Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity
Faithful explanations of time-series classifiers should identify subsequences that are not only sufficient to preserve a black-box model's prediction, but also necessary for maintaining it. However, existing sufficiency-oriented methods can assign high importance to spurious subsequences that support the prediction without being essential to the model's decision. We introduce \textbf{TimePNS}, a necessity-aware framework for time-series explanation. Inspired by Pearl's counterfactual notion of necessity, TimePNS assesses whether a temporal factor is necessary by intervening on it and measuring
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- LinkedLinked via arxiv author · 85%Hongnan Ma →
“Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity”
- LinkedLinked via arxiv author · 85%Yiwei Shi →
“Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity”
- LinkedLinked via arxiv author · 85%Mengyue Yang →
“Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity”
- LinkedLinked via arxiv author · 85%Weiru Liu →
“Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity”