{"as_of":"2026-08-13T14:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d2981f5e00cb1ea47158688c36f70b27b70c74dbe6045c1ab2f4519535102f2f","coverage":[{"denominator":59,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":59,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T19:55:10.160611Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2411.10198/citation-record","integrity":"/paper/2411.10198/integrity","json":"/paper/2411.10198/citation-record.json","paper":"/paper/2411.10198"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.08116","last_updated":"2021-09-23T14:00:04Z","snapshot_observed_at":"2026-08-12T21:50:27.586960Z","submitted_at":"2021-03-15T03:26:06Z","title":"Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.08116","snapshot_observed_at":"2026-08-12T19:55:09.879994Z","title":"Improving generalization of transfer learning across do- mains using spatio-temporal features in autonomous driving","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.879994Z"},"links":{"cited_paper":"/paper/2103.08116","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:0f665c23ec2d7c034ebbf3b8fff0573bd6035adf63b6566060869464d7de01b1","observation_id":"e5777d03-5ff1-443a-a5f0-87f279d05695","resolution":{"observed_at":"2026-08-12T19:55:09.879994Z","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":"2026-08-12T19:55:10.749517Z","title":"Efficient prediction of human motion for real-time robotics applica- tions with physics-inspired neural networks","venue":null,"work_id":"3dca3eb5-fa77-405c-9c09-270470abc252","year":2021},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.884272Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:dc09c606a898ed26aa2e7bf22e578acbd0bd3bb44948e0f3e78a9cb60c5e2ba5","observation_id":"6d2589de-e0d0-4049-8370-2db9103bb5fd","resolution":{"observed_at":"2026-08-12T19:55:10.753108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.740475Z","title":"Anticipating many futures: Online human motion predic- tion and generation for human-robot interaction","venue":null,"work_id":"caee3482-ab99-4edf-9d45-33dca19b6134","year":2018},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.887668Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:3374c70568fc59bea112e75a4f4fdf64c434ae9aad6b2fc03b30c8e6a05763d7","observation_id":"a9e73dc2-6be2-4a4f-9ea8-ffcd7077f554","resolution":{"observed_at":"2026-08-12T19:55:10.743772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:55:09.890962Z","title":"Mau: A motion- aware unit for video prediction and beyond","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.890962Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:595153649ebff8adb837f2afc8ed6f171a8db16e8f243bb7b0f8e3860345d1b7","observation_id":"50b3ed71-f205-4890-a6be-16949e6fdad2","resolution":{"observed_at":"2026-08-12T19:55:09.890962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.10224","last_updated":"2022-03-18T08:45:29Z","snapshot_observed_at":"2026-08-08T08:30:35.914721Z","submitted_at":"2021-07-21T17:23:06Z","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.10224","snapshot_observed_at":"2026-08-12T19:55:09.893992Z","title":"Cyclemlp: A mlp-like architecture for dense prediction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.893992Z"},"links":{"cited_paper":"/paper/2107.10224","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:f3ff27cf3063988f707fcca771c7573fa078fd72e37c48d668907a582d2e4132","observation_id":"d99d91fc-8f5d-4584-8408-deaf31cd9514","resolution":{"observed_at":"2026-08-12T19:55:09.893992Z","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":"2026-08-12T19:55:10.726549Z","title":"Spatio-temporal image representation and deep- learning-based decision framework for automated vehicles","venue":null,"work_id":"e31c2678-3aeb-431b-9655-d43b0adac563","year":2022},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.897395Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:f7371301e4af24831c7925d15eb1edfe30d1a93976aa6a840e2bd33e1e5b3816","observation_id":"23d454bc-d45f-49c8-9d13-9f9ab43a7c5b","resolution":{"observed_at":"2026-08-12T19:55:10.730314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.06743","last_updated":"2017-04-17T18:36:08Z","snapshot_observed_at":"2026-07-06T04:57:08.358661Z","submitted_at":"2016-05-22T06:15:31Z","title":"Inductive Bias of Deep Convolutional Networks through Pooling Geometry","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.06743","snapshot_observed_at":"2026-08-12T19:55:09.900519Z","title":"Inductive bias of deep convolutional networks through pooling