{"as_of":"2026-08-18T12:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:22bfa8ab8adb42e92ced15e1afe7df850bd03876de40ef18f0f4a3c4f76aadbf","coverage":[{"denominator":18,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":18,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:51:22.001700Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2505.11902/citation-record","integrity":"/paper/2505.11902/integrity","json":"/paper/2505.11902/citation-record.json","paper":"/paper/2505.11902"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:51:22.313834Z","title":"Mai-unet: A multi-scale attention interactive network for multivariate long-term time series forecasting","venue":null,"work_id":"1e4d05a8-fced-4cdb-98e1-132ef1c38987","year":2024},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.939757Z"},"links":{"citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:ee031e9be842b5e1393cd3c8c2b16eb8dc47faaa85293694ce3b3f88a9155803","observation_id":"37f94947-7015-4882-9a6c-2d386f43f2f3","resolution":{"observed_at":"2026-08-15T20:51:22.319525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2503.16991","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:51:22.218443Z","title":"Trace: Time series parameter efficient fine-tuning","venue":null,"work_id":"a92b42c9-b6ff-44f4-9b5c-df264b8dd29d","year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.962834Z"},"links":{"citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:e4474b6e7bef641ec6952982ca329f7f347a8d00d759127e2d056af67c5c5f01","observation_id":"73e924ca-6cfa-4e44-b3b6-a3dbae6465b8","resolution":{"observed_at":"2026-08-15T20:51:22.227430Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.11672","last_updated":"2022-10-17T17:01:20Z","snapshot_observed_at":"2026-08-16T17:19:08.844246Z","submitted_at":"2022-02-23T18:23:07Z","title":"Learning Fast and Slow for Online Time Series Forecasting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.11672","snapshot_observed_at":"2026-08-15T20:51:21.971408Z","title":"Learning fast and slow for online time series forecasting","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.971408Z"},"links":{"cited_paper":"/paper/2202.11672","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:38377f9eab3c65b4869340defb60a146c874779850d0d8ed9229f45480c7cfb6","observation_id":"e9bca0be-c7a9-4635-9484-faac0393fdc1","resolution":{"observed_at":"2026-08-15T20:51:21.971408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10726","last_updated":"2021-03-18T17:58:01Z","snapshot_observed_at":"2026-08-16T06:30:33.794820Z","submitted_at":"2020-06-18T17:55:28Z","title":"Tent: Fully Test-time Adaptation by Entropy Minimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10726","snapshot_observed_at":"2026-08-15T20:51:21.980349Z","title":"Tent: Fully test-time adaptation by entropy minimization","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.980349Z"},"links":{"cited_paper":"/paper/2006.10726","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:1fa0bf6c5b8d469efefe63b85b183b97a1814491a72df68e01593ef7650147c4","observation_id":"8fc79008-3fe3-43ba-a15e-485a93f61171","resolution":{"observed_at":"2026-08-15T20:51:21.980349Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07125","last_updated":"2023-05-11T21:47:52Z","snapshot_observed_at":"2026-08-17T15:31:44.957387Z","submitted_at":"2022-02-15T01:43:27Z","title":"Transformers in Time Series: A Survey","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.07125","snapshot_observed_at":"2026-08-15T20:51:21.984849Z","title":"Transformers in time series: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.984849Z"},"links":{"cited_paper":"/paper/2202.07125","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:305988145aa2274fc6f95921e131e97560f1727270e1e1a291e966f37f8f319f","observation_id":"3bc481af-26b6-4ac0-a9df-90ed9fb01655","resolution":{"observed_at":"2026-08-15T20:51:21.984849Z","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":"2026-08-15T20:51:21.992979Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.992979Z"},"links":{"citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:cdc0ae4fff9559c014faeb92f232684d3a84336f56fdbd2bf98664c2049b2403","observation_id":"be0f216b-8730-4a09-ab2d-a4c946e4f2c3","resolution":{"observed_at":"2026-08-15T20:51:21.992979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20810","last_updated":"2024-12-30T09:06:47Z","snapshot_observed_at":"2026-08-15T07:52:59.758574Z","submitted_at":"2024-12-30T09:06:47Z","title":"TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.20810","snapshot_observed_at":"2026-08-15T20:51:21.997274Z","title":"Timeraf: