AI Paper Atlas

Research map / Time series / Causal and generative time series

TimeSeg: An Information-Theoretic Segment-Wise Explainer for Time-Series Predictions

Hwijin Kim, Jaeho Kim, Changhee Lee

ICLR 2026 · Time series › Causal and generative time series · approach: Robust forecasting and evaluation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use TimeSeg instead of TimeX++ on MIT-ECGexplainer · MIT-ECGF1: 0.593 -> 0.739Improved
use TimeSeg instead of LIMESegment on SeqComb-UVexplainer · SeqComb-UVF1: 0.430 -> 0.645Improved
use TimeSeg instead of TimeX++ on FreqShapes-Vexplainer · FreqShapes-VF1: 0.799 -> 0.722Hurt
use TimeSeg instead of TimeX++ on Waferexplainer · Wafer mean substitutionsufficiency drop: 52.39 -> 0.19Improved
use TimeSeg segments instead of point-wise methodsexplainer · SeqComb-UVcontiguity: 0.215 -> 0.017Improved
raise lambda from 0.1 to 0.9 (ablation)TimeSeg · MIT-ECGsparsity: 0.218 -> 0.098Improved
raise lambda from 0.1 to 0.9 (ablation)TimeSeg · MIT-ECGsufficiency: 0.558 -> 4.728Hurt
lambda 0.3 versus 0.1 (ablation)TimeSeg · MIT-ECGF1: 0.702 -> 0.739Improved
allow multiple segments, Kmax 1 to 3 (ablation)TimeSeg · SeqComb-UVF1: 0.499 -> 0.652Improved
increase Kmax from 3 to 7 (ablation)TimeSeg · SeqComb-UVF1: 0.652 -> 0.642No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy