INSIGHTS: Demonstration-Based Summaries of Time Series Predictors

• URL: http://arxiv.org/abs/2605.18849v1
• Date: Wed, 13 May 2026 08:17:35 GMT
• Title: INSIGHTS: Demonstration-Based Summaries of Time Series Predictors
• Abstract summary: We introduce INSIGHTS, a model-agnostic, user-centric approach for providing global explanations of time series models.<n>Our approach prioritizes simplicity, efficiency, and transparency in its design, ensuring that stakeholders can readily adopt its outputs.
• Score: 10.537943094162754
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Explainability methods have progressed rapidly, but global explanations for time-series models remain underdeveloped, with most approaches focusing on local, instance-level attributions. We introduce INSIGHTS, a model-agnostic, user-centric approach for providing global explanations of time series models. Our approach prioritizes simplicity, efficiency, and transparency in its design, ensuring that stakeholders can readily adopt its outputs. While current methods focus on local explanations, INSIGHTS generates sample summaries that offer a comprehensive overview of model behavior. It balances the importance and diversity of time series samples to create informative subsets using utility functions that capture domain-specific aspects of time series behavior, such as exceeding domain norms. We evaluate INSIGHTS through experiments, interviews, and a user study. Our results indicate INSIGHTS effectively constructs comprehensive, diverse time series subsets, producing summaries manageable for individual evaluation. It is preferred by domain experts for its ability to provide a stable understanding of model behavior and the quality of the samples identified. Moreover, user study participants presented with INSIGHTS-based summaries exhibit an enhanced understanding of the model's overall behavior.

Related papers

• TimeVista: Exploring and Exploiting Vision-Language Models as Judges for Time Series Forecasting [51.59529402134439]
  ''LLM-as-a-Judge'' paradigm has revolutionized text evaluation by providing flexible, human-aligned judgment.<n>We propose a novel framework integrating micro- and macro-level judgments informed by contextual information.<n>Extensive meta-evaluations demonstrate that Vision-Language Models (VLMs) are highly reliable judges.
  arXiv  Detail & Related papers  (2026-06-15T03:39:55Z)
• INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification [12.611616081807673]
  INSHAPE is an interpretable framework that discovers variable-length, discriminative temporal patterns specific to each time series.<n>In experiments on 128 UCR and 30 UEA benchmark datasets, INSHAPE consistently outperforms state-of-the-art shapelet-based methods.
  arXiv  Detail & Related papers  (2026-05-19T16:43:41Z)
• It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks [87.7937890373758]
  Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.<n>We introduce TIME, a next-generation task-centric benchmark comprising 50 fresh datasets and 98 forecasting tasks.<n>We propose a novel pattern-level evaluation perspective that moves beyond traditional dataset-level evaluations based on static meta labels.
  arXiv  Detail & Related papers  (2026-02-12T16:31:01Z)
• ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting [25.219624871510376]
  We propose ProtoTS, a novel interpretable forecasting framework that achieves both high accuracy and transparent decision-making.<n>ProtoTS computes instance-prototype similarity based on a denoised representation that preserves abundant heterogeneous information.<n> Experiments on multiple realistic benchmarks, including a newly released LOF dataset, show that ProtoTS not only exceeds existing methods in forecast accuracy but also delivers expert-steerable interpretations.
  arXiv  Detail & Related papers  (2025-09-27T07:10:21Z)
• Stochastic Encodings for Active Feature Acquisition [100.47043816019888]
  Active Feature Acquisition is an instance-wise, sequential decision making problem.<n>The aim is to dynamically select which feature to measure based on current observations, independently for each test instance.<n>Common approaches either use Reinforcement Learning, which experiences training difficulties, or greedily maximize the conditional mutual information of the label and unobserved features, which makes myopic.<n>We introduce a latent variable model, trained in a supervised manner. Acquisitions are made by reasoning about the features across many possible unobserved realizations in a latent space.
  arXiv  Detail & Related papers  (2025-08-03T23:48:46Z)
• When Does Multimodality Lead to Better Time Series Forecasting? [96.26052272121615]
  We investigate whether and under what conditions such multimodal integration consistently yields gains.<n>Our findings reveal that the benefits of multimodality are highly condition-dependent.<n>Our study offers a rigorous, quantitative foundation for understanding when multimodality can be expected to aid forecasting tasks.
  arXiv  Detail & Related papers  (2025-06-20T23:55:56Z)
• Evaluating Generalization and Representation Stability in Small LMs via Prompting, Fine-Tuning and Out-of-Distribution Prompts [2.377892000761193]
  We investigate the generalization capabilities of small language models under two popular adaptation paradigms: few-shot prompting and supervised fine-tuning.<n>Our findings highlight critical differences in how small models internalize and generalize knowledge under different adaptation strategies.
  arXiv  Detail & Related papers  (2025-06-16T01:44:26Z)
• Implet: A Post-hoc Subsequence Explainer for Time Series Models [7.890123610098698]
  We introduce Implet, a novel post-hoc explainer for time series models.<n>Our approach identifies critical temporal segments that significantly contribute to the model's predictions.<n>We propose a cohort-based (group-level) explanation framework.
  arXiv  Detail & Related papers  (2025-05-13T17:01:23Z)
• Context is Key: A Benchmark for Forecasting with Essential Textual Information [87.3175915185287]
  "Context is Key" (CiK) is a forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context.<n>We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters.<n>We propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark.
  arXiv  Detail & Related papers  (2024-10-24T17:56:08Z)
• Extracting Interpretable Local and Global Representations from Attention on Time Series [0.135975510645475]
  This paper targets two transformer attention based interpretability methods working with local abstraction and global representation. We distinguish local and global contexts, and provide a comprehensive framework for both general interpretation options.
  arXiv  Detail & Related papers  (2023-09-16T00:51:49Z)
• Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization [50.20034493626049]
  Recent pre-trained language models (PLMs) achieve promising results in existing abstractive summarization datasets. Existing summarization benchmarks overlap in time with the standard pre-training corpora and finetuning datasets. We show that parametric knowledge stored in summarization models significantly affects the faithfulness of the generated summaries on future data.
  arXiv  Detail & Related papers  (2023-05-03T08:08:07Z)
• An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
  Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches. This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
  arXiv  Detail & Related papers  (2022-07-07T06:50:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.