Paper Citation Record · LEDGER

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy

As of 21 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2509.21190.

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

pith.paper-citation-record.v1
2509.21190 v5

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:53:45.443308Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

36 of 36 outbound references displayed

verified exact2
verified fuzzy20
unresolved13
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 55ada0f8-cabb-4789-ad85-36ba45b32770 · outbound

This paper cites •Increase after downward spike.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy •Increase after downward spike

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.133279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 469f2d86-d660-438e-bddd-7784608ee510 · outbound

This paper cites MOMENT: A Family of Open Time-series Foundation Models.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy MOMENT: A Family of Open Time-series Foundation Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.280447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed2a22e7-db54-424c-bba6-9128cab5a438 · outbound

This paper cites From tables to time: How tabpfn-v2 outper- forms specialized time series forecasting models.arXiv preprint arXiv:2501.02945,.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy From tables to time: How tabpfn-v2 outper- forms specialized time series forecasting models.arXiv preprint arXiv:2501.02945,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.284432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c72260a7-396e-4883-950f-40e436ef9fd4 · outbound

This paper cites The table is grouped by anomaly type, with metrics listed vertically for each.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy The table is grouped by anomaly type, with metrics listed vertically for each

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:45.968013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 219b66d9-9581-44f6-b24d-97355c73df11 · outbound

This paper cites Breaking the time-frequency granularity discrepancy in time-series anomaly detection.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Breaking the time-frequency granularity discrepancy in time-series anomaly detection

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.189718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6a9c721f-484d-48e0-8b94-64540eb618bd · outbound

This paper cites A Time Series is Worth 64 Words: Long-term Forecasting with Transformers.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy A Time Series is Worth 64 Words: Long-term Forecasting with Transformers

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.295419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbae536b-d3d5-4274-b281-df2acccead09 · outbound

This paper cites Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:53:45.689234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 05e31808-3cfe-4bbe-ab65-47023bec3903 · outbound

This paper cites Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.303826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f5219c2-10fd-4d46-8a4a-4d1d4ebc9ca2 · outbound

This paper cites Cauker: classification time series foundation models can be pretrained on synthetic data only.arXiv preprint arXiv:2508.02879,.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Cauker: classification time series foundation models can be pretrained on synthetic data only.arXiv preprint arXiv:2508.02879,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.308252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ca6b02c-cefb-4dfc-b830-a4c53ee79afc · outbound

This paper cites Chatts: Aligning time series with llms via synthetic data for enhanced understanding and reasoning.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Chatts: Aligning time series with llms via synthetic data for enhanced understanding and reasoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.311707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 692ef5a8-2402-4792-9218-1dd0ddeffece · outbound

This paper cites Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.315856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc36445-d746-4be0-bbb0-1c404c8b58e0 · outbound

This paper cites an unresolved cited work.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:53:46.178286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e0412427-bb45-4037-85b7-a9ca5283fc31 · outbound

This paper cites an unresolved cited work.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:53:46.166709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 61099e67-87e3-46e6-8573-ac0a2b03ce79 · outbound

This paper cites For any scalaru, the logistic sigmoid isσ(u) = 1 1+e−u.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy For any scalaru, the logistic sigmoid isσ(u) = 1 1+e−u

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.154849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 42ecd288-850c-4e4e-a287-f6efe74f8867 · outbound

This paper cites 19 Under review as a conference paper at ICLR 2026 •Sudden decrease(permanent level down-shift).

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy 19 Under review as a conference paper at ICLR 2026 •Sudden decrease(permanent level down-shift)

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.144206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 41a0add9-8bef-4b95-97a7-547865e4c76e · outbound

This paper cites Fort∈[t s,te), scale the duty cycle by a factorλ >0:d7→d ′ = min{1,max{0,λd}}.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Fort∈[t s,te), scale the duty cycle by a factorλ >0:d7→d ′ = min{1,max{0,λd}}

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.122577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fcef0055-5b07-42e7-827a-d36aa0deae21 · outbound

This paper cites Zero-Shot ModelsThese models are pre-trained on large-scale datasets and can be applied directly to new time series without fine-tuning.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Zero-Shot ModelsThese models are pre-trained on large-scale datasets and can be applied directly to new time series without fine-tuning

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.111922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 21347933-d452-47e8-b01d-8308b2dc31e0 · outbound

This paper cites Its window size is.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Its window size is

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.066782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9630bc68-891b-4573-b7a0-8f8aeeb9bbfa · outbound

This paper cites It is pre-trained on a large time series corpus for forecasting and multi-task learning (Shi et al., 2024).

