{"as_of":"2026-08-09T05:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3062047f4f12e6f77d4e0bf19cc00979cf2f4bd1577c3bf86b060b14ec4dd065","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T14:45:30.868808Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2508.20955/citation-record","integrity":"/paper/2508.20955/integrity","json":"/paper/2508.20955/citation-record.json","paper":"/paper/2508.20955"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.316928Z","title":"Back- propagation applied to handwritten zip code recognition","venue":null,"work_id":"e9d707c4-586b-4187-a2c2-8851065704ad","year":1989},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.725167Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:0397685dce5e15b458b12400b7685cf760d12a4f6e853f6be00e1418d2ed74be","observation_id":"f9482762-c029-42d8-a6b0-1fd84b05f3b9","resolution":{"observed_at":"2026-08-05T14:45:31.320644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:30.728286Z","title":"Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems, 25, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.728286Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:a4a24a207865129cd3f9457930cab01811b65559a140a53b8f93f19f1d02f412","observation_id":"42952b25-24d5-4584-8c9c-b9ca785260f6","resolution":{"observed_at":"2026-08-05T14:45:30.728286Z","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":"2026-08-05T14:45:30.731342Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.731342Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:87060d7b3187f8753284c6c3e01a97954e6811ee7b34fd0aaa59fd5282b8ae03","observation_id":"6652efb5-7d9a-4958-b830-c7fbe6fae04c","resolution":{"observed_at":"2026-08-05T14:45:30.731342Z","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":"2026-08-05T14:45:30.735539Z","title":"Efficientnet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.735539Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:d3743eb308693223b4fabaad64c6bab858283c7edba93233748b30a8c8d2a2e6","observation_id":"0b019cf3-8e34-4500-a4cb-dc1d779ff18b","resolution":{"observed_at":"2026-08-05T14:45:30.735539Z","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":"2026-08-05T14:45:30.738619Z","title":"At- tention is all you need.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.738619Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:206d4f0533bdb5bbcbfb874b54dabcef5a77137cc4f3ad09d20e7ad618ee2f9f","observation_id":"28a23ebd-cbd9-43b2-a07e-f7e012c861b4","resolution":{"observed_at":"2026-08-05T14:45:30.738619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","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":"2026-08-05T14:45:30.741921Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.741921Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:0b5920fb81817d5869f848f8ddbdba24b9056c586aef25281c1169e327c1d847","observation_id":"1bea85eb-ac8e-4a97-b494-96eb0bb0f69e","resolution":{"observed_at":"2026-08-05T14:45:30.741921Z","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":"2026-08-05T14:45:30.745574Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.745574Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:88184f3bf6cf8dc05ccd069913e488194287c54a7c69a2b37dd766c8ec29e97c","observation_id":"25c22196-75bf-4bde-8ab9-8d4288afaa5c","resolution":{"observed_at":"2026-08-05T14:45:30.745574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-05T14:45:30.748506Z","title":"F Wang et al.:Preprint submitted to Elsevier Page 11 of 13 E-ConvNeXt Mobilenets:Efficientconvolutionalneuralnetworksformobilevision applications","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.748506Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:3a8887f7e4dede3fb6bd557af99e7387c06920e0c75db529b6a1e1ce771b5364","observation_id":"bd290ba1-e7d3-4641-a31e-4758e952cb52","resolution":{"observed_at":"2026-08-05T14:45:30.748506Z","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":"2026-08-05T14:45:31.277789Z","title":"Swintransformer:Hierarchicalvision transformerusingshiftedwindows","venue":null,"work_id":"702f6400-dec5-4f64-9820-13114ae64767","year":2021},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.752495Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:d133aea7e765b2cdf416d7263556bb94bf3e042a220c0f845f4b0b7e5a3af4c3","observation_id":"866e1711-199c-4a81-a5de-2b91934e11d5","resolution":{"observed_at":"2026-08-05T14:45:31.281026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.267731Z","title":"Imagenet large scale visual recognition challenge.Internationaljournalofcomputervision ,115(3):211–252, 2015","venue":null,"work_id":"41983a50-f768-4cfd-a53f-0849101e624d","year":2015},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.755658Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:f6c278169ee2ec87d88fe213c708d6a08253ebdeeaf1c1d9cbe9bed77a912367","observation_id":"bdff1478-8a1f-4827-9ab9-7830c7f6d5eb","resolution":{"observed_at":"2026-08-05T14:45:31.271184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.257904Z","title":"Semantic understanding of scenes through the ade20k dataset","venue":null,"work_id":"2f80241c-a4de-4dca-894e-87dd0b3941eb","year":2019},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.758475Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:2a669f9a8b9c8d81c3f316d490e16cd16c3b4b6041c0390e33b0b8cdfbb4cc1b","observation_id":"9f11736e-7bbe-40bf-9c41-d195ffe1be5f","resolution":{"observed_at":"2026-08-05T14:45:31.261487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.247577Z","title":"Mi- crosoftcoco:Commonobjectsincontext","venue":null,"work_id":"eb94049a-6762-4b26-818f-58db56dba12b","year":2014},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.761842Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:d350e7e6862022e933f1e26e34ba847cbdf9d958f0c20d1c1a8aaaacd4ad3719","observation_id":"dd19954c-aa38-40c2-995b-4d9cc41a867c","resolution":{"observed_at":"2026-08-05T14:45:31.251301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.237441Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":"8d7db920-8991-45d5-9123-4cf26b45bdb6","year":2018},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.764653Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:84f5d3f4b2bad36e013f3f93a89c598387e935f81089e4325e2a9504f15920ec","observation_id":"21860653-dd81-4ae3-9c44-49f8e6ae28cd","resolution":{"observed_at":"2026-08-05T14:45:31.240996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:30.767516Z","title":"Searching for mobilenetv3","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.767516Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:ed333b425d59a403a2691bfe7a9d56aba5562bc189399d3334e4f1c49c9c4fc6","observation_id":"548c2ada-4733-449f-8f1e-d5bf5729b5f2","resolution":{"observed_at":"2026-08-05T14:45:30.767516Z","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":"2026-08-05T14:45:31.221522Z","title":"Run, don’t walk: chasing higher flops for faster neural networks","venue":null,"work_id":"b7066a3d-686d-4303-acad-14cccd418954","year":2023},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.770403Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:395c24d9984152f3d21ca77074cae10e0e2b7506fa1b02d8b9dc324b84187e8e","observation_id":"30f10645-c9ae-4b2d-bef3-4a46897e897b","resolution":{"observed_at":"2026-08-05T14:45:31.225031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:30.773333Z","title":"Cspnet: A new backbone that can enhance learning capability of cnn","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.773333Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:be9f5db0f4569560cd4bf3e8a8c18a3f428d4d67303aededcbd968855ee2232f","observation_id":"08bb6f3d-8618-4438-9db7-d3f32bdc5a6c","resolution":{"observed_at":"2026-08-05T14:45:30.773333Z","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":"2026-08-05T14:45:31.205676Z","title":"Shuf- flenet:Anextremelyefficientconvolutionalneuralnetworkformobile devices, 2017","venue":null,"work_id":"65acf079-120b-4076-a66a-a8012af2a818","year":2017},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.777597Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:c0f974ab462326818a7187807f4e2486a6ff9b95c5d1be91e3ccca7d96d6a9b1","observation_id":"d100fe98-fa75-451c-8137-0891764ef0d5","resolution":{"observed_at":"2026-08-05T14:45:31.209109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.196512Z","title":"Shuf- flenet:Anextremelyefficientconvolutionalneuralnetworkformobile