{"as_of":"2026-08-19T22:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b628bced6e002569ab1da51d958962313b0ee853eed08dcf0ad0f34e65d62cd7","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T22:02:51.907844Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2603.12916/citation-record","integrity":"/paper/2603.12916/integrity","json":"/paper/2603.12916/citation-record.json","paper":"/paper/2603.12916"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.16204","last_updated":"2025-08-22T08:24:02Z","snapshot_observed_at":"2026-08-15T21:16:37.607100Z","submitted_at":"2025-08-22T08:24:02Z","title":"Competition and Attraction Improve Model Fusion","version":1},"cited_work":{"arxiv_id":"2508.16204","doi":"10.48550/arxiv.2508.16204","metadata_source":"pith","pith_arxiv_id":"2508.16204","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"Competition and Attraction Improve Model Fusion","venue":"cs.AI","work_id":"3ac8d521-9c6b-4f6a-adeb-5a7c1de18c21","year":2025},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2508.16204","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:f558134c00cc9dfa1be1b17f74a52e300e52bb91fe88df1ab21569866e0dac58","observation_id":"a607b5f8-655a-47e2-8f26-3dc7d4b79347","resolution":{"observed_at":"2026-07-14T22:10:48.767648Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.08243","last_updated":"2023-04-13T17:59:37Z","snapshot_observed_at":"2026-08-16T16:01:20.302377Z","submitted_at":"2023-01-19T18:59:01Z","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.08243","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"https://doi.org/10.48550/arXiv.2301.08243, http://arxiv.org/ abs/2301.08243","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2301.08243","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:bbea281436d74b39f63e8d55ea6882db9606155f18054243a8b0388c8d79c36e","observation_id":"952fbc39-8d54-452a-8d14-aa50090e047a","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":"In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Min- ing","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:e59b6c285883f05076435ac9c057c502a85a8987276a86188ee24c218698b178","observation_id":"709dd53c-d8cf-44d4-8c8f-c131340985d2","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-08-15T04:53:45.483331Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"org/abs/1607.06450","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:1949255d5e8467ce3056f44157d2ce85ac2eadd532c264f9729042cc0a249e16","observation_id":"4dadb95c-87fb-4a20-bdf8-163e6db885ea","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.08544","last_updated":"2025-11-14T08:38:32Z","snapshot_observed_at":"2026-08-18T08:21:10.395771Z","submitted_at":"2025-11-11T18:21:55Z","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.08544","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"https://doi.org/10.48550/arXiv.2511.08544, http:// arxiv.org/abs/2511.08544","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2511.08544","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:860c7911dc3a27264f4ac8406e88d23c09d35486f738f3079f2418004aa93bc8","observation_id":"5ebeb192-db3c-49bd-846f-a4b90e9dd3d3","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:9fe0d7238f1218c7a4cf2685f9fd7992c01c88926fe19b171ccab4022192fb01","observation_id":"f59afab7-fc05-4128-9a6a-9e6721900dc3","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":"https://doi.org/10.1145/335191.335388, https://dl.acm.org/doi/10.1145/335191.335388 Predictable Query Dynamics for Time Series Anomaly Detection 15","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:9e28f0fc3f43e0231fda918199d3431902f971c787ffe9b1c044cb3904e0b3e3","observation_id":"9cc42358-ed35-43e5-b676-11f44fe35bcf","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":null,"venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:37211f4ffb4c9d7a96e99b5d40f909b65e4c9c9447b10d5c580c10603b8b4295","observation_id":"1e0bbb61-0e63-4e52-8f14-4b2395476b6c","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":"In: 2018 IEEE/CVF Conference on Com- puter Vision and Pattern Recognition","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:5dc18c35b8d8d2b2f53e9ce93c8dd3a4a724a7a8ab7ece16f65459b82fd2de44","observation_id":"45103419-ce49-4bc5-8993-39e9c03ee447","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"10.5220/0012163100003595","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Proceedings of the 15th International Joint Conference on Computational Intelligence","venue":null,"work_id":"2f692842-f0d8-4b97-829b-1f712523189b","year":2023},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:a0604e14cd40d4755310fd0759c234d064496a55853ce894fe41dedd0a0c9515","observation_id":"859eb009-ec42-4a16-8687-e8b19131f169","resolution":{"observed_at":"2026-07-14T22:10:48.856952Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"IEEE Transactions on Information Theory13(1), 21–27 (January 1967).https://doi.org/10.1109/TIT","venue":null,"work_id":null,"year":1967},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:738db319565892d0daa8499991383b9449227dadbca0fcd00bc94a7769ac1158","observation_id":"d824f529-5e42-4b7a-a832-fc87c0099742","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.06947","last_updated":"2021-06-13T09:07:30Z","snapshot_observed_at":"2026-08-16T18:17:32.712718Z","submitted_at":"2021-06-13T09:07:30Z","title":"Graph Neural Network-Based Anomaly Detection in Multivariate Time