A budgeted information-bottleneck forecaster matches black-box multivariate accuracy while using only 14–20% of history tokens as architecturally faithful explanations.
Time- RA : Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Information Bottleneck Learning for Faithful Time Series Forecasting Explanations
A budgeted information-bottleneck forecaster matches black-box multivariate accuracy while using only 14–20% of history tokens as architecturally faithful explanations.