devices","venue":null,"work_id":"9b466be9-72da-4f26-af3a-d528d420e9ac","year":2018},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.781876Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:bdfe66537e16ff0eb09ee73d3028519a87687979fafdbbc3d95284d87e8777d6","observation_id":"e15c4357-b287-4f1b-8f1b-502a3db5a309","resolution":{"observed_at":"2026-08-05T14:45:31.199732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.187082Z","title":"In International conference on machine learning, pages 10096–10106","venue":null,"work_id":"0c70fd64-1504-45f8-8a1d-0dac553979c0","year":2021},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.784495Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:a244f5c124ab096a7807236a73acafbad8cd55d71bc38f6fdaffd8a2dd770c74","observation_id":"d0d8c65f-3ae0-4389-a047-e98739d8aac7","resolution":{"observed_at":"2026-08-05T14:45:31.190511Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.177995Z","title":"Densely connected convolutional networks","venue":null,"work_id":"baa33ef9-ef74-4705-940b-9f1c2bf2d9b3","year":2017},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.787601Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:edb962630705a52fb8bcf0ff9df01676ab6b258844bbcf626982a71195232ddb","observation_id":"6d58da77-a354-4e5d-af61-f23c9d18374c","resolution":{"observed_at":"2026-08-05T14:45:31.181151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.168693Z","title":"Aggregatedresidualtransformationsfordeepneuralnetworks","venue":null,"work_id":"df573759-1442-4e84-9d71-0018e01e8065","year":2017},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.790516Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:ec4a3906b7e9248c5a69be22074d65005dd59ad6af51f3ccf114f1e77bcc52f6","observation_id":"eb7cbd91-5599-4806-8cdf-c59cad7842b3","resolution":{"observed_at":"2026-08-05T14:45:31.171849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.159323Z","title":"Squeeze-and-excitationnetworks","venue":null,"work_id":"0dae9185-5537-491c-a523-4b42bfa6dd41","year":2018},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.793456Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:083c04ebc3b24260b3ef6c0795cea40848b6df937a47f0a94e99a23d58bdc1d5","observation_id":"58ed5617-5384-468d-b559-f83a813671fb","resolution":{"observed_at":"2026-08-05T14:45:31.162410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.149753Z","title":"Eca-net: Efficient channel attention for deep convolutional neural networks","venue":null,"work_id":"017a6705-103a-40d2-b6fb-f3eced5cdb15","year":2020},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.796635Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:08480d1732de5ed4eda4d43b38d9cb46982eccfa216a0b49de3ee11f5e5996b2","observation_id":"23e5f1f4-564e-454c-9347-068a1b9b133b","resolution":{"observed_at":"2026-08-05T14:45:31.152994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.139550Z","title":"Global second-order pooling convolutional networks","venue":null,"work_id":"68c3cdc4-2a11-42b7-a5d4-7306efe7ab84","year":2019},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.799380Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:76760d0dc8857877c7aa03abdbb50508b71aa1bc4e7cb512312809ec0004af28","observation_id":"bbf08187-0b07-43d9-8e03-2c63de002da0","resolution":{"observed_at":"2026-08-05T14:45:31.142773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.128776Z","title":"Srm: A style- based recalibration module for convolutional neural networks","venue":null,"work_id":"304b2476-0550-45ae-8e2b-6e1091a7a2e6","year":2019},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.802048Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:9b6e8812fce214d9f6b4ff1768eb90c2ed95a334634003cd2a714625b1be754e","observation_id":"f6f77fbb-06a8-4c37-b04a-038ef39255ea","resolution":{"observed_at":"2026-08-05T14:45:31.132557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.118681Z","title":"Fcanet: Frequency channel attention networks","venue":null,"work_id":"ab579e0f-a53e-4db4-8068-43245ec09878","year":2021},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.805385Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:b5132d59785cb9857be6107395e103b250d297d339f7f2ca07d5c9a02a5eb731","observation_id":"43c11c41-1450-4145-8341-789481a90a07","resolution":{"observed_at":"2026-08-05T14:45:31.121953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2106.08254","last_updated":"2022-09-03T14:11:33Z","snapshot_observed_at":"2026-07-06T11:19:34.705520Z","submitted_at":"2021-06-15T16:02:37Z","title":"BEiT: BERT Pre-Training of Image Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08254","snapshot_observed_at":"2026-08-05T14:45:30.808283Z","title":"Beit: Bert pre- training of image transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.808283Z"},"links":{"cited_paper":"/paper/2106.08254","citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:1db7a771cbcf64793455cf0648ac329e2557f72b1bffc6567ee5acbcedf2153b","observation_id":"985da56a-71b5-4f5d-9435-ac95762f49bd","resolution":{"observed_at":"2026-08-05T14:45:30.808283Z","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":"2026-08-05T14:45:31.108090Z","title":"Batch renormalization: Towards reducing minibatch dependence in batch-normalized models.Advances in neural infor- mation processing systems, 30, 2017","venue":null,"work_id":"1caf0f6a-9fe1-4ea0-ab4a-ebc8f6feaa90","year":2017},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.812282Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:fec1ef5a434c564466272c80ddfce1fa18282fafcd1b4f043af5e99ed891412f","observation_id":"5504e1bb-6ede-46eb-ba25-12bc776b35e8","resolution":{"observed_at":"2026-08-05T14:45:31.112059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.097793Z","title":"Centermask: Real-time anchor- free instance segmentation","venue":null,"work_id":"2f4e2761-f995-463d-9088-a1bd21751835","year":2020},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.815261Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:82e56fcee21cab272dd1baed5f5a20d2c71f318fc30f444161107c9bc2fac4a1","observation_id":"654ff665-cfb2-4e71-85d7-cb3e1062e5fa","resolution":{"observed_at":"2026-08-05T14:45:31.101382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.087286Z","title":"Original approach for the localisation of objects in images.IEE Proceedings- Vision, Image and Signal Processing, 141(4):245–250, 1994","venue":null,"work_id":"d0701226-ecc5-4786-abc0-84c781b89bbf","year":1994},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.818173Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:057c61228572d87a8d02b3e376b7e859cbc66f37bde85d0f3949886b301e950c","observation_id":"2452ea62-3506-4e89-9a84-c7f571713244","resolution":{"observed_at":"2026-08-05T14:45:31.091068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-05T14:45:30.821879Z","title":"Decoupled weight decay regular- ization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.821879Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:0a29e85319f91b16ad0a0593296d7bf6a1be4f0fa4d5404a8cef16d77c43c7ff","observation_id":"acb625ee-db64-4711-a112-28eb8b9ff70b","resolution":{"observed_at":"2026-08-05T14:45:30.821879Z","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":"2026-08-05T14:45:31.076567Z","title":"Randaugment:Practicalautomateddataaugmentationwithareduced search space","venue":null,"work_id":"f0fd1913-4248-4da9-99c1-4f965f3b0c8d","year":2020},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.824786Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:8bc3aee6d0ece788040dcd5bbe19f0a129f80549115b7ca48b0e54177a06b0d3","observation_id":"69113330-6b3e-464e-961e-c2c0fb30a63a","resolution":{"observed_at":"2026-08-05T14:45:31.080249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"1710.09412","last_updated":"2018-04-27T21:39:25Z","snapshot_observed_at":"2026-08-08T10:28:19.597631Z","submitted_at":"2017-10-25T18:30:49Z","title":"mixup: Beyond Empirical Risk Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09412","snapshot_observed_at":"2026-08-05T14:45:30.827447Z","title":"mixup: Beyond empirical risk minimization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.827447Z"},"links":{"cited_paper":"/paper/1710.09412","citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:63c1011f3ed80d5baa4c6c710f693aad7a3f09c06d3e57968bc04754d329d8f3","observation_id":"2eb4581a-853e-4d19-bb09-b0c7b8c228e7","resolution":{"observed_at":"2026-08-05T14:45:30.827447Z","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":"2026-08-05T14:45:30.830436Z","title":"Cutmix: Regularization strategy to train strong classifiers with localizable