Tag
ConceptTS introduces an interpretable forecasting framework that uses large language models to propose human-readable concepts for multivariate time-series prediction, achieving competitive accuracy with transparency through concept bottlenecks.
This paper introduces a verifier-guided workflow around ODEFormer, a pretrained symbolic transformer, to discover interpretable equations for physical dynamical systems. It demonstrates transfer to vortex shedding and other systems using dynamical and physical-admissibility criteria to select equations from a candidate pool.
An arXiv paper presents an interpretable machine-learning framework for predicting the splitting strength of asphalt concrete using SHAP analysis, comparing six models with TabPFN performing best.
This paper introduces xMICD, a method that combines ICD code groupings with pre-trained embedding similarities to create low-dimensional, clinically interpretable patient representations, achieving predictive performance comparable to embedding-based approaches.
This paper proposes a hierarchical, interpretable-by-design pivot selection model based on proximity trees and ensemble learning. It is data-modality-agnostic and demonstrates competitive results across tabular, text, image, and time-series datasets.
This paper introduces ODIN, a novel autoencoder architecture that enforces orthogonality and importance ordering of latent dimensions, recovering PCA-like interpretability in a fully non-linear regime. The method integrates geometric constraints into the training objective, theoretically grounded and empirically validated on synthetic and real-world datasets.
GP_ELITE is a pure-Python library for genetic-programming based symbolic regression, enabling discovery of interpretable mathematical formulas from small experimental datasets. Version 0.2.0 introduces Levenberg–Marquardt constant fitting, multi-restart reliability, Pareto front output, and extrapolation mode.
This paper proposes an interpretable causal-discovery-guided framework for deriving a Sleep Recovery Score (SRS) from multimodal polysomnography data, demonstrating up to 2.5× stronger alignment with perceived recovery than the traditional Apnea–Hypopnea Index (AHI), with potential applications in connected health.
Researchers from Kennesaw State University investigate cross-prompt generalization in detecting AI-generated fake news using interpretable linguistic features (lexical diversity, readability, emotion). A random forest classifier trained on one prompting strategy and tested on another achieves AUC values of 0.988–1.000, suggesting these features capture stable, generalizable properties of AI-generated text.
This paper introduces a Riemannian version of archetypal analysis using data-driven pullback geometry to combine interpretability with non-linear expressiveness, proposing the Riemannian Archetypal Mapping (RAM) and demonstrating its effectiveness on synthetic data and MNIST.