{"as_of":"2026-08-11T12:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ebc846d8035606b52c02ca588ff720c152a3ca0c675396ee83f32cbd8cd9ceea","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:24:25.877527Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T04:27:04.776920Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-14T23:23:15.964658Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.15369","snapshot_observed_at":"2026-08-05T18:15:19.607391Z","title":"iformer: Integrating convnet and transformer for mobile application","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15057","last_updated":"2025-08-20T20:45:10Z","snapshot_observed_at":"2026-08-09T05:44:22.418041Z","submitted_at":"2025-08-20T20:45:10Z","title":"GasTwinFormer: A Hybrid Vision Transformer for Livestock Methane Emission Segmentation and Dietary Classification in Optical Gas Imaging","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T18:15:19.607391Z"},"links":{"cited_paper":"/paper/2501.15369","citing_paper":"/paper/2508.15057"},"observation_digest":"sha256:245d62fea1ba09eab5e2499c54f84c4b4945f7ddaa4f29a9f49a4f8b37e96d90","observation_id":"0e5cecb1-0c79-4215-894e-d4d26fb69b6b","resolution":{"observed_at":"2026-08-05T18:15:19.607391Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"cited_work":{"arxiv_id":"2501.15369","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.15369","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"iformer: Integrating convnet and transformer for mobile application","venue":null,"work_id":"84714564-55c3-41c2-aec5-aabb0a22bea8","year":2025},"citing_paper":{"arxiv_id":"2604.09648","last_updated":"2026-03-27T19:30:06Z","snapshot_observed_at":"2026-08-07T09:26:53.516186Z","submitted_at":"2026-03-27T19:30:06Z","title":"TRACE: Thermal Recognition Attentive-Framework for CO2 Emissions from Livestock","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-14T23:19:53.767212Z"},"links":{"cited_paper":"/paper/2501.15369","citing_paper":"/paper/2604.09648"},"observation_digest":"sha256:fe2da4058e4b71394720c34bfb5942c89e168b81d20ae58f97162c005f6bb4c7","observation_id":"783770f6-731f-486d-a7df-e92b17d11d27","resolution":{"observed_at":"2026-05-14T23:23:15.971581Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.15369","snapshot_observed_at":"2026-08-08T04:27:04.776920Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.05671","last_updated":"2026-08-06T07:08:15Z","snapshot_observed_at":"2026-08-10T23:34:53.432379Z","submitted_at":"2026-08-06T07:08:15Z","title":"URNet: A Unified Reparameterized Network for Efficient RGB-D Semantic Segmentation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T04:27:04.776920Z"},"links":{"cited_paper":"/paper/2501.15369","citing_paper":"/paper/2608.05671"},"observation_digest":"sha256:5b4f43be073a39b58ece8b5001564117b2bc3b8311e646bcc5ddc860d24b5e94","observation_id":"a96d29e5-84d0-42fb-8768-a1e51d642c57","resolution":{"observed_at":"2026-08-08T04:27:04.776920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2501.15369/citation-record","integrity":"/paper/2501.15369/integrity","json":"/paper/2501.15369/citation-record.json","paper":"/paper/2501.15369"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:24:26.415177Z","title":"Output Size(Downs","venue":null,"work_id":"5a34b6d5-2a66-47cb-8d31-3aa1c1f38554","year":2025},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.872853Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:b89260a5621434b0f5fccf0c8d37b3f2ee2f4fac07cdef38b7354efb4f7e89c9","observation_id":"d9190fcc-6032-4f4f-88fa-9302b6c922f6","resolution":{"observed_at":"2026-08-10T14:24:26.420195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:24:26.430647Z","title":"As summarized in Table 14, split and concatenate operations introduce additional runtime","venue":null,"work_id":"43de2ca5-e2c8-44cd-8ba5-bb987b8eda9b","year":2025},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.868469Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:79b311d591bad95bd63f9e99a2106ba469b473c7abe0f6efe54d0f27131cb6cc","observation_id":"7f3c098c-800b-4983-95c1-104a0790f215","resolution":{"observed_at":"2026-08-10T14:24:26.435576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.01378","last_updated":"2022-06-02T12:16:28Z","snapshot_observed_at":"2026-08-06T03:49:21.426661Z","submitted_at":"2021-07-03T08:28:34Z","title":"Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.01378","snapshot_observed_at":"2026-08-10T14:24:25.750290Z","title":"Learning efficient vision transformers via fine-grained