Retrieval-augmented foundation model for zero-shot time series forecasting","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.997274Z"},"links":{"cited_paper":"/paper/2412.20810","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:d1f7ccc2dce940da9d9ed471344c60aedd5391bc585ae1327b6b24996afe5f9e","observation_id":"20e586ac-b827-4b3a-86c7-6b1ea9b08787","resolution":{"observed_at":"2026-08-15T20:51:21.997274Z","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":"2026-08-15T20:51:22.289243Z","title":"By definition, the dynamic hypothesis space is the union over time: Hdyn = [ t∈[0,T] Vt = K[ i=1 Fi, whereFi :=S t∈[ti−1,ti)Vt denotes the function class active in segmenti","venue":null,"work_id":"8aad00c4-686e-4721-be7d-8ff2515d2cf8","year":2012},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:22.001700Z"},"links":{"citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:ed5c4eaa1a861a055ba672a2ce0adcbde275ee003c95294e0cd6d1573d80f1cb","observation_id":"44403c5b-298d-4b21-b327-c192d0675590","resolution":{"observed_at":"2026-08-15T20:51:22.294501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.02999","last_updated":"2018-10-22T16:11:14Z","snapshot_observed_at":"2026-08-14T19:38:16.450214Z","submitted_at":"2018-03-08T08:29:38Z","title":"On First-Order Meta-Learning Algorithms","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.02999","snapshot_observed_at":"2026-08-15T20:51:21.966744Z","title":"On first-order meta-learning algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.966744Z"},"links":{"cited_paper":"/paper/1803.02999","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:52df3bf03eaf71c6004ec0a275342f0a27d4141936f7744feaf656fead573fa5","observation_id":"7664b5da-2713-4d1b-bf77-f63409266022","resolution":{"observed_at":"2026-08-15T20:51:21.966744Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.01669","last_updated":"2025-04-04T21:40:47Z","snapshot_observed_at":"2026-08-18T07:54:16.063711Z","submitted_at":"2025-03-03T15:42:06Z","title":"An Efficient Continual Learning Framework for Multivariate Time Series Prediction Tasks with Application to Vehicle State Estimation","version":2},"cited_work":{"arxiv_id":"2503.01669","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.01669","snapshot_observed_at":"2026-08-15T20:51:22.266323Z","title":"An Efficient Continual Learning Framework for Multivariate Time Series Prediction Tasks with Application to Vehicle State Estimation","venue":"cs.LG","work_id":"7482c669-5707-48dd-9285-4f132558e676","year":2025},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.944455Z"},"links":{"cited_paper":"/paper/2503.01669","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:d3f31e74f3088fd922b30ec61033460a6a88bfe1b549ddc187d66b221e828fba","observation_id":"b9603a38-0bd4-4731-a568-1b1211ad8c43","resolution":{"observed_at":"2026-08-15T20:51:22.270566Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.05098","last_updated":"2017-06-15T21:38:12Z","snapshot_observed_at":"2026-08-13T21:53:02.384757Z","submitted_at":"2017-06-15T21:38:12Z","title":"An Overview of Multi-Task Learning in Deep Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.05098","snapshot_observed_at":"2026-08-15T20:51:21.976045Z","title":"An overview of multi-task learning in deep neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.976045Z"},"links":{"cited_paper":"/paper/1706.05098","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:5398333f6eaedcde7714f0963d2306d3fc606b47f27d8f319066226cd37f7927","observation_id":"d337f313-d371-4602-87f5-fe7049f90f83","resolution":{"observed_at":"2026-08-15T20:51:21.976045Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-08-12T12:37:28.207761Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-15T20:51:21.958117Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.958117Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:7fc87291ddaf456dab4876a31811e7c6f2e5e987e8826d6324f91cfe1156b1aa","observation_id":"1925d21e-8824-4188-813c-dbf5e100450c","resolution":{"observed_at":"2026-08-15T20:51:21.958117Z","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":"2026-08-15T20:51:21.924827Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.924827Z"},"links":{"citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:4c0de9e14e9d6d8240a50680a0f6a5f90efeff294e61355cf59325cc68910b0d","observation_id":"8fd847cd-c725-4ef3-8d17-ba97a6c72438","resolution":{"observed_at":"2026-08-15T20:51:21.924827Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-17T18:04:53.578114Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-15T20:51:21.949213Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.949213Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:03917c5e06bb90eb0fb579c9482d4850477500c9480f3afe89787c0d8292f3fd","observation_id":"5b879605-eba4-4681-a0e6-6e9f78ac83ad","resolution":{"observed_at":"2026-08-15T20:51:21.949213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12672","last_updated":"2025-01-13T20:42:06Z","snapshot_observed_at":"2026-08-16T13:08:45.715375Z","submitted_at":"2024-10-16T15:36:13Z","title":"Context Matters: Leveraging Contextual Features for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12672","snapshot_observed_at":"2026-08-15T20:51:21.929527Z","title":"Chinchali","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.929527Z"},"links":{"cited_paper":"/paper/2410.12672","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:e18a5cc58391eddd0895d89a1f8cc8915ab38bc63f4ac271f2786c02fb6f29b6","observation_id":"1b581287-8e92-4577-a26e-c3b1a203c888","resolution":{"observed_at":"2026-08-15T20:51:21.929527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.13041","last_updated":"2025-05-20T07:40:13Z","snapshot_observed_at":"2026-08-16T02:04:38.459254Z","submitted_at":"2025-01-22T17:40:17Z","title":"TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.13041","snapshot_observed_at":"2026-08-15T20:51:21.953227Z","title":"Timefilter: Patch-specific spatial-temporal graph filtration for time series forecasting","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.953227Z"},"links":{"cited_paper":"/paper/2501.13041","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:d1bd7b39c839cae7cfe0e3cc868ddf43e6424b3e7ec1e8dd33181afe8daf2915","observation_id":"7be5bdde-52c0-4c56-8094-d9ece4fe3912","resolution":{"observed_at":"2026-08-15T20:51:21.953227Z","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":"2026-08-15T20:51:22.302338Z","title":"Kernel-u-net: Mul- tivariate time series forecasting using custom kernels","venue":null,"work_id":"948cab58-2941-4178-8015-a8cdaa6d9d34","year":2024},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.988874Z"},"links":{"citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:a4e5cf7d492f9959150f6906ebf9dccfdad86a60b1dee7fdc3e91a4c87fdf223","observation_id":"9af5aea5-65e5-4315-9e47-54842a5a64f2","resolution":{"observed_at":"2026-08-15T20:51:22.306326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12672","last_updated":"2025-01-13T20:42:06Z","snapshot_observed_at":"2026-08-16T13:08:45.715375Z","submitted_at":"2024-10-16T15:36:13Z","title":"Context Matters: Leveraging Contextual Features for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12672","snapshot_observed_at":"2026-08-15T20:51:21.934229Z","title":"URL https: //doi.org/10.48550/arXiv.2410.12672","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T20:51:21.934229Z"},"links":{"cited_paper":"/paper/2410.12672","citing_paper":"/paper/2505.11902"},"observation_digest":"sha256:a93be6d7dc9bb7abc7047c4603d73a9db83ba3e82b5cf67a6c04112e69bc93e3","observation_id":"f1c6f1dd-ca5e-4a4a-8ef5-7f73904e41ff","resolution":{"observed_at":"2026-08-15T20:51:21.934229Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.11902","last_updated":"2025-05-17T08:33:57Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T19:37:27.876603Z","submitted_at":"2025-05-17T08:33:57Z","title":"Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series"},"reference_resolution":{"displayed":18,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":2,"verified_fuzzy":3},"total_outbound_references":18},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2505.11902."}