Work

Signals, Concepts, and Laws: Toward Universal, Explainable Time-Series Forecasting

Year: 2025

Type: preprint

Abstract: Accurate, explainable and physically credible forecasting remains a persistent challenge for multivariate time-series whose statistical properties vary across domains. We propose DORIC, a Domain-Universal, ODE-Regularized, Interpretable-Concept Transformer for Time-Series Forecasting that generates predictions through five self-supervised, domain-agnostic concepts while enforcing differentiable residuals grounded in first-principles constraints.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2508.01407

Authors: Ma, Hongwei, Gao, Junbin, Tran, Minh-Ngoc

Language: English

Topic: Time Series Analysis and Forecasting

Subfield: Signal Processing

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4415330527

Cites:

Cited by:

Related to: