{"as_of":"2026-08-08T20:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2c3b8414bd1d5a22294f6728bad1c7a3cf050d7c019293461506a25d18718177","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":35,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:16:59.107256Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":122,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2305.10721","last_updated":"2026-05-17T02:25:14Z","snapshot_observed_at":"2026-08-03T04:41:00.104637Z","submitted_at":"2023-05-18T05:39:46Z","title":"Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-24T08:31:08.898349Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2305.10721"},"observation_digest":"sha256:2b11047c91e17a6408b1609ed33f9a255f250677f9c0eac4abc92758f93b2b36","observation_id":"b5e8a7da-58d0-4d74-a1a3-296c3c5273ab","resolution":{"observed_at":"2026-05-24T08:34:11.877283Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2310.10688","last_updated":"2024-04-17T18:24:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-14T17:01:37Z","title":"A decoder-only foundation model for time-series forecasting","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-16T18:07:21.246053Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2310.10688"},"observation_digest":"sha256:fd281fbf95aa0b45fd6ed40bdd0d7c3895ca9afe2154d72c4a0f67f1fd1940fd","observation_id":"2ea59cf9-6491-4699-b036-233628fe7556","resolution":{"observed_at":"2026-05-16T18:07:21.272001Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2407.13278","last_updated":"2026-05-04T08:07:42Z","snapshot_observed_at":"2026-07-06T18:48:20.902620Z","submitted_at":"2024-07-18T08:31:55Z","title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","version":3},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-05-23T23:03:45.096751Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2407.13278"},"observation_digest":"sha256:3cf85a83f44605617d49145446b47aec62d43b1f588d1174f1f9a48143623822","observation_id":"5593e975-0c74-4566-9b85-17362cacb14d","resolution":{"observed_at":"2026-05-23T23:05:51.489070Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2505.16786","last_updated":"2026-05-16T12:46:24Z","snapshot_observed_at":"2026-08-02T17:32:20.274118Z","submitted_at":"2025-05-22T15:28:47Z","title":"FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecasting","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-22T13:41:26.675038Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2505.16786"},"observation_digest":"sha256:f0929e15893e2b9f19042125daab226953c9a4658cc80f3795cdcdb91b86c128","observation_id":"67e57592-4f10-48b3-a77d-633235bec11b","resolution":{"observed_at":"2026-05-22T13:41:36.157975Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-07T12:16:59.107256Z","title":"O., and Pfis- ter, T","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00188","last_updated":"2026-06-04T04:48:12Z","snapshot_observed_at":"2026-08-08T10:13:09.091247Z","submitted_at":"2025-05-30T19:56:54Z","title":"Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time Series","version":2},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-07T12:16:59.107256Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2506.00188"},"observation_digest":"sha256:79e953a166f3be948857ed73b969a3b14849c2e1125fc8c859aaa3fb4375b34e","observation_id":"9f9f4a5b-a5be-4ed6-a79a-391ea5f77e07","resolution":{"observed_at":"2026-08-07T12:16:59.107256Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-07T05:29:03.484104Z","title":"Tsmixer: An all-mlp architecture for time series forecasting","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07920","last_updated":"2025-06-09T16:33:29Z","snapshot_observed_at":"2026-08-07T09:21:43.318215Z","submitted_at":"2025-06-09T16:33:29Z","title":"W4S4: WaLRUS Meets S4 for Long-Range Sequence Modeling","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T05:29:03.484104Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2506.07920"},"observation_digest":"sha256:e46b777f52759b3c415211cdf346445dc7f026249ee01a76ca679a94c93ad6cc","observation_id":"6f63de68-2003-4aff-b604-1df42af538dd","resolution":{"observed_at":"2026-08-07T05:29:03.484104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-07T00:47:52.026626Z","title":"Tsmixer: