{"as_of":"2026-08-22T00:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2df357c275affdd267f8b13c20cba9891ec5ff0c23e429377694d7b9f0fde215","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T15:53:45.443308Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.21190/citation-record","integrity":"/paper/2509.21190/integrity","json":"/paper/2509.21190/citation-record.json","paper":"/paper/2509.21190"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.129655Z","title":"•Increase after downward spike","venue":null,"work_id":"6940bb7a-ecdc-430f-8b2e-1b34f63d9e4f","year":2026},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.334983Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:315b9bacb8622e4d1a24c9fa7290ef033cc40ec0ff5cde5e62f7b7e156a979dd","observation_id":"55ada0f8-cabb-4789-ad85-36ba45b32770","resolution":{"observed_at":"2026-08-15T15:53:46.133279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03885","last_updated":"2024-10-10T15:37:45Z","snapshot_observed_at":"2026-08-19T12:57:25.768155Z","submitted_at":"2024-02-06T10:48:46Z","title":"MOMENT: A Family of Open Time-series Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03885","snapshot_observed_at":"2026-08-15T15:53:45.280447Z","title":"Monash time series forecasting archive","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.280447Z"},"links":{"cited_paper":"/paper/2402.03885","citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:2ccec90184d7906e9c435d5c05a3999b59b4f4fc831b6a940670b7564b001b47","observation_id":"469f2d86-d660-438e-bddd-7784608ee510","resolution":{"observed_at":"2026-08-15T15:53:45.280447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:45.284432Z","title":"From tables to time: How tabpfn-v2 outper- forms specialized time series forecasting models.arXiv preprint arXiv:2501.02945,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.284432Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:65af030269ed84f57bda14ae053cc7b19290aedd164317245638fd3decfa966c","observation_id":"ed2a22e7-db54-424c-bba6-9128cab5a438","resolution":{"observed_at":"2026-08-15T15:53:45.284432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:45.964018Z","title":"The table is grouped by anomaly type, with metrics listed vertically for each","venue":null,"work_id":"02321393-1c23-456a-a644-f1146c7b8cd3","year":2026},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.439160Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:cc3551822450bed6d8aa1d21bd0450a640fd4aae426b12e29b19839419b34ae8","observation_id":"c72260a7-396e-4883-950f-40e436ef9fd4","resolution":{"observed_at":"2026-08-15T15:53:45.968013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.185343Z","title":"Breaking the time-frequency granularity discrepancy in time-series anomaly detection","venue":null,"work_id":"10d019ee-9116-44d5-b42a-0a7ce14dc4c7","year":2024},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.291316Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:ac7ecc82c6d7b9f7de3e3842d8ded8275482cd742868e83c4710885356186928","observation_id":"219b66d9-9581-44f6-b24d-97355c73df11","resolution":{"observed_at":"2026-08-15T15:53:46.189718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.14730","last_updated":"2023-03-05T22:11:56Z","snapshot_observed_at":"2026-08-17T01:22:50.943392Z","submitted_at":"2022-11-27T05:15:42Z","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.14730","snapshot_observed_at":"2026-08-15T15:53:45.295419Z","title":"A time series is worth 64 words: Long-term forecasting with transformers.arXiv preprint arXiv:2211.14730,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.295419Z"},"links":{"cited_paper":"/paper/2211.14730","citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:578f6c2e83d4880c179aaecfcd4c7088f8eda6da524f8d11162d95acf26e694e","observation_id":"6a9c721f-484d-48e0-8b94-64540eb618bd","resolution":{"observed_at":"2026-08-15T15:53:45.295419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15273","last_updated":"2025-03-03T12:40:28Z","snapshot_observed_at":"2026-08-20T05:13:06.068149Z","submitted_at":"2024-05-24T06:59:43Z","title":"Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders","version":4},"cited_work":{"arxiv_id":"2405.15273","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.15273","snapshot_observed_at":"2026-08-15T15:53:45.684140Z","title":"Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders","venue":"cs.LG","work_id":"1a870375-65d0-4ee2-b422-d5d33a584fdd","year":2024},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.299431Z"},"links":{"cited_paper":"/paper/2405.15273","citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:08a2ea14e03fe3b63a6c24ba7dac277f9fe5c047fc75ecde5b261a28451b5eb2","observation_id":"fbae536b-d3d5-4274-b281-df2acccead09","resolution":{"observed_at":"2026-08-15T15:53:45.689234Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.16040","last_updated":"2025-02-27T05:38:14Z","snapshot_observed_at":"2026-08-18T09:55:20.793664Z","submitted_at":"2024-09-24T12:42:18Z","title":"Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.16040","snapshot_observed_at":"2026-08-15T15:53:45.303826Z","title":"Time-moe: Billion-scale time series foundation models with mixture of experts.arXiv preprint arXiv:2409.16040,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.303826Z"},"links":{"cited_paper":"/paper/2409.16040","citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:caf2e42b1cb6b6272e7e2dbbab408ed4d74b2df5ba3a582d5ef2adc41b0c8c8b","observation_id":"05e31808-3cfe-4bbe-ab65-47023bec3903","resolution":{"observed_at":"2026-08-15T15:53:45.303826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:45.308252Z","title":"Cauker: classification time series foundation models can be pretrained on synthetic data only.arXiv preprint arXiv:2508.02879,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.308252Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:59ef789d8548e3425155acd814f8af8d5bb675f6c32590912458c74982d9b272","observation_id":"7f5219c2-10fd-4d46-8a4a-4d1d4ebc9ca2","resolution":{"observed_at":"2026-08-15T15:53:45.308252Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:45.311707Z","title":"Chatts: Aligning time series with llms via synthetic data for enhanced understanding and reasoning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.311707Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:f8b9c952ef6b5ca574acc6dc9e057e670c1cd86c7a3c813bc942ef205f44aa16","observation_id":"7ca6b02c-cefb-4dfc-b830-a4c53ee79afc","resolution":{"observed_at":"2026-08-15T15:53:45.311707Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.02642","last_updated":"2022-06-29T13:21:52Z","snapshot_observed_at":"2026-08-19T21:21:40.889804Z","submitted_at":"2021-10-06T10:33:55Z","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.02642","snapshot_observed_at":"2026-08-15T15:53:45.315856Z","title":"Anomaly transformer: Time series anomaly detection with association discrepancy.arXiv preprint arXiv:2110.02642,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.315856Z"},"links":{"cited_paper":"/paper/2110.02642","citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:b7fb98bf143792243ee303d44985f6c04102d83752e7076b6c56b6c17868061b","observation_id":"692ef5a8-2402-4792-9218-1dd0ddeffece","resolution":{"observed_at":"2026-08-15T15:53:45.315856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.174758Z","title":null,"venue":null,"work_id":"d3f9070f-31f4-421b-b916-21fa06acb5ce","year":2026},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.319412Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:0fa5bd9402321b113bd3a5021623378904bac74e5c7ae83fde583cd4e45e3485","observation_id":"cbc36445-d746-4be0-bbb0-1c404c8b58e0","resolution":{"observed_at":"2026-08-15T15:53:46.178286Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.162679Z","title":null,"venue":null,"work_id":"d1cf0303-dcc3-4c9d-9261-2fc4f014f07e","year":2026},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.323615Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:a7180799574dd49d52de0840711baf2728c23f3e1a0a59e03ce52c7dff494483","observation_id":"e0412427-bb45-4037-85b7-a9ca5283fc31","resolution":{"observed_at":"2026-08-15T15:53:46.166709Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.151204Z","title":"For any scalaru, the logistic sigmoid isσ(u) = 1 1+e−u","venue":null,"work_id":"17bdea20-0abd-47d5-9404-e559a89b73eb","year":2026},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.327178Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:228d9e73f86788261bc49575f812c761fac7fadbe6e050914c9fbee8780073e8","observation_id":"61099e67-87e3-46e6-8573-ac0a2b03ce79","resolution":{"observed_at":"2026-08-15T15:53:46.154849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.140044Z","title":"19 Under review as a conference paper at ICLR 2026 •Sudden decrease(permanent level down-shift)","venue":null,"work_id":"a83e9332-f20e-4386-b456-e6c82bb601e8","year":2026},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.330865Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:adb9239f13ffff9920a052d9b8a6205558ed3ee15b5efae3f090081fbc493a36","observation_id":"42ecd288-850c-4e4e-a287-f6efe74f8867","resolution":{"observed_at":"2026-08-15T15:53:46.144206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.118731Z","title":"Fort∈[t s,te), scale the duty cycle by a factorλ >0:d7→d ′ = min{1,max{0,λd}}","venue":null,"work_id":"4b1cbba6-5c93-48bb-a2d0-98e982c6cc95","year":2024},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.338975Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:183c2872318dce7f4d9f1a6d88443cf0f3cc3c7502f3508aadc600150e9e469e","observation_id":"41a0add9-8bef-4b95-97a7-547865e4c76e","resolution":{"observed_at":"2026-08-15T15:53:46.122577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.107793Z","title":"Zero-Shot ModelsThese models are pre-trained on large-scale datasets and can be applied directly to new time series without fine-tuning","venue":null,"work_id":"86bea16e-d0f9-44c5-914d-0616f299fb5a","year":2024},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.343343Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:7cc96952de65b82228ca39cf0a62fedb39d39f0b7109d742cc278e203d31ee85","observation_id":"fcef0055-5b07-42e7-827a-d36aa0deae21","resolution":{"observed_at":"2026-08-15T15:53:46.111922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.062821Z","title":"Its window size is","venue":null,"work_id":"195d834a-d6b7-4303-b27d-92ae43ec3abb","year":2024},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.408556Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:8b6c7150a6313ee25a91b79ab4158a3f47ba9217fc88d9651a27f7585d8f464c","observation_id":"21347933-d452-47e8-b01d-8308b2dc31e0","resolution":{"observed_at":"2026-08-15T15:53:46.066782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.047730Z","title":"It is pre-trained on a large time series corpus for forecasting and multi-task learning (Shi et al., 2024)","venue":null,"work_id":"c9258236-ea5f-4633-b102-0b59ba2e8f9e","year":2024},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.412524Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:42864feaabb3826f9e582405b4f2ce2ac9d193382c8dfb6f41fc57f4859bf517","observation_id":"9630bc68-891b-4573-b7a0-8f8aeeb9bbfa","resolution":{"observed_at":"2026-08-15T15:53:46.053800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.036031Z","title":"•TranAD: A transformer-based model that uses a reconstructive approach to detect anomalies by comparing original and reconstructed time series (Tuli et al., 2022)","venue":null,"work_id":"e9b7e067-424f-4cd8-a349-71d1a73f7d4f","year":2022},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.416404Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:61bdff5ef894d180417a3eb01435052a3bddfe969a69c4c42faa1edeed2cefad","observation_id":"99a03b95-7bd6-4fb5-b94b-8e63165f6eba","resolution":{"observed_at":"2026-08-15T15:53:46.040032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.024419Z","title":"We set the window size to","venue":null,"work_id":"c3ad038e-60a6-4d7e-9aa1-6d6b21085a08","year":2020},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.419902Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:31a6423fdc023aeea42b529f52b44b45023e3f7099b4cd2caa23df205425c548","observation_id":"6496a3ff-66eb-45a2-9cf6-82c47a6e6264","resolution":{"observed_at":"2026-08-15T15:53:46.028501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.012669Z","title":"The model is configured with a window size of","venue":null,"work_id":"26620ab1-2a18-41b6-a800-daf318be8564","year":2019},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.423490Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:b88839a2bc4f9d2e86f247401f52c68568490180e54dadb0e5938c742aba32f0","observation_id":"ed490a4e-1d89-412a-b6e7-5dd62444b768","resolution":{"observed_at":"2026-08-15T15:53:46.016405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.000514Z","title":"For univariate datasets, we set n neighbors to 50, and for multivariate, we set n neighbors to 50 with metric as