geometry","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.900519Z"},"links":{"cited_paper":"/paper/1605.06743","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:9a1a1f0b0d7a0e997811fe142287f173d6f739b54df6894d2f479a073a9e91ff","observation_id":"d42c47b9-64e7-465a-b7b0-5944ff774ba5","resolution":{"observed_at":"2026-08-12T19:55:09.900519Z","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":"2026-08-12T19:55:10.717840Z","title":"Pedestrian detection: A benchmark","venue":null,"work_id":"d36df06d-978d-4452-b729-7a57086bddab","year":2009},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.904012Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:fdd4ffc077cdec101249aeec4421fdaceab4f496045fb863843e2432b64ba069","observation_id":"69732bd6-a4a7-4ced-8c8a-5cc0d968d063","resolution":{"observed_at":"2026-08-12T19:55:10.720989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-13T14:19:26.598265Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-12T19:55:09.906615Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.906615Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:73aca2b318cfa279f9674e18b149a73379f46bcd7416635f7bef5d63897da2b6","observation_id":"c20f7826-48b0-4f95-b329-b770ced21ef2","resolution":{"observed_at":"2026-08-12T19:55:09.906615Z","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":"2026-08-12T19:55:10.708689Z","title":null,"venue":null,"work_id":"ec342256-e8ce-4257-be06-5f72a8992be3","year":2019},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.909309Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:895516bb632c9b98e14ddb2d69e3dbef63cd04c7510cda68130e170c37b95c41","observation_id":"50377bd2-a4fa-4edd-b446-b22de1ed79cf","resolution":{"observed_at":"2026-08-12T19:55:10.711945Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.699774Z","title":"Simvp: Simpler yet better video prediction","venue":null,"work_id":"d40042c4-444a-42b5-9f98-5b88cc257665","year":2022},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.912191Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:307d8586d04a13a3ad1e7aabea69f4484de1cc5abba2dd56f6df4aeb7e97e272","observation_id":"f6fda495-c83d-49ca-94ce-ccf1f0aea0b5","resolution":{"observed_at":"2026-08-12T19:55:10.703097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:55:09.914851Z","title":"Are we ready for autonomous driving? the kitti vision benchmark suite","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.914851Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:74112a9bef0a4c111c9d0ff6655947cc0d9f40d846c26e4bd93773b175ba6141","observation_id":"2764772a-c992-46ca-9dfc-d2ebfce0fc52","resolution":{"observed_at":"2026-08-12T19:55:09.914851Z","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":"2026-08-12T19:55:09.917418Z","title":"Deep Learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.917418Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:43003a42402a17aabb53233800461bd19a57d4ca31254e384abb6abff71adff6","observation_id":"08ae71b8-c179-4fe4-9096-e7b4cd49916a","resolution":{"observed_at":"2026-08-12T19:55:09.917418Z","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":"2026-08-12T19:55:10.680343Z","title":"Disentangling physi- cal dynamics from unknown factors for unsupervised video prediction","venue":null,"work_id":"1870caf7-8457-4656-953d-0862f610aee5","year":2020},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.919685Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:8e0374d1ff0ecc2e71e274a678da0503a2fd60999f35416cc5edd70d2d604bc0","observation_id":"0772fabc-2202-4f45-8b9c-1e603b1beca5","resolution":{"observed_at":"2026-08-12T19:55:10.683923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.670999Z","title":"Classifying pedestrian actions in advance using predicted video of urban driving scenes","venue":null,"work_id":"165897ad-0c83-4145-be99-3df111238ea7","year":2019},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.922219Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:db0c61b1bfe3933a41878932bfe75f071b5126dc0db7423d80ab8cab097f12db","observation_id":"04553204-7548-41cf-96a0-51125296c589","resolution":{"observed_at":"2026-08-12T19:55:10.674301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.662384Z","title":"Delving deep into rectifiers: Surpassing human-level perfor- mance on imagenet classification","venue":null,"work_id":"1642c9eb-aa41-438b-88c8-73b122f1d08c","year":2015},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.924785Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:d15dda04f9fd38c5a61fe1c2d0d2bf69abd510ee881fc136d8a370f6b3d1f2be","observation_id":"16f630af-a0a6-4fd9-af4b-fbee7a8eb2b6","resolution":{"observed_at":"2026-08-12T19:55:10.665418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.653970Z","title":"A dynamic multi-scale voxel flow network for video prediction","venue":null,"work_id":"88d996dc-da68-4a82-b510-6cecb87f5ec2","year":2023},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.927386Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:17d416fb5f24f52129f86a364c8defbdc7816fa16d068cccb0f4d81f03798b4a","observation_id":"1565775c-f41a-46b4-bdca-f85958e0698c","resolution":{"observed_at":"2026-08-12T19:55:10.656790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.644738Z","title":"Learning robot activities from first-person human videos using convolutional future regression","venue":null,"work_id":"1aa3f410-f1ea-41cb-b7db-0d80850322db","year":null},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.930174Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:defb6a0987952da094ff51fdbb93dfef73bc5bb4fab1d3d6137e0f8f7f9aaf8a","observation_id":"0ad150f8-76c1-4256-bf94-cb6003ea3c92","resolution":{"observed_at":"2026-08-12T19:55:10.648105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.03620","last_updated":"2023-03-03T19:04:38Z","snapshot_observed_at":"2026-08-11T00:43:34.132817Z","submitted_at":"2022-07-07T23:55:52Z","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.03620","snapshot_observed_at":"2026-08-12T19:55:09.933222Z","title":"More convnets in the 2020s: Scal- ing up kernels beyond 51x51 using sparsity","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.933222Z"},"links":{"cited_paper":"/paper/2207.03620","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:09a99ac614967f436a5e1bee3a5e63a68bbb4a5ffdd7698e63420a6d39a2f2c6","observation_id":"647fdc14-3417-45e3-be95-06c96b132448","resolution":{"observed_at":"2026-08-12T19:55:09.933222Z","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":"2026-08-12T19:55:09.936500Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.936500Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:e63a80fbd641b62719448fb577f7a53a864f4fc671aedb3aa47ee36ba3b7b1c6","observation_id":"657789a7-b35b-41ab-9cff-41f0d1a98c1b","resolution":{"observed_at":"2026-08-12T19:55:09.936500Z","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":"2026-08-12T19:55:10.631350Z","title":"Video frame synthesis using deep voxel flow","venue":null,"work_id":"098bd430-dd09-4c33-aebb-c96a2654a9d6","year":2017},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.939601Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:cbc76b24ff63e2931fb0c31970e948f5db2d2a98c32960fc6ab152f9246d256f","observation_id":"55447e5a-e6ad-4df6-8927-c961ec82c19e","resolution":{"observed_at":"2026-08-12T19:55:10.634447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.08104","last_updated":"2017-03-01T01:00:54Z","snapshot_observed_at":"2026-07-06T04:57:37.363685Z","submitted_at":"2016-05-25T23:58:55Z","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.08104","snapshot_observed_at":"2026-08-12T19:55:09.942565Z","title":"Deep pre- dictive coding networks for video prediction and unsuper- vised learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.942565Z"},"links":{"cited_paper":"/paper/1605.08104","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:69ab8b1102e4b26228a8903ee8b98da69bb7413db7f9ab154d2f5b92d947868b","observation_id":"82649d70-2b67-47e1-a124-48a8d8811d83","resolution":{"observed_at":"2026-08-12T19:55:09.942565Z","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":"2026-08-12T19:55:10.622732Z","title":"Predicting fu- ture occupancy grids in dynamic environment with spatio- temporal learning","venue":null,"work_id":"101432af-0625-43f1-92c3-bbeef92f834f","year":2022},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.946392Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:9deb6e490934717a986393c4aa757e80efd38df812281b8df4e6ae90225a2d9b","observation_id":"04284588-8a6b-442d-83bd-d63389370dab","resolution":{"observed_at":"2026-08-12T19:55:10.625763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:55:09.949652Z","title":"U- net: Convolutional networks for biomedical image segmen- tation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.949652Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:4d0fdf0aa52fe1670ae7220424b7ac27b6c89f19cb13170c30b411b5bda3d53f","observation_id":"e396159f-c377-4e1f-9ab0-560ce6ea3955","resolution":{"observed_at":"2026-08-12T19:55:09.949652Z","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":"2026-08-12T19:55:10.608747Z","title":"Rousseeuw","venue":null,"work_id":"0b83c411-d6fa-40e6-8a9b-5747be262df7","year":1987},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.952947Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:0bd63454f025bce728f9f692b375af5d9b535408b6cb764af27dbb12673092fb","observation_id":"6c2a9ddc-30cd-4de6-9347-71bf1da99e77","resolution":{"observed_at":"2026-08-12T19:55:10.612231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:55:09.956213Z","title":"Recog- nizing