AI Paper Atlas

Research map / Time series / Causal and generative time series

Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring

Changhun Kim, Yechan Mun, Hyeongwon Jang, Eunseo Lee, Sangchul Hahn, Eunho Yang

ICLR 2026 · Time series › Causal and generative time series · approach: Robust forecasting and evaluation · 0 citations (OpenAlex)

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 SWING instead of IGDelta-XAI wrapper · MIMIC-III LSTM, T2-T1=1CPD: 13.42 -> 23.87Improved
use SWING instead of IGDelta-XAI wrapper · MIMIC-III LSTM, T2-T1=1CPP (lower better): 33.55 -> 17.76Improved
add retrospective baseline selection (ablation)SWING · MIMIC-III LSTM, T2-T1=24CPP (lower better): 79.70 -> 60.29Improved
add retrospective baseline selection and piecewise integration (ablation)SWING · MIMIC-III LSTM, T2-T1=24CPP (lower better): 104.05 -> 60.29Improved
add dual-path integration (ablation)SWING · MIMIC-III LSTM, T2-T1=24CPP (lower better): 71.01 -> 60.29Improved
add dual-path integration (ablation)SWING · MIMIC-III LSTM, T2-T1=24CPD: 55.01 -> 41.07Hurt
use baseline offset d=1 instead of d=0 (ablation)SWING · MIMIC-III LSTM, T2-T1=24CPD: 33.80 -> 41.07Improved
use baseline offset d=1 instead of d=3 (ablation)SWING · MIMIC-III LSTM, T2-T1=24Corr.: 0.19 -> 0.21Mixed
vary n_samples from 10 to 100 (ablation)SWING · MIMIC-IIIfaithfulness metricsNo clear effect
use forward-fill instead of zero substitution for evaluation (ablation)evaluation protocol · MIMIC-III LSTMOOD score: 0.840 -> 0.093Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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