An all-mlp architecture for time series forecasting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12696","last_updated":"2025-06-15T02:53:25Z","snapshot_observed_at":"2026-08-08T00:02:50.094552Z","submitted_at":"2025-06-15T02:53:25Z","title":"TFKAN: Time-Frequency KAN for Long-Term Time Series Forecasting","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T00:47:52.026626Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2506.12696"},"observation_digest":"sha256:a7ea0b01d24583bc04174e41061b842cbab04723aa741015d3254fb3a4676b11","observation_id":"8df96d46-ea34-46fd-b0bb-1575bf94c16a","resolution":{"observed_at":"2026-08-07T00:47:52.026626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-06T21:25:22.672473Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.01067","last_updated":"2025-06-30T23:59:12Z","snapshot_observed_at":"2026-08-07T15:16:03.377679Z","submitted_at":"2025-06-30T23:59:12Z","title":"Evaluation of a Foundational Model and Stochastic Models for Forecasting Sporadic or Spiky Production Outages of High-Performance Machine Learning Services","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T21:25:22.672473Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2507.01067"},"observation_digest":"sha256:483c251bc14d8313357132cd7407718e74f8c3e1eafe9de2d8aead3100d5919e","observation_id":"03452e7f-8d0f-44d8-af65-471a0595618e","resolution":{"observed_at":"2026-08-06T21:25:22.672473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-06T19:52:02.701611Z","title":"Tsmixer: An all-mlp architecture for time series forecasting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04381","last_updated":"2025-07-06T12:58:52Z","snapshot_observed_at":"2026-08-07T19:24:20.635724Z","submitted_at":"2025-07-06T12:58:52Z","title":"DC-Mamber: A Dual Channel Prediction Model based on Mamba and Linear Transformer for Multivariate Time Series Forecasting","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T19:52:02.701611Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2507.04381"},"observation_digest":"sha256:6ef1082fab252c8c0a266d079f5422e275156c2ce01e37c68151c405d30f3d69","observation_id":"81021648-e7e1-4f2c-8142-3a1593fdec57","resolution":{"observed_at":"2026-08-06T19:52:02.701611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-06T19:26:46.553377Z","title":"Arik, and Tomas Pfis- ter","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.05753","last_updated":"2025-07-08T07:57:08Z","snapshot_observed_at":"2026-08-07T05:27:15.719764Z","submitted_at":"2025-07-08T07:57:08Z","title":"Jigsaw: Training Multi-Billion-Parameter AI Weather Models with Optimized Model Parallelism","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T19:26:46.553377Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2507.05753"},"observation_digest":"sha256:dd00ae56a583585ca02dbdb31f120a9486a56db401b6a2187413ab21dab67f18","observation_id":"2150dc04-31ca-40a9-9748-bd3f458e3812","resolution":{"observed_at":"2026-08-06T19:26:46.553377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-06T18:01:24.969257Z","title":"Tsmixer: An all-mlp architecture for time series forecasting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09445","last_updated":"2025-08-02T05:17:13Z","snapshot_observed_at":"2026-08-08T07:36:39.888730Z","submitted_at":"2025-07-13T01:45:27Z","title":"Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:01:24.969257Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2507.09445"},"observation_digest":"sha256:f80a7b917caca0127c9cd378d38b253938190050c5cbd4c3aa7e0f1b593555b9","observation_id":"3a526238-4d2b-4ba5-9a82-0b4632d95471","resolution":{"observed_at":"2026-08-06T18:01:24.969257Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-06T16:54:08.324626Z","title":"O., Yoder, N","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.12331","last_updated":"2025-07-16T15:24:06Z","snapshot_observed_at":"2026-08-08T16:26:33.031332Z","submitted_at":"2025-07-16T15:24:06Z","title":"Causality analysis of electricity market liberalization on electricity price using novel Machine Learning methods","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T16:54:08.324626Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2507.12331"},"observation_digest":"sha256:f10600719320d4b92dfd74251824e29a4fc9973aa1191ddea69e69b12c6dc325","observation_id":"ca4623f6-98ac-471c-9186-cbac5cfc7eba","resolution":{"observed_at":"2026-08-06T16:54:08.324626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-06T16:42:56.791873Z","title":"Tsmixer: An all-mlp architecture for time series fore- casting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.12803","last_updated":"2025-07-17T05:39:15Z","snapshot_observed_at":"2026-08-08T14:47:59.438288Z","submitted_at":"2025-07-17T05:39:15Z","title":"FLDmamba: Integrating Fourier and Laplace Transform Decomposition with Mamba for Enhanced Time Series Prediction","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T16:42:56.791873Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2507.12803"},"observation_digest":"sha256:bcf25d8f1d95e880f5b52fb011213ea14c0ff28e5d185bb64db78b5995c1717b","observation_id":"579f4e3e-c4ce-4956-a0ed-0fb3d9799c3d","resolution":{"observed_at":"2026-08-06T16:42:56.791873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-06T11:05:12.870087Z","title":"Tsmixer: An all-mlp architecture for time series forecasting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.00037","last_updated":"2025-07-31T01:24:01Z","snapshot_observed_at":"2026-08-06T11:05:06.034184Z","submitted_at":"2025-07-31T01:24:01Z","title":"Predicting Large-scale Urban Network Dynamics with Energy-informed Graph Neural Diffusion","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T11:05:12.870087Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2508.00037"},"observation_digest":"sha256:d6d9606086edd50cfa2922c1b59b7938781268cbb010bc0e5dfe91557951d564","observation_id":"750dd503-b963-48fc-bbd2-87684b5120a5","resolution":{"observed_at":"2026-08-06T11:05:12.870087Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-06T05:14:36.465269Z","title":"TSmixer: An all-MLP architecture for time series forecasting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.02161","last_updated":"2025-08-04T08:03:01Z","snapshot_observed_at":"2026-08-07T22:31:42.946645Z","submitted_at":"2025-08-04T08:03:01Z","title":"User Trajectory Prediction Unifying Global and Local Temporal Information","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T05:14:36.465269Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2508.02161"},"observation_digest":"sha256:7c00ad9d6fd5c6f06eeace0f77628e4e93e816345ed827a70a7d80236c15d14c","observation_id":"fd11e854-4d90-4a35-9905-93e50512c727","resolution":{"observed_at":"2026-08-06T05:14:36.465269Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-06T04:33:16.141587Z","title":"Capistr´an, C.; Constandse, C.; and Ramos-Francia, M","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.09159","last_updated":"2025-08-21T12:56:00Z","snapshot_observed_at":"2026-08-06T04:33:08.772671Z","submitted_at":"2025-08-05T12:17:03Z","title":"Agoran: An Agentic Open Marketplace for 6G RAN Automation","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T04:33:16.141587Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2508.09159"},"observation_digest":"sha256:0e66a16f328504b51dc37f669d274ca93b21eb1cb8e5c991e0202f2d97550c23","observation_id":"22b42d72-513f-42c1-b5cf-7b7b71937b1a","resolution":{"observed_at":"2026-08-06T04:33:16.141587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T20:58:01.334939Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.09753","last_updated":"2025-08-13T12:34:15Z","snapshot_observed_at":"2026-08-05T20:57:59.525987Z","submitted_at":"2025-08-13T12:34:15Z","title":"TriForecaster: A Mixture of Experts Framework for Multi-Region Electric Load Forecasting with Tri-dimensional Specialization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T20:58:01.334939Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2508.09753"},"observation_digest":"sha256:447e3812605f15ab1fc76eda9d1e937ff588f90c2d672613f13a49981e750886","observation_id":"fef925fa-58a6-47e7-ba12-431ec2406789","resolution":{"observed_at":"2026-08-05T20:58:01.334939Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-04T16:45:00.188736Z","title":"Tsmixer: An all-mlp architecture for time series forecasting","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.12196","last_updated":"2026-05-23T18:24:30Z","snapshot_observed_at":"2026-08-04T16:44:58.619159Z","submitted_at":"2025-09-15T17:56:15Z","title":"Dynamic Relational Priming Improves Transformer in Multivariate Time Series","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T16:45:00.188736Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2509.12196"},"observation_digest":"sha256:4d82adbd8e6ff11766325b59db386af6bb3160b8ac9920113a4ed818489dc410","observation_id":"5a21ea7f-2301-4098-b2c0-aeb673913b79","resolution":{"observed_at":"2026-08-04T16:45:00.188736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2509.14000","last_updated":"2026-04-28T11:22:58Z","snapshot_observed_at":"2026-07-06T22:30:07.020487Z","submitted_at":"2025-09-17T14:12:36Z","title":"JaGuard: Position Error Correction of GNSS Jamming with Deep Temporal Graphs","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-18T16:00:42.688653Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2509.14000"},"observation_digest":"sha256:860581e7559cc3219500aac5f7c3cf37a8cef7c07803f9a460bd169f1d2aa1f0","observation_id":"29c994ac-38c5-43a6-9985-635e24d3809b","resolution":{"observed_at":"2026-05-18T16:01:34.523690Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-03T22:36:43.074456Z","title":"Tsmixer: An all-mlp architecture for time series forecasting.arXiv preprint arXiv:2303.06053,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.09789","last_updated":"2026-06-10T10:00:58Z","snapshot_observed_at":"2026-08-06T13:39:41.543118Z","submitted_at":"2025-11-12T22:43:40Z","title":"CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T22:36:43.074456Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2511.09789"},"observation_digest":"sha256:36e06a2d847cfb8446af40134807ee9b6d58fee8be17551eeecf2ac598f3ec3e","observation_id":"c1f77b1b-f0c7-4ffc-944e-73a48633c6ef","resolution":{"observed_at":"2026-08-03T22:36:43.074456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-03T20:11:31.158916Z","title":"Arik, and Tomas Pfister","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.07854","last_updated":"2026-06-29T03:12:06Z","snapshot_observed_at":"2026-08-03T20:11:29.399800Z","submitted_at":"2025-11-26T07:16:47Z","title":"HieraMix: A Hierarchical MLP-Mixer for Large-Scale Traffic Forecasting","version":2},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-03T20:11:31.158916Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2512.07854"},"observation_digest":"sha256:0d2d28357b48bff48287312c409570ebe5a9a9bc667c079e9886183e47f04ac1","observation_id":"d793dab4-dbe8-4fff-b147-9fce547ae931","resolution":{"observed_at":"2026-08-03T20:11:31.158916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-02T22:40:03.291831Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.16220","last_updated":"2026-06-25T10:07:31Z","snapshot_observed_at":"2026-08-06T06:58:14.490546Z","submitted_at":"2026-02-18T06:53:32Z","title":"SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T22:40:03.291831Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2602.16220"},"observation_digest":"sha256:f7ee5c7544d056743451f169cf396b64b42a02cbc8eb5dc02a0af8b44adda884","observation_id":"9b6765f9-9be6-4343-94ac-0ae5be40c686","resolution":{"observed_at":"2026-08-02T22:40:03.291831Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-02T22:41:30.477774Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.16224","last_updated":"2026-06-07T08:19:06Z","snapshot_observed_at":"2026-08-06T11:33:36.184893Z","submitted_at":"2026-02-18T06:59:05Z","title":"Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T22:41:30.477774Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2602.16224"},"observation_digest":"sha256:923d75e5897a3f82e3e222ee8902f3c878c27bf8eb5816970e8edf429d0a017a","observation_id":"7ef1af5e-1ea3-48a4-bd6f-aafede0ba4e3","resolution":{"observed_at":"2026-08-02T22:41:30.477774Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