manifold distillation.arXiv preprint arXiv:2107.01378,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.750290Z"},"links":{"cited_paper":"/paper/2107.01378","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:b61606ceee127140a07937827835d684aa1006f59a089ab2469c1eee2721caa1","observation_id":"73295e50-bd7b-44eb-b709-5d74ba03182c","resolution":{"observed_at":"2026-08-10T14:24:25.750290Z","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":"2026-08-10T14:24:25.760161Z","title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.760161Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:9a746d88a056fc23f4befde929ec52f946118d52da3000564142bc9e17e6c196","observation_id":"7a3b7a70-7319-4ecc-a751-9d8bd79b3ba0","resolution":{"observed_at":"2026-08-10T14:24:25.760161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11202","last_updated":"2024-04-22T02:46:44Z","snapshot_observed_at":"2026-08-10T23:34:09.511886Z","submitted_at":"2024-04-17T09:33:31Z","title":"GhostNetV3: Exploring the Training Strategies for Compact Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11202","snapshot_observed_at":"2026-08-10T14:24:25.771228Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.771228Z"},"links":{"cited_paper":"/paper/2404.11202","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:59e814a5b94ff8461563d7c68b17ab878900e98038aaf36422339c846fe651c1","observation_id":"6cc8cb61-63e8-45d7-9780-854cf91be753","resolution":{"observed_at":"2026-08-10T14:24:25.771228Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12635","last_updated":"2022-05-26T13:40:26Z","snapshot_observed_at":"2026-07-06T13:13:44.464408Z","submitted_at":"2022-05-25T10:21:57Z","title":"MoCoViT: Mobile Convolutional Vision Transformer","version":2},"cited_work":{"arxiv_id":"2205.12635","doi":null,"metadata_source":"pith","pith_arxiv_id":"2205.12635","snapshot_observed_at":"2026-08-10T14:24:26.228551Z","title":"MoCoViT: Mobile Convolutional Vision Transformer","venue":"cs.CV","work_id":"897c12bf-5248-4ac9-84c5-615cb9af6d9d","year":2022},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.775945Z"},"links":{"cited_paper":"/paper/2205.12635","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:4a7b75ad60868e59c197a69bc736f7629721227e391bfe67ddfa5ff7652be9b3","observation_id":"53bfef61-5a38-4b72-8f53-9cd9dcc763f3","resolution":{"observed_at":"2026-08-10T14:24:26.233526Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:24:25.785453Z","title":"Mobilevit: light-weight, general-purpose, and mobile- friendly vision transformer","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.785453Z"},"links":{"cited_paper":"/paper/2110.02178","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:551c0410f052a53f678f8437185b88af74b3e52e82962d0af4627cddbcb3207c","observation_id":"4cddf970-c1f2-44b6-bf17-4e5d2527574a","resolution":{"observed_at":"2026-08-10T14:24:25.785453Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.02680","last_updated":"2022-06-06T15:31:35Z","snapshot_observed_at":"2026-08-10T23:33:30.133660Z","submitted_at":"2022-06-06T15:31:35Z","title":"Separable Self-attention for Mobile Vision Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.02680","snapshot_observed_at":"2026-08-10T14:24:25.789994Z","title":"Separable self-attention for mobile vision transformers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.789994Z"},"links":{"cited_paper":"/paper/2206.02680","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:8803d6b375b79382196535cd2fdf4eae4792093539652bcf943f8352e97409a6","observation_id":"c0fdd873-3d36-4c96-b64a-1e81d10f7bd8","resolution":{"observed_at":"2026-08-10T14:24:25.789994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.03460","last_updated":"2024-09-05T12:18:32Z","snapshot_observed_at":"2026-08-09T05:45:36.994435Z","submitted_at":"2024-09-05T12:18:32Z","title":"LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones","version":1},"cited_work":{"arxiv_id":"2409.03460","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.03460","snapshot_observed_at":"2026-08-10T14:24:26.161214Z","title":"LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones","venue":"cs.CV","work_id":"6ff0c7e4-5c6e-4dcc-b13d-cbe16fbddb05","year":2024},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.794421Z"},"links":{"cited_paper":"/paper/2409.03460","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:12c1aa444ccf5a58901746f560f47503b2872153b2f0d6c24afd19af32d4e223","observation_id":"63e6987e-b72d-4c5b-88b5-16ecd4df25de","resolution":{"observed_at":"2026-08-10T14:24:26.166457Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.10518","last_updated":"2024-09-29T21:58:22Z","snapshot_observed_at":"2026-08-05T00:57:12.473863Z","submitted_at":"2024-04-16T12:41:25Z","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.10518","snapshot_observed_at":"2026-08-10T14:24:25.799146Z","title":"Mobilenetv4-universal models for the mobile ecosystem","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.799146Z"},"links":{"cited_paper":"/paper/2404.10518","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:57d326ca23879f5991453ae0c2d1c61b79be67f95a63251b27d916a486f9d1b9","observation_id":"2f06eaa5-dab3-4594-b0eb-7045037725cd","resolution":{"observed_at":"2026-08-10T14:24:25.799146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05202","last_updated":"2020-02-12T19:57:13Z","snapshot_observed_at":"2026-08-11T06:21:56.129166Z","submitted_at":"2020-02-12T19:57:13Z","title":"GLU Variants Improve Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05202","snapshot_observed_at":"2026-08-10T14:24:25.803619Z","title":"Glu variants improve transformer","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.803619Z"},"links":{"cited_paper":"/paper/2002.05202","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:7b6503c580bb97f90e2e4d5e2f8e232e259b29b4e8064790d870ff6923bac7c5","observation_id":"c745476a-4025-4fa0-9376-8401bad46c8c","resolution":{"observed_at":"2026-08-10T14:24:25.803619Z","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":"2026-08-10T14:24:26.536852Z","title":"Ghostnetv2: Enhance cheap operation with long-range attention","venue":null,"work_id":"3f1118cd-6730-4a1b-8d55-2ebbe6593dd6","year":2025},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.808883Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:7489b992d5834b2607551dc9f312330a91d3dd426b6f37ced9f0e411d4def61f","observation_id":"71663fe0-a633-4f04-b4ab-0f60da80557e","resolution":{"observed_at":"2026-08-10T14:24:26.541431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.03762","last_updated":"2023-08-02T00:41:18Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-06-12T17:57:34Z","title":"Attention Is All You Need","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.03762","snapshot_observed_at":"2026-08-10T14:24:25.812958Z","title":"Fastvit: A fast hybrid vision transformer using structural reparameterization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.812958Z"},"links":{"cited_paper":"/paper/1706.03762","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:e70519cd99d01e843dba8bfb4f925d100399d978f82643ad8461b4a69040376d","observation_id":"0f186b2d-b4b8-4a15-bcef-c9f390d1149f","resolution":{"observed_at":"2026-08-10T14:24:25.812958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13156","last_updated":"2025-02-07T03:53:24Z","snapshot_observed_at":"2026-07-06T14:46:15.598295Z","submitted_at":"2023-01-30T18:34:16Z","title":"SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.13156","snapshot_observed_at":"2026-08-10T14:24:25.817540Z","title":"Seaformer: Squeeze-enhanced axial transformer for mobile semantic segmentation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.817540Z"},"links":{"cited_paper":"/paper/2301.13156","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:d8a7d3081e0b62944b98ff44079bea764d9f3124be201ff805a6163233334fdd","observation_id":"0a17cbb7-aec3-42a5-8271-f88ba864f4c4","resolution":{"observed_at":"2026-08-10T14:24:25.817540Z","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":"2026-08-10T14:24:26.522480Z","title":"Focal modulation networks","venue":null,"work_id":"9d2ef0fe-7c08-448c-93c3-ef22cc88faa4","year":2025},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.822300Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:81c0cbc187be20989a7020be435c4203153a0b88e18640d9db8132f02c5891c9","observation_id":"c844e49d-22ac-4ed3-a09e-930b5f1000b2","resolution":{"observed_at":"2026-08-10T14:24:26.526772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.03952","last_updated":"2022-07-26T12:11:15Z","snapshot_observed_at":"2026-08-02T14:15:07.425676Z","submitted_at":"2022-03-08T09:25:17Z","title":"ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer","version":5},"cited_work":{"arxiv_id":"2203.03952","doi":null,"metadata_source":"pith","pith_arxiv_id":"2203.03952","snapshot_observed_at":"2026-08-10T14:24:25.970830Z","title":"ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer","venue":"cs.CV","work_id":"032bb1ce-da3d-4736-927f-81b8094eeff5","year":2022},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.826743Z"},"links":{"cited_paper":"/paper/2203.03952","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:4d65c4760ef85ee22b5a332d6c98416c87dd42b54dfff67634df8f8c25443358","observation_id":"c246c064-af1e-483f-870b-0cbe3c62d975","resolution":{"observed_at":"2026-08-10T14:24:25.976570Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:24:26.507145Z","title":"Rethinking