features","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.830436Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:92b99332ede3a7bc5ab8684f33dae493ba30c57fb8c64c32b9c8bece577e425c","observation_id":"f0206a4d-4b22-4375-8083-7b3721245a8d","resolution":{"observed_at":"2026-08-05T14:45:30.830436Z","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":"2026-08-05T14:45:31.060617Z","title":"Random erasing data augmentation","venue":null,"work_id":"d44a3a1d-5953-4795-b111-c703460133e3","year":2020},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.833218Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:c267c22e73cfa42fd5d87570558aac087b3adb653203fd7f319863608fd1f7ef","observation_id":"9328e8d8-5486-45a8-bc34-d51c98e5aa82","resolution":{"observed_at":"2026-08-05T14:45:31.063936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.050722Z","title":"Rethinking the inception architecture for computer vision","venue":null,"work_id":"053938b5-915e-430d-873e-61ddfec5ddb6","year":2016},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.836033Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:fc43e74142597f47b3aa98426608f422c05ac775f72b257785413e7b3129b5ee","observation_id":"b4e84dca-8d5d-4a98-86f0-2b3e99cdb85b","resolution":{"observed_at":"2026-08-05T14:45:31.054288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.040905Z","title":"Ghostnet: More features from cheap operations","venue":null,"work_id":"76d91698-a2ef-4fad-91f5-e0bb0ad6ced9","year":2020},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.838924Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:215a63a1403577c882954c928cedaa1d3415e7767011dc4e50bd2abaccb82864","observation_id":"f01092ee-e6b5-4d1d-8f16-0704652ffcaf","resolution":{"observed_at":"2026-08-05T14:45:31.044502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.030044Z","title":"Shuf- flenetv2:Practicalguidelinesforefficientcnnarchitecturedesign","venue":null,"work_id":"071d3669-f5b6-4c17-8061-bbceaa758d36","year":2018},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.841742Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:7ad792b1c64da2a18fe7f5aa5ca1571ff9724f428c3b385c3c8f632894c9187d","observation_id":"7b934e42-c92b-4e8e-baf2-520625f03345","resolution":{"observed_at":"2026-08-05T14:45:31.034274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2110.02178","last_updated":"2022-03-04T17:17:31Z","snapshot_observed_at":"2026-07-06T11:54:38.041673Z","submitted_at":"2021-10-05T17:07:53Z","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.02178","snapshot_observed_at":"2026-08-05T14:45:30.844559Z","title":"Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.844559Z"},"links":{"cited_paper":"/paper/2110.02178","citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:7172be4db3b7d7987a35f4cbd8366b354b50ac7f6dc5657a7858621c7697ece0","observation_id":"07d5e589-b6d0-4cc1-92a5-ddb0e84e1b5c","resolution":{"observed_at":"2026-08-05T14:45:30.844559Z","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":"2026-08-05T14:45:31.019494Z","title":"Edgenext: efficiently amalgamated cnn-transformer archi- tecture for mobile vision applications","venue":null,"work_id":"8b41845f-da7e-46d4-b7b7-438b815ef85d","year":2022},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.847579Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:a52df76b171f600c0c0d0a1b9143c61a1961364648a5924c07bf0e349700d292","observation_id":"9f66f47c-e238-4dec-8457-36e75a028983","resolution":{"observed_at":"2026-08-05T14:45:31.023015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:31.009509Z","title":"Rewrite the stars","venue":null,"work_id":"7a73320e-55df-48e6-a5cc-fc02db5f0542","year":2024},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.850508Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:372bc5ecf971f32c86b35736d62d093b30931334f2917e0ef03ef5be1ece35c2","observation_id":"b31f56d8-c0e2-49f0-bfa2-cb46dd378c68","resolution":{"observed_at":"2026-08-05T14:45:31.012996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"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":"2026-08-05T14:45:30.853193Z","title":"Cyclemlp: A