euclidean","venue":null,"work_id":"380407b7-059e-43a2-9014-25ff99510388","year":2000},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.427217Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:a572d002f361949781147b695d582d44ba066475ce807818b73019dfdb5d0067","observation_id":"bdf2628f-7f4d-4743-a435-8631e51c40f7","resolution":{"observed_at":"2026-08-15T15:53:46.004650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:45.988936Z","title":"For Temporal F1, we follow the implmentation of Sarfraz et al","venue":null,"work_id":"8436bed6-011b-4f72-8c8b-1590747044d9","year":2024},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.431141Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:e9155ce2bf4e106aebbed2b653490bf735e3cbf2b76584c1972d78075b922d9a","observation_id":"ded868b7-8e15-4c3c-a56d-2f095b87925f","resolution":{"observed_at":"2026-08-15T15:53:45.993079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:45.975896Z","title":"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","venue":null,"work_id":"751e4d37-61cc-4437-95d6-f0bacd89aabe","year":2026},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.435106Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:0a6daeb85ce0580f2315a559ea8ced0a32c0bb6836721aa5a2d2bed8fb0dc99c","observation_id":"ea107ae0-b41c-4a0b-be57-02ad2e6ad260","resolution":{"observed_at":"2026-08-15T15:53:45.980507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"3281.2870","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:45.531697Z","title":null,"venue":null,"work_id":"a8f1365f-c4b7-4085-a992-a26b1aa7ad0d","year":2024},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.443308Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:2d15abbfb682fcb0cdd8a759472d9148d4a462a1176fa4b502822c19fbdce9d8","observation_id":"1c51ab08-35b0-4cbf-b9f3-bf12b0ac285b","resolution":{"observed_at":"2026-08-15T15:53:45.538529Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.074676Z","title":"We set the window size to","venue":null,"work_id":"052433bd-a316-419f-9e34-28593dd905c5","year":2024},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.404620Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:a380291f5627bb7387b050f8cd2c161ed6862b92696a516b53582de1c1f3b8b0","observation_id":"bc18dde1-93c2-4643-87e3-12ee47c508c7","resolution":{"observed_at":"2026-08-15T15:53:46.078576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.086193Z","title":"We use a window size of","venue":null,"work_id":"471211cc-771a-464e-8dc5-3957136cf66b","year":2024},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.388725Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:9a37ac671b90d3ac274c2e1a8bee963d420d519cd0b05d9488b0eb6cba15a5f5","observation_id":"0b22e4f9-d8eb-4342-bd63-f144fec6462d","resolution":{"observed_at":"2026-08-15T15:53:46.090127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.097053Z","title":"It is pre-trained on a massive corpus for multi-task applications, including anomaly detection","venue":null,"work_id":"2152b5db-1909-46bd-b6ff-9614f6382b24","year":2026},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.349844Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:c2e4146d16051dab735e6146bba1582dddaba602b2be782b2085d0d5d7da199a","observation_id":"6b992313-f18e-44a5-9a16-24207127bd7f","resolution":{"observed_at":"2026-08-15T15:53:46.100649Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.14752","last_updated":"2024-10-18T02:37:14Z","snapshot_observed_at":"2026-08-17T07:14:52.585128Z","submitted_at":"2024-10-18T02:37:14Z","title":"TimeSeriesExam: A time series understanding exam","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.14752","snapshot_observed_at":"2026-08-15T15:53:45.267819Z","title":"Timeseriesexam: A time series understanding exam.arXiv preprint arXiv:2410.14752,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":2000,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.267819Z"},"links":{"cited_paper":"/paper/2410.14752","citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:45c05d3638b22f6ed71d55816254da110ed9f6cb28f752676f55d6ce23f2f238","observation_id":"2cd5de54-06cd-4f97-ab5f-8e89e2fc296b","resolution":{"observed_at":"2026-08-15T15:53:45.267819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07815","last_updated":"2024-11-04T17:42:45Z","snapshot_observed_at":"2026-08-20T06:56:18.647581Z","submitted_at":"2024-03-12T16:53:54Z","title":"Chronos: Learning the