Tootfinder

High-Dimensional Analysis of Single-Layer Attention for Sparse-Token Classification
Nicholas Barnfield, Hugo Cui, Yue M. Lu
https://arxiv.org/abs/2509.25153 https://

High-Dimensional Analysis of Single-Layer Attention for Sparse-Token Classification
When and how can an attention mechanism learn to selectively attend to informative tokens, thereby enabling detection of weak, rare, and sparsely located features? We address these questions theoretically in a sparse-token classification model in which positive samples embed a weak signal vector in a randomly chosen subset of tokens, whereas negative samples are pure noise. In the long-sequence limit, we show that a simple single-layer attention classifier can in principle achieve vanishing tes…

Nothing's new Lock Glimpse feature on the Phone (3a) Lite shows a rotating selection of wallpapers that link to clickbait articles from a company called Vilykke (Ben Schoon/9to5Google)
https://9to5google.com/2025/10/30/nothing-lock-screen-ads-sketchy/

Nothing’s bizarre new lock screen ‘ads’ want you to visit this sketchy clickbait farm [Gallery]
Nothing’s new “Lock Glimpse” feature delivers a rotating selection of wallpapers on the lock screen of the Phone (3a) Lite,...

Presenting a classifier to detect research contributions in OpenAlex
Nick Haupka
https://arxiv.org/abs/2507.22479 https://arxiv.org/pdf/2507.22479

Presenting a classifier to detect research contributions in OpenAlex
This paper introduces a document type classifier with the purpose to optimise the distinction between research and non-research journal publications in OpenAlex. Based on open metadata, the classifier can detect non-research or editorial content within a set of classified articles and reviews (e.g. paratexts, abstracts, editorials, letters). The classifier achieves an F1-score of 0,95, indicating a potential improvement in the data quality of bibliometric research in OpenAlex when applying the …

Usually, clickbait titles repel me as a reader/viewer. I tend to skip.
Occasionally, though, I do click on them. Maybe what's behing the clickbait is actually interesting?
I does happen. Sometimes I don't regret clicking (but I hardly ever share).
Most often, though, I do.

ABC-SN: Attention Based Classifier for Supernova Spectra
Willow Fox Fortino, Federica B. Bianco, Pavlos Protopapas, Daniel Muthukrishna, Austin Brockmeier
https://arxiv.org/abs/2507.22106

ABC-SN: Attention Based Classifier for Supernova Spectra
While significant advances have been made in photometric classification ahead of the millions of transient events and hundreds of supernovae (SNe) each night that the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) will discover, classifying SNe spectroscopically remains the best way to determine most subtypes of SNe. Traditional spectrum classification tools use template matching techniques (Blondin & Tonry 2007) and require significant human supervision. Two deep learning spe…

Generative Modeling and Decision Fusion for Unknown Event Detection and Classification Using Synchrophasor Data
Yi Hu, Zheyuan Cheng
https://arxiv.org/abs/2509.22795 https://

Generative Modeling and Decision Fusion for Unknown Event Detection and Classification Using Synchrophasor Data
Reliable detection and classification of power system events are critical for maintaining grid stability and situational awareness. Existing approaches often depend on limited labeled datasets, which restricts their ability to generalize to rare or unseen disturbances. This paper proposes a novel framework that integrates generative modeling, sliding-window temporal processing, and decision fusion to achieve robust event detection and classification using synchrophasor data. A variational autoe…

Label-Guided Imputation via Forest-Based Proximities for Improved Time Series Classification
Jake S. Rhodes, Adam G. Rustad, Sofia Pelagalli Maia, Evan Thacker, Hyunmi Choi, Jose Gutierrez, Tatjana Rundek, Ben Shaw
https://arxiv.org/abs/2509.22919

Label-Guided Imputation via Forest-Based Proximities for Improved Time Series Classification
Missing data is a common problem in time series data. Most methods for imputation ignore label information pertaining to the time series even if that information exists. In this paper, we provide a framework for missing data imputation in the context of time series classification, where each time series is associated with a categorical label. We define a means of imputing missing values conditional upon labels, the method being guided by powerful, existing supervised models designed for high ac…

A University of Texas Medical Branch Case Study on Aortic Calcification Detection
Eric Walser, Peter McCaffrey, Kal Clark, Nicholas Czarnek
https://arxiv.org/abs/2509.23930 http…

A University of Texas Medical Branch Case Study on Aortic Calcification Detection
This case study details The University of Texas Medical Branch (UTMB)'s partnership with Zauron Labs, Inc. to enhance detection and coding of aortic calcifications (ACs) using chest radiographs. ACs are often underreported despite their significant prognostic value for cardiovascular disease, and UTMB partnered with Zauron to apply its advanced AI tools, including a high-performing image model (AUC = 0.938) and a fine-tuned language model based on Meta's Llama 3.2, to retrospectively analyze im…

Multimodal Late Fusion Model for Problem-Solving Strategy Classification in a Machine Learning Game
Clemens Witt, Thiemo Leonhardt, Nadine Bergner, Mareen Grillenberger
https://arxiv.org/abs/2507.22426

Multimodal Late Fusion Model for Problem-Solving Strategy Classification in a Machine Learning Game
Machine learning models are widely used to support stealth assessment in digital learning environments. Existing approaches typically rely on abstracted gameplay log data, which may overlook subtle behavioral cues linked to learners' cognitive strategies. This paper proposes a multimodal late fusion model that integrates screencast-based visual data and structured in-game action sequences to classify students' problem-solving strategies. In a pilot study with secondary school students (N=149) p…

A Novel Preprocessing Unit for Effective Deep Learning based Classification and Grading of Diabetic Retinopathy
Pranoti Nage, Sanjay Shitole
https://arxiv.org/abs/2509.24497 htt…

A Novel Preprocessing Unit for Effective Deep Learning based Classification and Grading of Diabetic Retinopathy
Early detection of diabetic retinopathy (DR) is crucial as it allows for timely intervention, preventing vision loss and enabling effective management of diabetic complications. This research performs detection of DR and DME at an early stage through the proposed framework which includes three stages: preprocessing, segmentation, feature extraction, and classification. In the preprocessing stage, noise filtering is performed by fuzzy filtering, artefact removal is performed by non-linear diffus…