a misleading picture. This can lead to negative consequences on medical decision-making. We propose MED-OMIT as a metric to explore this challenge. We focus on using provider-patient history conversations to generate a subjective (a summary of the patient's history) as a case study. We begin by discretizing facts from the dialogue and identifying which are omitted from the subjective. To determine which facts are clinically relevant, we measure the importance of each fact to a simulated differential diagnosis. We compare MED-OMIT's performance to that of clinical experts and find broad agreement We use MED-OMIT to evaluate LLM performance on subjective generation and find some LLMs (gpt-4 and llama-3.1-405b) work well with little effort, while others (e.g. Llama 2) perform worse.

Chatbots are at the front lines of an unrelenting AI invasion. The steady increase of artificial minds in our collective psyche is akin to mass immigration--barely noticed and easily overlooked, until it's too late. Our cultural landscape is being colonized by bots, and as with illegal aliens, much of our population welcomes this as "progress." The bots will keep us company. They will learn and absorb our personalities.

For big fans of James Cameron's Avatar, the 13-year wait between the original and this year's sequel probably felt near interminable. But die-hard fans might have counted with a bit more agony and say it's actually been vomrra zìsìt, or "15 years." Rather, the blue-skinned Na'vi people, who inhabit the planet Pandora in Cameron's universe, have four digits per hand. As a result, their language--painstakingly built from scratch for the movies--uses base-eight counting instead of the human base-10. Fifteen in Na'vi actually means eight plus five (as opposed to 10 plus five in English), making it the equivalent of our 13.

Pyrocumulonimbus (pyroCb) clouds are storm clouds generated by extreme wildfires. PyroCbs are associated with unpredictable, and therefore dangerous, wildfire spread. They can also inject smoke particles and trace gases into the upper troposphere and lower stratosphere, affecting the Earth's climate. As global temperatures increase, these previously rare events are becoming more common. Being able to predict which fires are likely to generate pyroCb is therefore key to climate adaptation in wildfire-prone areas. This paper introduces Pyrocast, a pipeline for pyroCb analysis and forecasting. The pipeline's first two components, a pyroCb database and a pyroCb forecast model, are presented. The database brings together geostationary imagery and environmental data for over 148 pyroCb events across North America, Australia, and Russia between 2018 and 2022. Random Forests, Convolutional Neural Networks (CNNs), and CNNs pretrained with Auto-Encoders were tested to predict the generation of pyroCb for a given fire six hours in advance. The best model predicted pyroCb with an AUC of $0.90 \pm 0.04$.

Locus Robotics said its autonomous mobile robots (AMRs) have now surpassed one billion picks. The company's billionth pick was made at a home improvement retailer warehouse in Florida, where a LocusBot picked a cordless rotary tool kit. Just milliseconds after the billionth pick, another LocusBot picked a scented candle from a home goods warehouse in Ohio, and a running jacket from a global fitness and shoe brand in Pennsylvania. The company completed its billionth pick just 59 days after hitting its 900 millionth unit picked. For comparison, it took Locus 1,542 days to pick its first 100 million units.

The labels used to train machine learning (ML) models are of paramount importance. Typically for ML classification tasks, datasets contain hard labels, yet learning using soft labels has been shown to yield benefits for model generalization, robustness, and calibration. Earlier work found success in forming soft labels from multiple annotators' hard labels; however, this approach may not converge to the best labels and necessitates many annotators, which can be expensive and inefficient. We focus on efficiently eliciting soft labels from individual annotators. We collect and release a dataset of soft labels (which we call CIFAR-10S) over the CIFAR-10 test set via a crowdsourcing study (N=248). We demonstrate that learning with our labels achieves comparable model performance to prior approaches while requiring far fewer annotators -- albeit with significant temporal costs per elicitation. Our elicitation methodology therefore shows nuanced promise in enabling practitioners to enjoy the benefits of improved model performance and reliability with fewer annotators, and serves as a guide for future dataset curators on the benefits of leveraging richer information, such as categorical uncertainty, from individual annotators.

Machine learning researchers are teaching neural networks how to superficially judge humans -- and the results are as brutal as they are familiar. A study about the judgmental AI, published in the prestigious Proceedings of the National Academy of Sciences journal, describes how researchers trained the model how to judge attributes in human faces, the way we do upon first meeting each other, and how they trained it to manipulate photos to evoke different judgments, such as appearing "trustworthy" or "dominant." "Our dataset not only contains bias," Princeton computer science postdoctoral researcher Joshua Peterson wrote in a tweet thread about the research, "it deliberately reflects it." We collected over 1 million human judgments to power a model that can both predict and manipulate first impressions of diverse and naturalistic faces! The PNAS paper notes that the AI so mirrored human judgment that it tended to associate objective physical characteristics, such as someone's size or skin color, with attributes ranging from trustworthiness to privilege.

Many psychology studies have confirmed the biased nature of human judgments and decision-making. When interacting with a new person, for instance, humans often make a series of automatic and superficial judgments based solely on their appearance, facial features, ethnicity, body-type, and body language. Researchers at Researchers at Princeton University, Stevens Institute of Technology, and the Booth School of Business of the University of Chicago have recently tried to predict some of the automatic inferences that humans make about others based solely on their face, using deep neural networks. Their paper, published in PNAS, introduces a machine learning model that can predict the arbitrary judgments users will make about specific pictures of faces with remarkable accuracy. "As psychologists, we are interested in how people perceive and judge faces, especially when there are important consequences, such as hiring and sentencing decisions involved," Joshua Peterson, one of the researchers who carried out the study, told TechXplore "However, most work up to now was limited to studying artificial 3D face renderings or small sets of photographs."