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy It is pre-trained on a large time series corpus for forecasting and multi-task learning (Shi et al., 2024)

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.053800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 99a03b95-7bd6-4fb5-b94b-8e63165f6eba · outbound

This paper cites •TranAD: A transformer-based model that uses a reconstructive approach to detect anomalies by comparing original and reconstructed time series (Tuli et al., 2022).

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy •TranAD: A transformer-based model that uses a reconstructive approach to detect anomalies by comparing original and reconstructed time series (Tuli et al., 2022)

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.040032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6496a3ff-66eb-45a2-9cf6-82c47a6e6264 · outbound

This paper cites We set the window size to.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy We set the window size to

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.028501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ed490a4e-1d89-412a-b6e7-5dd62444b768 · outbound

This paper cites The model is configured with a window size of.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy The model is configured with a window size of

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.016405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bdf2628f-7f4d-4743-a435-8631e51c40f7 · outbound

This paper cites For univariate datasets, we set n neighbors to 50, and for multivariate, we set n neighbors to 50 with metric as euclidean.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy For univariate datasets, we set n neighbors to 50, and for multivariate, we set n neighbors to 50 with metric as euclidean

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.004650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ded868b7-8e15-4c3c-a56d-2f095b87925f · outbound

This paper cites For Temporal F1, we follow the implmentation of Sarfraz et al.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy For Temporal F1, we follow the implmentation of Sarfraz et al

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:45.993079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ea107ae0-b41c-4a0b-be57-02ad2e6ad260 · outbound

This paper cites The total loss is a sum of two components: a Mean Squared Error loss for a masked reconstruction task and a Cross-Entropy loss for an anomaly detection task.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy The total loss is a sum of two components: a Mean Squared Error loss for a masked reconstruction task and a Cross-Entropy loss for an anomaly detection task

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:45.980507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1c51ab08-35b0-4cbf-b9f3-bf12b0ac285b · outbound

This paper cites an unresolved cited work.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Unresolved cited work

Reference 36

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T15:53:45.538529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bc18dde1-93c2-4643-87e3-12ee47c508c7 · outbound

This paper cites We set the window size to.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy We set the window size to

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.078576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0b22e4f9-d8eb-4342-bd63-f144fec6462d · outbound

This paper cites We use a window size of.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy We use a window size of

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.090127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6b992313-f18e-44a5-9a16-24207127bd7f · outbound

This paper cites It is pre-trained on a massive corpus for multi-task applications, including anomaly detection.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy It is pre-trained on a massive corpus for multi-task applications, including anomaly detection

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.100649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2cd5de54-06cd-4f97-ab5f-8e89e2fc296b · outbound

This paper cites TimeSeriesExam: A time series understanding exam.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy TimeSeriesExam: A time series understanding exam

Reference 2000

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.267819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1c0ddff-69fe-4568-8cde-a857e6816cd9 · outbound

This paper cites Chronos: Learning the Language of Time Series.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Chronos: Learning the Language of Time Series

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.179976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d21c82bb-9b65-469c-8068-70aed465a32f · outbound

This paper cites CICADA: Cross-Domain Interpretable Coding for Anomaly Detection and Adaptation in Multivariate Time Series.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy CICADA: Cross-Domain Interpretable Coding for Anomaly Detection and Adaptation in Multivariate Time Series

Reference 2019

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:53:45.724779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d8ed83fb-7d02-4a6d-85b3-f9b7dcd9a57f · outbound

This paper cites Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.216190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9285c32-c4be-4f66-b9c7-8b6e820959d7 · outbound

This paper cites Tspulse: Dual space tiny pre-trained models for rapid time- series analysis.arXiv preprint arXiv:2505.13033,.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Tspulse: Dual space tiny pre-trained models for rapid time- series analysis.arXiv preprint arXiv:2505.13033,

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T15:53:45.272690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 626259ec-a06d-49e6-93da-4c8aa709da32 · outbound

This paper cites Lof: identifying density-based local outliers.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Lof: identifying density-based local outliers

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.211642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6289efcf-8d44-419b-bb45-0c91699fb173 · outbound

This paper cites Units: A unified multi-task time series model.Advances in Neural Information Processing Systems, 37: 140589–140631,.

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy Units: A unified multi-task time series model.Advances in Neural Information Processing Systems, 37: 140589–140631,

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:53:46.201119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

No inbound Pith citation observations are available.