Series","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.06947","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2106.06947","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:70e598c0543b1e4e0180131902473fe0f84e493fd39e04954b2559393eb7608a","observation_id":"acdc9c14-1724-482a-b508-735722db79df","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:258e8818c3bc0a8feb74898b7c02be6ed948ae128e533eb4165d382f78fc069b","observation_id":"9f3bb5a4-fbc0-4db8-81cd-5c7815cf604a","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.07733","last_updated":"2020-09-10T09:46:02Z","snapshot_observed_at":"2026-08-14T05:53:12.800111Z","submitted_at":"2020-06-13T22:35:21Z","title":"Bootstrap your own latent: A new approach to self-supervised Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.07733","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2006.07733","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:0a2a079f569016740679625d02c362140f456c3c3b341a8fac070d436e260e44","observation_id":"60da1ac1-6a2b-4c98-905a-3e9857fa91ab","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":"IEEE Trans- actions on Knowledge and Data Engineering33(4), 1479–1489 (Apr 2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:712c864753d7abf96f25185fb226c45ee905fe5ea5ef4bd4db059645991db63a","observation_id":"d453435b-0a12-4346-a946-3b5e33702cd6","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":"Pat- tern Recognition Letters24(9), 1641–1650 (2003)","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:85a22ec79e8ce615bbd1f312b443ab2a455b8a3db431a418ae1d15cd7d51061c","observation_id":"d4ba8270-1dfd-4173-af69-aa27332faff5","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.05267","last_updated":"2016-11-16T13:19:19Z","snapshot_observed_at":"2026-08-14T21:30:09.436235Z","submitted_at":"2016-11-16T13:19:19Z","title":"Temporal Convolutional Networks for Action Segmentation and Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.05267","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"CoRRabs/1611.05267(2016), http://arxiv.org/abs/1611.05267","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/1611.05267","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:b6ff709d15788729eec65ed432ecf86e019c84dc27ec7a33e900fb31b1afafd6","observation_id":"abe04b24-9eac-4f3d-af7f-66613d3f0634","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2020.298074","doi":"10.1109/tnnls.2020.2980749","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"IEEE Trans- actions on Neural Networks and Learning Systems32(3), 1177–1191 (Mar 2021)","venue":"IEEE Transactions on Neural Networks and Learning Systems","work_id":"4d1f5d0a-f2e1-417b-9468-9721ac6ca2dc","year":2021},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:ef8eddb0b0597fde140bd3e6a66f97bb187d73b1b70cd7e31a2634d802fc0a22","observation_id":"1986b4d2-9d8e-43bf-8a62-7fcd3f802342","resolution":{"observed_at":"2026-07-14T22:10:48.819761Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.09463","last_updated":"2020-09-20T16:06:39Z","snapshot_observed_at":"2026-08-09T02:35:54.414586Z","submitted_at":"2020-09-20T16:06:39Z","title":"COPOD: Copula-Based Outlier Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.09463","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"https://doi.org/10.48550/arXiv.2009.09463, http://arxiv.org/abs/ 2009.09463","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2009.09463","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:ad58bc60306dac7791b2c1acd356feab1487c558fb2e6eae45b37fb66f7ef121","observation_id":"15be2462-4916-40b6-8080-0fe2230e80d1","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":"International Jour- nal of Forecasting37(4), 1748–1764 (Oct 2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:d6efa2ad56a9953cee651ba524f6245257ded35bea695a8ebb7b07b0c698eb67","observation_id":"4cac205b-8534-453b-9fe9-dfb1caff3fa3","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-07-14T22:02:51.907844Z","title":"In: 2008 Eighth IEEE In- ternational Conference on Data Mining","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:3a033b7ceb66c897caca15b1603cd24e5e6cbc25e0ab5fd808130b3879da4b19","observation_id":"2b6873cd-f683-4f35-8fac-2e325352283b","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":"In: Advances in Neural Information Processing Systems 37","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:0ba80ccdae4c5f95451cc5af8582df86ef7e0051728c297c34ef1abbc50a4886","observation_id":"47f8d9b5-2301-41f4-85f9-c3019d354d82","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:198ddd0544bae4b110bd3fc04d700e84d234bc0844b44de5f1d0a5a4a18f552c","observation_id":"97ccf8fc-53c0-47d6-aafe-b89fcdb3ccde","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:4448aa3f2bee54cf2c9357f4604f8a4fd9c1b4a1a350bcd1b903267b5b87d970","observation_id":"2ee40161-4ba3-4849-be06-666a7500bacc","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":"Proceedings of the VLDB Endowment15(11), 2774–2787 (Jul 2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:24395380944dffd85e5d3322af5122e0b1a2f0966e227ed52ff7a28bfa9f1ea3","observation_id":"16c52192-6062-4383-81e2-746344a3d5b3","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":"In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:e4dc78e46903bed88f44bddc8261cadef4a6e2183371fc61b9ed542704955c1e","observation_id":"eee52783-db6b-4536-9e6e-539491647744","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2019.101395","doi":"10.1504/ijdmb.2019.101395","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"International Journal of Data Mining and Bioinfor- matics22(4), 389 (2019)","venue":"International Journal of Data Mining and