Language of Time Series","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07815","snapshot_observed_at":"2026-08-15T15:53:45.179976Z","title":"Chronos: Learning the language of time series.arXiv preprint arXiv:2403.07815,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.179976Z"},"links":{"cited_paper":"/paper/2403.07815","citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:c31224d286cb32e600409b4e7f4c8196f3acc6996f6b750d32f573c758591255","observation_id":"f1c0ddff-69fe-4568-8cde-a857e6816cd9","resolution":{"observed_at":"2026-08-15T15:53:45.179976Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.00415","last_updated":"2025-05-01T09:26:40Z","snapshot_observed_at":"2026-08-21T10:44:12.556795Z","submitted_at":"2025-05-01T09:26:40Z","title":"CICADA: Cross-Domain Interpretable Coding for Anomaly Detection and Adaptation in Multivariate Time Series","version":1},"cited_work":{"arxiv_id":"2505.00415","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.00415","snapshot_observed_at":"2026-08-15T15:53:45.711364Z","title":"CICADA: Cross-Domain Interpretable Coding for Anomaly Detection and Adaptation in Multivariate Time Series","venue":"cs.LG","work_id":"ae0b09ec-5a49-4082-852e-2b94b71b1b7c","year":2025},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.287778Z"},"links":{"cited_paper":"/paper/2505.00415","citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:3ff2b088bb05f73c3c936aebef90c09ded02d613bc78347386b66e74997993ca","observation_id":"d21c82bb-9b65-469c-8068-70aed465a32f","resolution":{"observed_at":"2026-08-15T15:53:45.724779Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09385","last_updated":"2024-10-12T06:35:18Z","snapshot_observed_at":"2026-08-21T14:04:14.980166Z","submitted_at":"2024-10-12T06:35:18Z","title":"Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09385","snapshot_observed_at":"2026-08-15T15:53:45.216190Z","title":"Mamba4cast: Efficient zero-shot time series forecasting with state space models.arXiv preprint arXiv:2410.09385,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.216190Z"},"links":{"cited_paper":"/paper/2410.09385","citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:41278b5943d45d3fd936b05d82e272f33da59edea2501df3ca9e0f0d7bc98b0c","observation_id":"d8ed83fb-7d02-4a6d-85b3-f9b7dcd9a57f","resolution":{"observed_at":"2026-08-15T15:53:45.216190Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:45.272690Z","title":"Tspulse: Dual space tiny pre-trained models for rapid time- series analysis.arXiv preprint arXiv:2505.13033,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.272690Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:0889fe479d0f1ab5a84d4c82a297e2ee2fc34ee57d1453475fab2f94d45eba0a","observation_id":"b9285c32-c4be-4f66-b9c7-8b6e820959d7","resolution":{"observed_at":"2026-08-15T15:53:45.272690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.207873Z","title":"Lof: identifying density-based local outliers","venue":null,"work_id":"810dbf8e-579c-41df-af07-40305eb57937","year":2000},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.248422Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:05f9097283a5bed195206d908138c6d5387b33ecf5a529d649d7c82d1788cd32","observation_id":"626259ec-a06d-49e6-93da-4c8aa709da32","resolution":{"observed_at":"2026-08-15T15:53:46.211642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:53:46.197427Z","title":"Units: A unified multi-task time series model.Advances in Neural Information Processing Systems, 37: 140589–140631,","venue":null,"work_id":"54efc4d3-5dd7-4bfc-b4df-64af6bc1cc63","year":2026},"citing_paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy","version":5},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T15:53:45.276478Z"},"links":{"citing_paper":"/paper/2509.21190"},"observation_digest":"sha256:a744634a81c2b8d83f90c01dc48d8d452ce04f9a63f4deacd1a2fb7f1992612d","observation_id":"6289efcf-8d44-419b-bb45-0c91699fb173","resolution":{"observed_at":"2026-08-15T15:53:46.201119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.21190","last_updated":"2026-05-29T08:39:58Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T07:12:12.725545Z","submitted_at":"2025-09-25T14:05:15Z","title":"Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":2,"verified_fuzzy":20},"total_outbound_references":36},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2509.21190."}