mlp-likearchitecturefordenseprediction.arxiv2021","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.853193Z"},"links":{"cited_paper":"/paper/2107.10224","citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:642b5101ee67dbc0e04e125a72f3906cfb53be210c75919b02bbe68bf1e386bb","observation_id":"8bfd7371-fcab-491c-8bd0-13845fa1cdbc","resolution":{"observed_at":"2026-08-05T14:45:30.853193Z","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":"2026-08-05T14:45:30.998962Z","title":"Metaformer is actually what F Wang et al.:Preprint submitted to Elsevier Page 12 of 13 E-ConvNeXt you need for vision","venue":null,"work_id":"949305a2-61a9-48ec-b4a5-2c0bbc5874b7","year":2022},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.856428Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:fde3b500ab335da73e575fb5932ad89da2bdf88b931196d5b3c4379e558c1168","observation_id":"893b9478-4149-4d1e-a23f-5e8e311152e9","resolution":{"observed_at":"2026-08-05T14:45:31.002311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T14:45:30.988715Z","title":"Pyramid vision transformer: A versatile backbone for dense prediction without con- volutions","venue":null,"work_id":"f4e7c3e8-31a7-428c-af4f-08692100af97","year":2021},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.859550Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:4719ee3ddac8c1570f0226b8c38c6b047cdc711aa7e2853effe9725addeb0d5c","observation_id":"5e46d772-c85e-4c2b-82a8-628e004630b4","resolution":{"observed_at":"2026-08-05T14:45:30.992208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2106.05681","last_updated":"2021-06-10T11:56:19Z","snapshot_observed_at":"2026-08-08T13:22:01.947698Z","submitted_at":"2021-06-10T11:56:19Z","title":"A Dataset And Benchmark Of Underwater Object Detection For Robot Picking","version":1},"cited_work":{"arxiv_id":"2106.05681","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.05681","snapshot_observed_at":"2026-08-05T14:45:30.902334Z","title":"A Dataset And Benchmark Of Underwater Object Detection For Robot Picking","venue":"cs.CV","work_id":"d56d4ba6-ce1a-4c5a-961a-61bab24bc3b9","year":2021},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.862545Z"},"links":{"cited_paper":"/paper/2106.05681","citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:dd3305c22cdccd637306eda71e0bd1b4d5e54474824ad3d5ee3e97fefe8c6582","observation_id":"91f2696b-3286-470b-ada5-42ac11db8e32","resolution":{"observed_at":"2026-08-05T14:45:30.907510Z","resolver_source":"local_arxiv","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":"2203.16250","last_updated":"2022-12-12T03:06:38Z","snapshot_observed_at":"2026-07-06T12:54:43.710902Z","submitted_at":"2022-03-30T12:31:39Z","title":"PP-YOLOE: An evolved version of YOLO","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.16250","snapshot_observed_at":"2026-08-05T14:45:30.865679Z","title":"arXivpreprint arXiv:2203.16250, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.865679Z"},"links":{"cited_paper":"/paper/2203.16250","citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:8c72fd3caaa9a68245f406e09a421eb688099d2c375f7f3805f8ba1f7572323e","observation_id":"10c949ab-840d-4c4e-b0c3-52ff50fcc5f8","resolution":{"observed_at":"2026-08-05T14:45:30.865679Z","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":"2026-08-05T14:45:30.976993Z","title":"Yolov10: Real-time end-to-end object detection.Advances in Neural Information Processing Systems, 37:107984–108011, 2024","venue":null,"work_id":"4721e999-402a-40b3-9775-65f8b90d3659","year":2024},"citing_paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T14:45:30.868808Z"},"links":{"citing_paper":"/paper/2508.20955"},"observation_digest":"sha256:6fa3f051d5dccc313162b9a363d175333a74f90cf9c554b6b96f734b75a8c5ae","observation_id":"801bc52e-2deb-442b-90ff-fda2e8dd6fa7","resolution":{"observed_at":"2026-08-05T14:45:30.981743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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"}}],"paper":{"arxiv_id":"2508.20955","last_updated":"2025-08-28T16:17:19Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T23:19:48.867165Z","submitted_at":"2025-08-28T16:17:19Z","title":"E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":1,"verified_fuzzy":30},"total_outbound_references":47},"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 9 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2508.20955."}