Bioinformatics","work_id":"2c26dc23-4884-4904-8ab7-919a057df848","year":2019},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:de998fb82c0233a58d3474edbaf1411cbac7dcbb67c4866872440ac3ddaf866e","observation_id":"25b7bb29-1b66-437f-b135-66696cd4837d","resolution":{"observed_at":"2026-07-14T22:10:48.774545Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:ed59122b0e66d17a6b3d312568ae32e1e940e769caa3183dbcde5ebc56506406","observation_id":"6219fd12-b117-4d54-8e0b-4a2f0d975d0e","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.07284","last_updated":"2022-05-14T15:21:54Z","snapshot_observed_at":"2026-08-16T17:27:30.640616Z","submitted_at":"2022-01-18T19:41:29Z","title":"TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.07284","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"https://doi.org/10.48550/arXiv.2201.07284, http://arxiv.org/abs/ 2201.07284, arXiv:2201.07284","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2201.07284","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:6d00f68cce4e5885ab4fdc7bedc6820071d32e648330cd9e846028a6c3319ebb","observation_id":"a33af0a5-2626-4274-ae47-09b2ce2e68c0","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":"In: Proceedings of the 31st International Conference on Neural Information Processing Systems","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:90141e469fd0a16d75e166ff247eb5083d6e2ba7ff9d8ba748e9072eab76326a","observation_id":"e9a46cb9-40d5-432e-bfa7-a0d614f58040","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2021.104354","doi":"10.1016/j.engappai.2021.104354","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Engineering Applications of Artificial Intelligence 104, 104354 (Sep 2021)","venue":"Engineering Applications of Artificial Intelligence","work_id":"a4bd0985-0646-4e06-934a-f2cb22ed3427","year":2021},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:e95b2328ce7d6087ace6513fe6d690f39935a937d8a1be74f26e7b5c21c27d33","observation_id":"26d15d44-9c65-492c-9f2f-bba390112024","resolution":{"observed_at":"2026-07-14T22:10:48.812826Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02186","last_updated":"2023-04-12T02:34:03Z","snapshot_observed_at":"2026-08-17T15:00:57.936069Z","submitted_at":"2022-10-05T12:19:51Z","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02186","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"https://doi.org/10.48550/arXiv.2210.02186, http://arxiv.org/abs/ 2210.02186, arXiv:2210.02186 Predictable Query Dynamics for Time Series Anomaly Detection 17","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2210.02186","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:332542937de76faf86d0d827ba9507264d11b4420875acbfa046e10b1222141a","observation_id":"3aa00573-c4c3-4ef4-a4d9-3d378662e0a2","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.03903","last_updated":"2018-02-12T06:23:04Z","snapshot_observed_at":"2026-08-14T19:46:57.230166Z","submitted_at":"2018-02-12T06:23:04Z","title":"Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.03903","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"48550/arXiv.1802.03903, http://arxiv.org/abs/1802.03903, arXiv:1802.03903","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/1802.03903","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:21305655a8d1ee999a68ebb0d46539e9e5f70e44692c9e6625d4a2eeb2fa671e","observation_id":"26b6681b-433b-442f-b13f-528bfba11c5c","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2110.02642","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:f881823c1d3c5a2e08490a2f8fab07e40ed5eb498bffd0ba97c1b2f3089ce54d","observation_id":"ccda3df8-24fd-4622-81a6-87410f7c52d7","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03756","last_updated":"2024-01-05T06:49:04Z","snapshot_observed_at":"2026-08-19T19:46:33.050752Z","submitted_at":"2023-07-06T15:01:58Z","title":"FITS: Modeling Time Series with $10k$ Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03756","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2307.03756","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:35475688b463c255de5095d1e6e127bdfe7583d96161a8266dd334ede8991662","observation_id":"3843aa8d-458a-4719-884d-030ee267132d","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","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":"2026-07-14T22:02:51.907844Z","title":null,"venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:5f11cacc422dc3f916652f635519c57165142eeed577cc21d5c98c6dfacc1093","observation_id":"0e070967-4ef9-427b-8652-bf73b0df8a2c","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11939","last_updated":"2023-10-15T05:07:17Z","snapshot_observed_at":"2026-08-16T15:53:17.363089Z","submitted_at":"2023-02-23T11:37:39Z","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11939","snapshot_observed_at":"2026-07-14T22:02:51.907844Z","title":"Mean± standard deviation over all evaluated series","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-14T22:02:51.907844Z"},"links":{"cited_paper":"/paper/2302.11939","citing_paper":"/paper/2603.12916"},"observation_digest":"sha256:33a0c4e362e4bb0aa41ce981e3dd2646e618d4f53ba889d50d3f8455c59c14eb","observation_id":"9e79aa33-cf4f-4e7a-b2f5-b34c9013e5ff","resolution":{"observed_at":"2026-07-14T22:02:51.907844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.12916","last_updated":"2026-05-28T21:42:50Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T21:15:49.816394Z","submitted_at":"2026-03-13T11:40:51Z","title":"Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":5,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":27,"verified_exact":4,"verified_fuzzy":0},"total_outbound_references":37},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2603.12916."}