mobile block for efficient attention-based models","venue":null,"work_id":"b28af936-fba3-48e5-9f36-6cd6fc64a9c6","year":2023},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.831342Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:70b20b2db730e2d1b2f2984dfdd1aee12ccfcc6684ddb0ce50d201f407edaf50","observation_id":"795abad9-8884-44ec-958e-30af093881fe","resolution":{"observed_at":"2026-08-10T14:24:26.512617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03703","last_updated":"2024-12-13T03:19:24Z","snapshot_observed_at":"2026-07-06T18:57:52.401361Z","submitted_at":"2024-08-07T11:33:46Z","title":"CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.03703","snapshot_observed_at":"2026-08-10T14:24:25.835655Z","title":"Cas-vit: Convolu- tional additive self-attention vision transformers for efficient mobile applications","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.835655Z"},"links":{"cited_paper":"/paper/2408.03703","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:156f98b59da719f75acf2ab797c026f37a4e172079bb55e9dc0b66f44130ded2","observation_id":"77bdea01-bb04-4242-9ce3-cd24fa52e2ee","resolution":{"observed_at":"2026-08-10T14:24:25.835655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16004","last_updated":"2024-07-20T03:45:15Z","snapshot_observed_at":"2026-08-10T23:36:16.573764Z","submitted_at":"2024-06-23T04:11:12Z","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","version":2},"cited_work":{"arxiv_id":"2406.16004","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.16004","snapshot_observed_at":"2026-08-10T14:24:25.930726Z","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","venue":"cs.CV","work_id":"12063277-6c1c-4663-8fc3-eb22b971ca0c","year":2024},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.840065Z"},"links":{"cited_paper":"/paper/2406.16004","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:c0e6f892f983175b40dcbd98f7fa73bfaf9818b640ed23e1e682bded543a65dd","observation_id":"8c5290ac-db1f-4e98-8388-26e1bddd47c1","resolution":{"observed_at":"2026-08-10T14:24:25.937495Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.07268","last_updated":"2023-07-05T16:11:41Z","snapshot_observed_at":"2026-07-06T13:31:35.196992Z","submitted_at":"2022-07-15T03:27:13Z","title":"Lightweight Vision Transformer with Cross Feature Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.07268","snapshot_observed_at":"2026-08-10T14:24:25.844988Z","title":"Lightweight vision transformer with cross feature attention","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.844988Z"},"links":{"cited_paper":"/paper/2207.07268","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:4b93711e5fe1aed19a43b40dcd61850b7367184b9adf26e869a9b88a59ccfa61","observation_id":"89668b24-70ff-4a2a-90ea-e270b573b731","resolution":{"observed_at":"2026-08-10T14:24:25.844988Z","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":"2026-08-10T14:24:26.492981Z","title":"training config iFormer-T/S/M/L/H resolution 2242 weight init trunc","venue":null,"work_id":"39b03edc-3e97-4a4f-b0b0-d8f5d3db3edc","year":2025},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.849789Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:c9069c46910822a5fcef6bd0358edb85723b2a69266a46ef4c1a2de85d1b34e9","observation_id":"e32bfcb0-3efa-4e85-8b7a-f1d2cd046961","resolution":{"observed_at":"2026-08-10T14:24:26.497833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:24:26.461439Z","title":"We hypothesize that implementing more effective spatial mixing before the FFN diminishes its significance","venue":null,"work_id":"3a344adc-9a97-4f36-b125-15dff9394029","year":2022},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.859316Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:d780cdddf7bd187cc1275a61a7ba60cba9b315139751bd3796be6b83284d0a1c","observation_id":"4488822f-27f6-4572-a599-a7890b132daa","resolution":{"observed_at":"2026-08-10T14:24:26.466290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:24:26.445445Z","title":"Table 13: Object detection & Semantic segmentation results using backbone pretrained for 450 