ProtoSSL discovers generalizable prototypes from unlabeled time-series via self-supervision and assigns them to new tasks for interpretable predictions, outperforming supervised baselines in low-data regimes on ECG datasets.
Explainable artificial intelligence (xai) on timeseries data: A survey.arXiv preprint arXiv:2104.00950
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 2representative citing papers
TFRBench is a new benchmark and multi-agent synthesis method that generates reasoning traces for time-series forecasting and shows these traces raise average accuracy from ~40% to ~57% when used to prompt LLMs.
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
STRIDE injects distilled LLM reasoning as continuous cross-modal priors into TSFMs via mean-pooled hidden states, achieving SOTA forecasting (0.674 MASE, 0.454 CRPS) on GIFT-Eval and superior reasoning on TFRBench.
A gated residual KAN framework called Temporal Functional Circuits maps edge functions to input lags, ranks them by activation, and validates faithfulness via interventions showing that learned B-splines add predictive value beyond base activations.
INSIGHTS creates manageable global summaries of time series model behavior by balancing sample importance and diversity with domain-specific utility functions, validated via experiments and user studies.
citing papers explorer
-
ProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data
ProtoSSL discovers generalizable prototypes from unlabeled time-series via self-supervision and assigns them to new tasks for interpretable predictions, outperforming supervised baselines in low-data regimes on ECG datasets.
-
TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems
TFRBench is a new benchmark and multi-agent synthesis method that generates reasoning traces for time-series forecasting and shows these traces raise average accuracy from ~40% to ~57% when used to prompt LLMs.
-
On What We Can Learn from Low-Resolution Data
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
-
Reasoning-Aware Training for Time Series Forecasting
STRIDE injects distilled LLM reasoning as continuous cross-modal priors into TSFMs via mean-pooled hidden states, achieving SOTA forecasting (0.674 MASE, 0.454 CRPS) on GIFT-Eval and superior reasoning on TFRBench.
-
Temporal Functional Circuits: From Spline Plots to Faithful Explanations in KAN Forecasting
A gated residual KAN framework called Temporal Functional Circuits maps edge functions to input lags, ranks them by activation, and validates faithfulness via interventions showing that learned B-splines add predictive value beyond base activations.
-
INSIGHTS: Demonstration-Based Summaries of Time Series Predictors
INSIGHTS creates manageable global summaries of time series model behavior by balancing sample importance and diversity with domain-specific utility functions, validated via experiments and user studies.