human actions: a local svm approach","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.956213Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:4fa5390c7364167c3e77d6c402baf7ef0dfe0505c744c432e9ae2295195aff6c","observation_id":"dcd96fd4-bcef-4f77-9aa3-4cfb7e5d9f07","resolution":{"observed_at":"2026-08-12T19:55:09.956213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.07849","last_updated":"2023-03-14T12:41:56Z","snapshot_observed_at":"2026-08-13T12:24:57.894902Z","submitted_at":"2023-03-14T12:41:56Z","title":"Implicit Stacked Autoregressive Model for Video Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.07849","snapshot_observed_at":"2026-08-12T19:55:09.963407Z","title":"Implicit stacked autoregressive model for video prediction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.963407Z"},"links":{"cited_paper":"/paper/2303.07849","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:5cf0f518babcd13a1743609d082e12a45cf083e295e867f6b10c23052c561f73","observation_id":"f4b0a008-30d1-4184-9d92-a3ae74ed0269","resolution":{"observed_at":"2026-08-12T19:55:09.963407Z","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":"2026-08-12T19:55:09.966909Z","title":"Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.966909Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:179a3a8767b64fbdb52e73f0c1a7bf4a4ce85307ff52401f89d134dccf130db3","observation_id":"431d08fa-3fe7-45a2-b78a-abad8853365d","resolution":{"observed_at":"2026-08-12T19:55:09.966909Z","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":"2026-08-12T19:55:10.578343Z","title":"Convolutional lstm network: A machine learning approach for precipitation nowcasting","venue":null,"work_id":"137edd4f-d720-48f9-b65c-53c16fd1825b","year":2015},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.970228Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:ae17e8d091f7aebe96f722806fd5cd8f8807397ff3c62490f0133f1c299e8ab7","observation_id":"150d773e-feac-4f95-8f08-c66ffe134647","resolution":{"observed_at":"2026-08-12T19:55:10.581979Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.567416Z","title":"Unsupervised learning of video representations using lstms","venue":null,"work_id":"10e8fb8b-6187-4080-abc3-9ab0060cdeeb","year":2015},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.973450Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:8bc04c4f1739fbc09a7407110acc1fbff27f00155cc3eaa9b7ab3d41c7917f6c","observation_id":"c288bac3-bbc1-486d-a469-777707d57e36","resolution":{"observed_at":"2026-08-12T19:55:10.571141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.555821Z","title":"Sequence to sequence learning with neural networks","venue":null,"work_id":"79d5e656-b53f-4a63-a5fd-24713058a56c","year":2014},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.976605Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:190eb16b6d64e48466561d245cbfab5f4a684c82c6455cd446e0187ee65e578a","observation_id":"0056a8f2-5450-4995-aea4-a61471281ed8","resolution":{"observed_at":"2026-08-12T19:55:10.559718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.544791Z","title":"Going deeper with convolutions","venue":null,"work_id":"6f5b74f5-3fa3-4672-86f8-3e33081be9bd","year":2015},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.979780Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:0546b1e2d8ce55d9750caf08f04619e4bac050e5ab3316fecad7f0309cd9a478","observation_id":"2ae2aa7b-7ecd-4db6-99d4-58a4101bb3b4","resolution":{"observed_at":"2026-08-12T19:55:10.548620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.532842Z","title":"Temporal attention unit: To- wards efficient spatiotemporal predictive learning","venue":null,"work_id":"ca6bd55b-9466-4be7-8cc0-3438098b93fa","year":2023},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.982775Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:adde1ce3ebd9bc8649a6137ff4d999bb1eb186c79095c34a31404d2674af6466","observation_id":"2c6c98ad-0ee5-47bb-a47f-7c89c21adc55","resolution":{"observed_at":"2026-08-12T19:55:10.536983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11249","last_updated":"2023-10-18T00:02:52Z","snapshot_observed_at":"2026-08-13T11:13:44.442125Z","submitted_at":"2023-06-20T03:02:14Z","title":"OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11249","snapshot_observed_at":"2026-08-12T19:55:09.985653Z","title":"Open- stl: A comprehensive benchmark of spatio-temporal predic- tive learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.985653Z"},"links":{"cited_paper":"/paper/2306.11249","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:2dda2e2efcd365be5d38cbc8bd90d1a547aadc6724166eafc12d0c145f7eeed1","observation_id":"520de40a-a81d-411d-a512-4db84a6e8289","resolution":{"observed_at":"2026-08-12T19:55:09.985653Z","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":"2026-08-12T19:55:10.089112Z","title":"Mlp-mixer: An all-mlp architecture for vision","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.089112Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:98390876743248447c95c73620312cf3cd299a9ad7e104fa504f4062f7ecd345","observation_id":"b2667f17-4a86-43e3-aa63-902f4198f3c2","resolution":{"observed_at":"2026-08-12T19:55:10.089112Z","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":"2026-08-12T19:55:10.515277Z","title":"Resmlp: Feedforward networks for image classification with data-efficient training","venue":null,"work_id":"e3d93468-f1d8-4cb6-bfa6-419299c45ee5","year":2022},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.092669Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:a5d51315f4a4b65c4ea077b04ea87dfbd5a764466f1a47305b015ebf1ba09cf0","observation_id":"ddb5b90f-1da9-4f36-a3f8-d5ffe95827c3","resolution":{"observed_at":"2026-08-12T19:55:10.518467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.09792","last_updated":"2022-01-24T16:42:56Z","snapshot_observed_at":"2026-08-10T07:30:43.773450Z","submitted_at":"2022-01-24T16:42:56Z","title":"Patches Are All You Need?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.09792","snapshot_observed_at":"2026-08-12T19:55:10.095375Z","title":"Patches are all you need? arXiv preprint arXiv:2201.09792, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.095375Z"},"links":{"cited_paper":"/paper/2201.09792","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:d4c11876d98929a2cd33a6a8dabc4ddb25ae042e9131b29f3a71385f96273fb0","observation_id":"545d3cc4-fb19-4c6e-b179-508df48ec8f2","resolution":{"observed_at":"2026-08-12T19:55:10.095375Z","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":"2026-08-12T19:55:10.098176Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.098176Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:780464320170c2301f955ff5e3435369ed8bc70ca5a88f77be6f466f7f80f5a5","observation_id":"d2166c17-3fca-43b6-b003-0ed4251648db","resolution":{"observed_at":"2026-08-12T19:55:10.098176Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.08033","last_updated":"2018-01-08T01:21:32Z","snapshot_observed_at":"2026-08-01T16:57:58.024755Z","submitted_at":"2017-06-25T04:18:12Z","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.08033","snapshot_observed_at":"2026-08-12T19:55:10.100677Z","title":"Decomposing motion and con- tent for natural video sequence prediction","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.100677Z"},"links":{"cited_paper":"/paper/1706.08033","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:98f346dda0f3a36c90451df54dd016aa41a531eede938cd6780c4fb4c33b3d8d","observation_id":"0e04bd53-2c22-4280-9d10-91247394ed15","resolution":{"observed_at":"2026-08-12T19:55:10.100677Z","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":"2026-08-12T19:55:10.497872Z","title":"Mcvd-masked conditional video diffusion for prediction, generation, and interpolation","venue":null,"work_id":"ff60f68b-bba7-4d64-ac69-5efffbaaa3ee","year":2022},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.103450Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:d6eabf4e4dbc5078e690f56c05cddae54caa2bae35536d33a507e36334b80146","observation_id":"0f8393fe-66e5-44b4-829c-4266eaceb0a1","resolution":{"observed_at":"2026-08-12T19:55:10.501337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.487616Z","title":"Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning","venue":null,"work_id":"079a8732-11c6-46b6-85df-15dda4cf25b1","year":2018},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.105988Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:115821d643bdb4b534b434b7abd35a2601954dd07eeb50061e4ac13824cbafa3","observation_id":"c8835ff8-8246-4f36-8664-f65e3fb46588","resolution":{"observed_at":"2026-08-12T19:55:10.491059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.477046Z","title":"Eidetic 3d lstm: A model for video prediction and beyond","venue":null,"work_id":"55e29b13-d376-4c48-bac7-da4c4cac2913","year":2018},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.108647Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:24cc6d18c997ca3df04579006dbd67e184bb6433838ec1bd36ea37502a452d45","observation_id":"ec406a26-d675-4a55-a465-2e6b5ff2c5fe","resolution":{"observed_at":"2026-08-12T19:55:10.480599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.466388Z","title":"Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms","venue":null,"work_id":"3447caec-af69-4a5d-bca7-63933cdd7958","year":2017},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.111410Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:702a8de06a30dd0f01dd0e9bb3b545ea0ddb9d235403f8a3f574d2263cabda30","observation_id":"1f622742-611c-4b66-9fe0-17ed6ce478b8","resolution":{"observed_at":"2026-08-12T19:55:10.469997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.454245Z","title":"Predrnn: A recurrent neural network for spatiotemporal predictive learn- ing","venue":null,"work_id":"fc5ef1c2-0048-4754-ad6a-f5cfc16fc80f","year":2022},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.114041Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:6ac8b74e1ba7ee9797ec099932bf277551fb27a37e3b75e7668e7315080b8f4f","observation_id":"435b323a-4813-4668-a466-8e42d1ddde0b","resolution":{"observed_at":"2026-08-12T19:55:10.458770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.442733Z","title":"Memory in memory: A predictive neural network for learning higher-order non- stationarity from spatiotemporal dynamics","venue":null,"work_id":"5d040635-980d-46ed-bef9-477773bc4b43","year":2019},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.116823Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:f1fbe8e11548e721813280456065894d9545ce9a1608e73de56a54e5d58ca259","observation_id":"8bc093b9-fee4-4230-9f56-33da4aa15339","resolution":{"observed_at":"2026-08-12T19:55:10.446446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.431643Z","title":"Sample-efficient reinforcement learning via conservative model-based actor-critic","venue":null,"work_id":"7c4f4f82-f072-48c9-9dd7-4f03978a2062","year":2022},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.119511Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:df81370cb2b677ef4a5d8e6184202159078098ac81485ab202a2e07ba6cf27e1","observation_id":"dedf46c7-7b0d-4fa4-8d39-9f790af1bd2b","resolution":{"observed_at":"2026-08-12T19:55:10.435383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.420436Z","title":"Theoretical analysis of the induc- tive biases in deep convolutional networks.Advances in Neu- ral Information Processing Systems, 36, 2024","venue":null,"work_id":"6527200a-9e6c-4258-b6e1-137dd7aec7d3","year":2024},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.122114Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:e57b6fc50f325cfbd1ffe74a1fd39c1cd80596cd24e5e71461e3016797b1f127","observation_id":"c4d95904-2d0a-4fe7-baf2-deb7c58ba17f","resolution":{"observed_at":"2026-08-12T19:55:10.424405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.409579Z","title":"Sample efficient deep reinforcement learning for dialogue systems with large action spaces","venue":null,"work_id":"9c77b85f-f8c8-46d6-9773-fbcd13e0fb86","year":2018},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.125281Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:bdd4788842435b684a1afd655bca315d61aff94e32c13d6017b41c486c4cbef1","observation_id":"873ac086-634e-4bf4-9d1b-d951b401824d","resolution":{"observed_at":"2026-08-12T19:55:10.413269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.11421","last_updated":"2025-01-14T08:59:17Z","snapshot_observed_at":"2026-08-13T11:39:02.614741Z","submitted_at":"2023-05-19T04:16:50Z","title":"PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction","version":3},"cited_work":{"arxiv_id":"2305.11421","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.11421","snapshot_observed_at":"2026-08-12T19:55:10.192769Z","title":"PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction","venue":"cs.CV","work_id":"94adb212-56f5-4a6f-9607-84c674d27657","year":2023},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.128731Z"},"links":{"cited_paper":"/paper/2305.11421","citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:b5fc63f7c1c93a60d58252313a75d8a09ba301cd03e65fe5a6de87640f460ba6","observation_id":"812dfe92-d89b-4203-834f-2ab7a377edfd","resolution":{"observed_at":"2026-08-12T19:55:10.198506Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.398974Z","title":"Predcnn: Predictive learning with cascade convo- lutions","venue":null,"work_id":"29c19aab-31c6-4537-91c8-f1724fa10818","year":2018},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.132269Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:03a83d59f76217c09162a05993a45a2d71189058c71bb86389168a7f3f3c1139","observation_id":"3e1e0875-42d6-4c05-9cdd-57a28977a129","resolution":{"observed_at":"2026-08-12T19:55:10.402625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:55:10.135815Z","title":"Vptr: Efficient transformers for video prediction","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.135815Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:ea47da7b64224119077b67b8ac75fc479f5b174a4814276d805494ae5c70ec97","observation_id":"b57a6bbb-7f66-410a-adea-5d321787510e","resolution":{"observed_at":"2026-08-12T19:55:10.135815Z","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":"2026-08-12T19:55:10.382085Z","title":"Crevnet: Conditionally reversible video prediction, 2019","venue":null,"work_id":"ad61050d-ed6c-4169-940b-b34135bfabc2","year":2019},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.139511Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:af7c73f5fef8998a7614f8cc7e662cf1d89896feb87f3e1165d71f13fc947b4c","observation_id":"fcada6cc-c360-4ba9-b884-e11d7d8f2726","resolution":{"observed_at":"2026-08-12T19:55:10.385153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.370909Z","title":"Efficient and information-preserving future frame prediction and beyond","venue":null,"work_id":"7d2e8dea-329f-4b7e-bb84-ef891a10120b","year":2020},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.142982Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:f79e6ca239c08084184acb18ca70ee70eea44635d5daf20e11502d33cbc453d1","observation_id":"fc2a83ea-2d41-4fbd-afdf-da3979ab0e83","resolution":{"observed_at":"2026-08-12T19:55:10.374895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.359739Z","title":"Predicting citywide crowd flows using deep spatio-temporal residual networks","venue":null,"work_id":"8b300a30-ff3a-402e-9ac0-7c5e5d1be73a","year":2018},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.146576Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:08572cc5555a329f9b3c46bcdf37de2550f9fc31a1bcbd9b9ff0a8a0d74b0120","observation_id":"fee79c12-bdc3-4ee3-a631-a6f8027b93ab","resolution":{"observed_at":"2026-08-12T19:55:10.363158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.348936Z","title":"Pose-forecasting aided human video prediction with graph convolutional networks","venue":null,"work_id":"657f1e25-50b1-428c-99cc-afb13b143062","year":2020},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.150030Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:936d2afd0b9f770e3b30589631d36405d7d9a6e53fd9873f59714bca1357ef40","observation_id":"eea4b4fd-078d-434c-a64e-02952c8556b0","resolution":{"observed_at":"2026-08-12T19:55:10.352472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.337526Z","title":"• Repeated STLMixer The parameter count from our proposed STLMixer architecture is O de · (d2 + d · k2 T1 + d · k2 T2 )","venue":null,"work_id":"4e0a8b44-c9ce-4893-a64f-0c771baaa0a1","year":null},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.153668Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:cd6073531ff32407651679976593824370be851fc401302198dcba1785430202","observation_id":"509ec157-59dc-44d0-86f7-d84a13688fe3","resolution":{"observed_at":"2026-08-12T19:55:10.341162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.327040Z","title":"Similarly k2 T1 ≪ d and k2 T2 ≪ d","venue":null,"work_id":"54e01ec4-a6ba-44d1-9068-0f05644d9aa2","year":null},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.157250Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:16022fca87ba516bbae0aecdcbf958635521ffeff42962d422172a97e37e1460","observation_id":"54079ed0-07ea-4e2a-809c-6eaaa7ecc0fe","resolution":{"observed_at":"2026-08-12T19:55:10.330379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.315973Z","title":"dis- persion","venue":null,"work_id":"7a673c35-90ec-4e2d-8c76-2db3a5c8395c","year":2000},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:10.160611Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:908c380ab53b59e20dfd02bacba43432452e4c6b3d99e8155651a0f3f0aec75e","observation_id":"b428b63e-bcd1-4d3d-9ca7-bc7a65cd4388","resolution":{"observed_at":"2026-08-12T19:55:10.319729Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:55:10.594683Z","title":"IEEE, 2004","venue":null,"work_id":"dea57396-fe40-436a-97d7-1465d5099762","year":2004},"citing_paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing","version":1},"reference_index":2004,"source":"pdf_text","source_observed_at":"2026-08-12T19:55:09.959596Z"},"links":{"citing_paper":"/paper/2411.10198"},"observation_digest":"sha256:30c55cec64ae3a51d59c104db238822d413b0efd40166b6c9df4ed59b5faf808","observation_id":"1a87e3e7-f773-49bf-8522-5f2e505db882","resolution":{"observed_at":"2026-08-12T19:55:10.597816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.10198","last_updated":"2024-11-15T13:53:19Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T21:50:34.006090Z","submitted_at":"2024-11-15T13:53:19Z","title":"STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing"},"reference_resolution":{"displayed":59,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":1,"verified_fuzzy":37},"total_outbound_references":59},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:2411.10198."}