Entity · paper

Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity

paperactiveprovisionalbeyond-sufficiency-time-series-explanation-with-counterfactual-necessity-e61efdd3·1 events·first seen Jul 24, 2026

Aliases: Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity

Co-occurring entities

TimePNS

More like this (12)

Counterfactual Trajectory Utility The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting counterfactual chart generation Counterfactual Editing counterfactual reasoning Constraint-Aware Counterfactual Editing for Aspect-Based Sentiment Analysis Time Series Foundation Models Attainable Utility Preservation Bridge Evidence: Static Retrieval Utility Does Not Predict Causal Utility in Multi-Step Agentic Search Causal Discovery on Irregular Time Series Temporal Simultaneity Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit

Recent events (1)

4arXiv · cs.LG·Jul 24, 2026·source ↗

TimePNS: Counterfactual necessity framework for time-series classifier explanation

A new arXiv preprint introduces TimePNS, a two-stage framework for explaining time-series classifiers using Pearl's counterfactual notion of necessity. The method addresses a gap in existing sufficiency-oriented explanation methods, which can assign high importance to spurious subsequences that support but are not essential to a model's prediction. TimePNS learns a causal generative process and uses counterfactual interventions to identify decision-critical temporal subsequences, reporting improved sufficiency-necessity trade-offs over baselines on synthetic and real-world benchmarks.

Evaluation and Benchmarking Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity TimePNS