2604.26762","last_updated":"2026-04-29T14:57:21Z","snapshot_observed_at":"2026-08-02T13:06:11.110145Z","submitted_at":"2026-04-29T14:57:21Z","title":"Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-07T10:58:36.216692Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2604.26762"},"observation_digest":"sha256:e2296eb586f31b8aac16f3ae9c0e1016f73ca62eb9d3c56257aee6f823b16d86","observation_id":"bbc2e7e5-f6b1-460f-8d56-16a74979e361","resolution":{"observed_at":"2026-05-12T09:26:25.890400Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2605.13678","last_updated":"2026-05-13T15:36:46Z","snapshot_observed_at":"2026-07-06T23:25:11.623026Z","submitted_at":"2026-05-13T15:36:46Z","title":"Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-05-14T19:11:29.594372Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2605.13678"},"observation_digest":"sha256:952a419e8f0531333cabac231c2a035d762fbe4341d98996d18166e8b58dd570","observation_id":"96af2a29-650a-4e9d-86dc-cfca294d0fa7","resolution":{"observed_at":"2026-05-14T19:12:50.800298Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2605.22086","last_updated":"2026-05-21T07:27:22Z","snapshot_observed_at":"2026-07-06T23:32:25.286443Z","submitted_at":"2026-05-21T07:27:22Z","title":"GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-22T07:42:29.916098Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2605.22086"},"observation_digest":"sha256:a07394efcdfac82811ab24f7b5eb32f1c265ae3e8a5c7713d9fb64445079676b","observation_id":"08c6528d-4b04-433a-a6a0-960520e60afa","resolution":{"observed_at":"2026-05-22T07:44:42.795980Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2605.28166","last_updated":"2026-06-02T00:37:54Z","snapshot_observed_at":"2026-08-07T11:38:28.569735Z","submitted_at":"2026-05-27T08:48:58Z","title":"QuITE: Query-Based Irregular Time Series Embedding","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T14:00:34.801331Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2605.28166"},"observation_digest":"sha256:dc0260b813b6802a3041226f6f6e4b7a2a4d72aee4caf22859889cd7bec69d95","observation_id":"31f89dab-c0b1-446c-b193-a18bb1a55d84","resolution":{"observed_at":"2026-06-29T14:03:29.410595Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2606.00338","last_updated":"2026-05-29T20:26:26Z","snapshot_observed_at":"2026-07-06T23:41:01.066075Z","submitted_at":"2026-05-29T20:26:26Z","title":"CHAM-net: A Contrastive Hierarchical Adaptive Meta-network for Robust Global Methane Flux Prediction","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-06-28T23:09:03.816025Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2606.00338"},"observation_digest":"sha256:0d5a3f51780fe68e74e86a8b483b8cb5adc59c3193b5de9bf4405d873ff7ea20","observation_id":"28d3136a-50d1-4307-868b-5ea0d5cc70d0","resolution":{"observed_at":"2026-06-28T23:12:46.209845Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2606.19560","last_updated":"2026-06-17T20:01:48Z","snapshot_observed_at":"2026-08-02T08:46:24.267258Z","submitted_at":"2026-06-17T20:01:48Z","title":"Understanding Key Features of Time Series Foundation Models from Epidemic Forecasting","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-26T20:56:17.158686Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2606.19560"},"observation_digest":"sha256:33ff2b4fb654ac01bde6c0e02836789a356fbeb476704da85aef53bc3df2cef1","observation_id":"55e90726-60ad-4302-959b-4349131fd320","resolution":{"observed_at":"2026-07-04T00:49:18.897141Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2606.20010","last_updated":"2026-06-18T09:44:25Z","snapshot_observed_at":"2026-08-06T03:15:18.035475Z","submitted_at":"2026-06-18T09:44:25Z","title":"Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-26T17:57:08.795530Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2606.20010"},"observation_digest":"sha256:70e10ad7bf413f496a557668ba61890a03557d649370fd4a6821389bce8f264e","observation_id":"56cbe21d-a3b2-4693-8877-212b449336cf","resolution":{"observed_at":"2026-07-04T03:29:31.293261Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2606.27282","last_updated":"2026-06-29T17:59:36Z","snapshot_observed_at":"2026-08-06T19:26:33.128218Z","submitted_at":"2026-06-25T16:57:50Z","title":"How