Paper Citation Record · LEDGER

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models

As of 15 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2412.04532.

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

pith.paper-citation-record.v1
2412.04532 v3

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T21:35:48.818102Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+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

16 of 16 outbound references displayed

verified exact0
verified fuzzy4
unresolved11
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1fe99bba-9e99-4feb-acfa-d7bdaa829daf · outbound

This paper cites (Suresh et al.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models (Suresh et al

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:35:48.943621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ead48eb7-9763-404a-81ab-397475e6743e · outbound

This paper cites (2020) ablated the input features by sampling counterfactuals from the bootstrapped distribution.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models (2020) ablated the input features by sampling counterfactuals from the bootstrapped distribution

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:35:48.937791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8b0e7c5f-e268-4560-a916-0ed207d380f8 · outbound

This paper cites an unresolved cited work.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:35:48.930774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 98e96f16-cd5f-4a0c-82a2-301e67d12c10 · outbound

This paper cites an unresolved cited work.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:35:48.923795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0af6933d-b29a-45c5-9015-af9159132113 · outbound

This paper cites an unresolved cited work.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:35:48.916802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 60738749-8c16-4417-baea-4d36e4eccd46 · outbound

This paper cites an unresolved cited work.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:35:48.909881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 431a788a-1c02-4e2f-a2f2-54332da55d89 · outbound

This paper cites an unresolved cited work.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:35:48.902905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9b4b2598-efcd-41ba-b69b-9affe0913fb2 · outbound

This paper cites (2023) explicitly accounted for the temporal dependence among observations of the same feature by summarizing its importance over a lookback window.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models (2023) explicitly accounted for the temporal dependence among observations of the same feature by summarizing its importance over a lookback window

Reference 8

Resolution: malformed identifier; raw_fallback, observed 2026-08-11T21:35:48.895581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c9186d81-bf6f-42f3-8e2f-eda03069679c · outbound

This paper cites (2020) proposed to separate the temporal dimension when calculating feature importance and rescaling it.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models (2020) proposed to separate the temporal dimension when calculating feature importance and rescaling it

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:35:48.887694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1ee92e98-ced7-4f89-89f7-326e2dd8481a · outbound

This paper cites (2024d) designed a contrastive learning-based masking method to learn locally sparse perturbations for better explaining feature relevance with and without top important features.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models (2024d) designed a contrastive learning-based masking method to learn locally sparse perturbations for better explaining feature relevance with and without top important features

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:35:48.879850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3e27e03a-8b14-4d0e-9d52-e7a5ba489b4b · outbound

This paper cites an unresolved cited work.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:35:48.871526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 076bb2ce-3ce1-460e-ae7f-278ac47486b6 · outbound

This paper cites an unresolved cited work.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:35:48.863874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fa433d7a-ef00-44d1-b7f2-4afc51a0e9b1 · outbound

This paper cites an unresolved cited work.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:35:48.856905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 41d7f135-d2fd-4c0b-a571-9c6b50e2c411 · outbound

This paper cites SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T21:35:48.776965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72933196-132e-44c3-afb2-7b81b38d53b7 · outbound

This paper cites ETSformer: Exponential Smoothing Transformers for Time-series Forecasting.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models ETSformer: Exponential Smoothing Transformers for Time-series Forecasting

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T21:35:48.783980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31fa1aa2-b41e-41c1-95d4-85d8e7d2a6cc · outbound

This paper cites TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables.

WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T21:35:48.780831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.