Paper Citation Record · LEDGER

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks

As of 9 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2602.02763.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2602.02763 v3

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T05:20:53.418351Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy0
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c5a82e55-0db6-48bf-9855-1d54b357b638 · outbound

This paper cites Ground-truth explanations correspond to the low-variance subsequences on the appropriate sensor.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Ground-truth explanations correspond to the low-variance subsequences on the appropriate sensor

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.329357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3229875d-1471-4b77-b0b0-8cf8cc1597f3 · outbound

This paper cites A Survey of the State of Explainable AI for Natural Language Processing.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks A Survey of the State of Explainable AI for Natural Language Processing

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:50.854704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd8833da-7df6-43a7-b4fb-e0184cb509d3 · outbound

This paper cites The Complex Gradient Operator and the CR-Calculus.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks The Complex Gradient Operator and the CR-Calculus

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:51.831523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ff4581-54c4-4c7f-9553-aee91be94ce6 · outbound

This paper cites Graph Neural Network Explanations are Fragile.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Graph Neural Network Explanations are Fragile

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:52.106309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1a64ef5-71d1-4254-a70e-5e62de897383 · outbound

This paper cites iTransformer: Inverted Transformers Are Effective for Time Series Forecasting.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:52.258255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c5316ba-1ccb-4eaf-8353-92ec67a5fd05 · outbound

This paper cites an unresolved cited work.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:52.592269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3b07ee1-fac3-4810-82a4-fb22889bd715 · outbound

This paper cites B., Gudelek, M.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks B., Gudelek, M

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:52.751486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92f3b21b-8bc7-4528-90cf-89b8392a93dc · outbound

This paper cites XAI Methods for Neural Time Series Classification: A Brief Review.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks XAI Methods for Neural Time Series Classification: A Brief Review

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:52.777341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84e03d85-fea3-4b3a-a460-3be6bc57eca5 · outbound

This paper cites Intriguing properties of neural networks.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Intriguing properties of neural networks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:52.881041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3912f63-8f14-47e8-9a2c-8707094fa8fe · outbound

This paper cites ALO-VC: Any-to-any Low-latency One-shot Voice Conversion.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks ALO-VC: Any-to-any Low-latency One-shot Voice Conversion

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.020882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0594c32e-64fe-4dca-9d11-77573c64de28 · outbound

This paper cites Related Work Details This appendix complements the concise Related Work in the main paper by providing additional context and representative references.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Related Work Details This appendix complements the concise Related Work in the main paper by providing additional context and representative references

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.127794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cafdca7a-b7f2-4937-817e-645454f8b152 · outbound

This paper cites The increasing deployment of deep models in high-stakes applications has made human-understandable explanations a key requirement for trustworthy decision making.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks The increasing deployment of deep models in high-stakes applications has made human-understandable explanations a key requirement for trustworthy decision making

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.188370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 445b90dc-394a-4a52-9a9f-5128894f09be · outbound

This paper cites an unresolved cited work.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.222224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c818c9d-c09f-4f2f-8d6a-666523aaa0fe · outbound

This paper cites Explainer robustness in other domains.Compared to time series, explainer robustness has been more extensively studied in vision and NLP.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Explainer robustness in other domains.Compared to time series, explainer robustness has been more extensively studied in vision and NLP

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.237678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 395a0b7e-f094-4bb4-9a92-e75a6b6e6ad8 · outbound

This paper cites vulnerable.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks vulnerable

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.249025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4cb0749-d8fd-4194-9381-212d8a0a242b · outbound

This paper cites Sinceα freq >0and(1−tanh 2)>0, the partial derivative ∂Mf ∂Θf is a strictly positive scalar.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Sinceα freq >0and(1−tanh 2)>0, the partial derivative ∂Mf ∂Θf is a strictly positive scalar

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.315478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 858f7f19-c27d-4a59-8522-e1303f15d5c6 · outbound

This paper cites It contains continuous recordings of daily activities from 9 subjects measured by multiple sensors.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks It contains continuous recordings of daily activities from 9 subjects measured by multiple sensors

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.397337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0374a66c-11ae-4724-98fd-30303b6bdbbf · outbound

This paper cites For a fair comparison, we use the same time-series explanation- alignment loss (i.e., the same target definition and distance metric) as in TSEF.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks For a fair comparison, we use the same time-series explanation- alignment loss (i.e., the same target definition and distance metric) as in TSEF

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.418351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b9d3e3d-12db-4bb6-8b6b-43b6a8ef57ca · outbound

This paper cites non-seizure.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks non-seizure

Reference 2001

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:53.374385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 553a71a3-689c-4cc8-b81e-2ce88d2c665f · outbound

This paper cites Crafting papers on machine learning.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Crafting papers on machine learning

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:51.957493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88dfcbcf-fee1-44ad-85ed-2d5f60c68fbe · outbound

This paper cites Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey

Reference 2012

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:52.684386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27e0862e-9262-49ff-9fae-2110ebf3a2e0 · outbound

This paper cites Targeted Attacks on Timeseries Forecasting.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Targeted Attacks on Timeseries Forecasting

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:51.221537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f54e8d4d-62c8-4c99-bc0e-32b688cc3ae4 · outbound

This paper cites Towards Deep Learning Models Resistant to Adversarial Attacks.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Towards Deep Learning Models Resistant to Adversarial Attacks

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:52.477013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 364cb680-e24d-49e4-9ded-6d807911841a · outbound

This paper cites The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:52.370750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bf65a0a-6d18-458f-9d83-3fbf0ee6f416 · outbound

This paper cites Shapex: Shapelet-driven post hoc explanations for time series classification models.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Shapex: Shapelet-driven post hoc explanations for time series classification models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:51.566901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a356b658-62ce-49ee-b2b6-63b678f87299 · outbound

This paper cites Adversarial Attacks and Defences: A Survey.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Adversarial Attacks and Defences: A Survey

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:50.746224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea580bf5-732c-44c8-ac75-9849b697cf09 · outbound

This paper cites Categorical Reparameterization with Gumbel-Softmax.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Categorical Reparameterization with Gumbel-Softmax

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:51.671351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14c026cf-27f4-4ed7-a200-e7091ce2aca8 · outbound

This paper cites Towards Imperceptible Adversarial Attacks for Time Series Classification with Local Perturbations and Frequency Analysis.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Towards Imperceptible Adversarial Attacks for Time Series Classification with Local Perturbations and Frequency Analysis

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:51.402621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bb463d0-7545-447d-a6c2-ff22a5785ff9 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Explaining and Harnessing Adversarial Examples

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:50.996971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84b07097-b5a6-42af-b027-5468ed01137e · outbound

This paper cites Adversarial Attacks on Multivariate Time Series.

Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks Adversarial Attacks on Multivariate Time Series

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T05:20:51.486690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.