Good Can Linear Models Be for Time-Series Forecasting?","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-26T05:15:56.114842Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2606.27282"},"observation_digest":"sha256:a343a67948d949624eb7b34025d3f1e36eea58df26802742d56df020c63469b8","observation_id":"d2210843-d56e-48b2-b78f-7d8486bc036b","resolution":{"observed_at":"2026-07-04T13:19:51.312197Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2606.27282","last_updated":"2026-06-29T17:59:36Z","snapshot_observed_at":"2026-08-06T19:26:33.128218Z","submitted_at":"2026-06-25T16:57:50Z","title":"How Good Can Linear Models Be for Time-Series Forecasting?","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-30T09:33:16.718840Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2606.27282"},"observation_digest":"sha256:a1a19e0f479fc1d93ff47305af1e47ed50ab3cf8c66172e082f49addd4ad9757","observation_id":"81ae6eaf-2a53-40f1-8ab6-c075945f3e59","resolution":{"observed_at":"2026-06-30T09:34:34.427171Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":"2303.06053","doi":"10.48550/arxiv.2303.06053","metadata_source":"arxiv_reference","pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Arik, and Tomas Pfister","venue":"arXiv (Cornell University)","work_id":"54394ebd-5fcb-41f1-a7f5-9d0a980d589c","year":2023},"citing_paper":{"arxiv_id":"2606.31470","last_updated":"2026-06-30T10:49:04Z","snapshot_observed_at":"2026-08-07T04:43:41.133787Z","submitted_at":"2026-06-30T10:49:04Z","title":"CLOUDADV: Decision-Aligned Instance Sizing with Zero-Shot Foundation Models under Drift","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-01T05:47:18.737852Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2606.31470"},"observation_digest":"sha256:9e22f2dddd294da1658e3cdbd1f844dc4d7dcd2872cfb86a686893593b578346","observation_id":"5ff2cc25-b66e-42bb-b0d0-9b9fc31713f5","resolution":{"observed_at":"2026-07-01T10:15:43.958537Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-07-13T02:18:39.493876Z","title":"Tsmixer: An all-mlp architecture for time series forecasting.arXiv preprint arXiv:2303.06053, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.09537","last_updated":"2026-07-10T15:42:01Z","snapshot_observed_at":"2026-07-30T00:00:50.021634Z","submitted_at":"2026-07-10T15:42:01Z","title":"GatedLinear: Adaptive Routing of Complementary Linear Bases for Time Series Forecasting","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-13T02:18:39.493876Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2607.09537"},"observation_digest":"sha256:601210abc7e264e18dac2394e59f4793645fd34596d9cfc65a2c57a1c0658488","observation_id":"f0732c9b-5584-4bd8-b9f2-82717ef6f075","resolution":{"observed_at":"2026-07-13T02:18:39.493876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06053","snapshot_observed_at":"2026-08-01T10:29:17.331865Z","title":"arXiv preprint arXiv:2303.06053 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20230","last_updated":"2026-07-22T14:49:10Z","snapshot_observed_at":"2026-08-07T20:19:33.906925Z","submitted_at":"2026-07-22T14:49:10Z","title":"PIER: Physics-Informed Environmental Retrieval for Time-Series Modeling","version":1},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-01T10:29:17.331865Z"},"links":{"cited_paper":"/paper/2303.06053","citing_paper":"/paper/2607.20230"},"observation_digest":"sha256:b7b35cae2cf1fbe98a3972a6dc943eea399b6a831fe0437ad4836226bd595b2a","observation_id":"00497ecc-8426-404e-87fe-1c63728e6c1b","resolution":{"observed_at":"2026-08-01T10:29:17.331865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2303.06053/citation-record","integrity":"/paper/2303.06053/integrity","json":"/paper/2303.06053/citation-record.json","paper":"/paper/2303.06053"},"outbound":[],"paper":{"arxiv_id":"2303.06053","last_updated":"2023-09-11T11:19:49Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T06:19:20.551499Z","submitted_at":"2023-03-10T16:41:24Z","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 35 inbound Pith citation observations for arXiv:2303.06053."}