Pith. sign in

REVIEW 1 cited by

An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2012.04344 v1 pith:7YC7S5JX submitted 2020-12-08 cs.LG cs.AI

classification cs.LGcs.AI
keywords methodsseriestechniquestimeattributionempiricalexplainableimages
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques. However, many proposed XAI methods produce unverified outputs. Evaluation and verification are usually achieved with a visual interpretation by humans on individual images or text. In this preregistration, we propose an empirical study and benchmark framework to apply attribution methods for neural networks developed for images and text data on time series. We present a methodology to automatically evaluate and rank attribution techniques on time series using perturbation methods to identify reliable approaches.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Interpretable deep convolutional model for nonlinear multivariate time series in complex systems

    stat.ML 2025-01 conditional novelty 5.0 of 10

    DCIts is a convolutional model whose per-sample transition tensor recovers signed, lag-resolved causal coefficients matching the ground-truth generators of eight synthetic multivariate time series.

Pith tools