epochs","venue":null,"work_id":"f26fa856-40a7-469e-b405-08cc2dad2932","year":2016},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.863826Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:03184ff7792e9f268d72c5d3202a7dcf4d83b1948f21e95d7fcf82755d8399f5","observation_id":"56003c13-3b83-42a6-a255-53505e453a0c","resolution":{"observed_at":"2026-08-10T14:24:26.450582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:24:26.398628Z","title":"Channel Chunking","venue":null,"work_id":"8da1d6d4-3a76-43ef-b424-8716f597b0b0","year":2018},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.877527Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:6a5d0dd0a376777ed8f3f8338e3ca13ef37f570b2463b593500e81e233695681","observation_id":"45435208-475e-4761-9f79-53af2839b018","resolution":{"observed_at":"2026-08-10T14:24:26.404399Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.09461","last_updated":"2023-03-01T19:45:11Z","snapshot_observed_at":"2026-07-06T14:06:56.291161Z","submitted_at":"2022-10-17T22:23:40Z","title":"Token Merging: Your ViT But Faster","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.09461","snapshot_observed_at":"2026-08-10T14:24:25.725000Z","title":"Token merging: Your vit but faster","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.725000Z"},"links":{"cited_paper":"/paper/2210.09461","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:fa86aa9af9a602a76d8b83854923324ff2e49869bcc210a319dfcad892ae7f5a","observation_id":"5ce762c7-d284-4a90-bc61-6bbf7e0fdd05","resolution":{"observed_at":"2026-08-10T14:24:25.725000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1502.03167","last_updated":"2015-03-02T20:44:12Z","snapshot_observed_at":"2026-07-06T04:08:54.419941Z","submitted_at":"2015-02-11T01:44:18Z","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.03167","snapshot_observed_at":"2026-08-10T14:24:25.765485Z","title":"Batch normalization: Accelerating deep network training by reducing internal covari- ate shift","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.765485Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:f5f883c9bc1fa34da82bf15f2718ba21f322320d74fb76ec5e7b83b3bb81eff7","observation_id":"acee2e1e-a389-45ff-a941-c1a7ba5386f2","resolution":{"observed_at":"2026-08-10T14:24:25.765485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.19963","last_updated":"2024-03-29T03:48:35Z","snapshot_observed_at":"2026-07-06T17:52:54.875134Z","submitted_at":"2024-03-29T03:48:35Z","title":"Efficient Modulation for Vision Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.19963","snapshot_observed_at":"2026-08-10T14:24:25.780813Z","title":"Efficient modulation for vision networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.780813Z"},"links":{"cited_paper":"/paper/2403.19963","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:1e567e5ffe638a30d70fc7ef573617ca050a6553205cc5633935b0d5003a0a75","observation_id":"6d2e531d-9dec-42c3-bb3b-85c903ab4906","resolution":{"observed_at":"2026-08-10T14:24:25.780813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.10882","last_updated":"2023-02-13T01:19:57Z","snapshot_observed_at":"2026-08-10T23:32:09.056322Z","submitted_at":"2021-02-22T10:29:55Z","title":"Conditional Positional Encodings for Vision Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.10882","snapshot_observed_at":"2026-08-10T14:24:25.735397Z","title":"Mixformer: Mixing features across windows and dimensions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.735397Z"},"links":{"cited_paper":"/paper/2102.10882","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:9340e1fc56b78c127089760fd271ba09d4ab05f0a36e484767bad4e8768fe599","observation_id":"6d2d82fb-c37b-488b-b7c5-7bc20ddac949","resolution":{"observed_at":"2026-08-10T14:24:25.735397Z","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":"2026-08-10T14:24:26.551513Z","title":"In https://github.com/apple/coremltools","venue":null,"work_id":"1eb12768-ca25-4cf3-a667-0d46bb76cc9a","year":2009},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.740572Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:c2da2016af00ac5845ff8f0391e3c48a2641631da88d47028210d742bf5c3c4b","observation_id":"d0ac8a56-b136-4a20-838c-6627d1354dc6","resolution":{"observed_at":"2026-08-10T14:24:26.556111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.06189","last_updated":"2024-04-01T19:14:25Z","snapshot_observed_at":"2026-08-04T20:27:15.995220Z","submitted_at":"2023-06-09T18:41:37Z","title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.06189","snapshot_observed_at":"2026-08-10T14:24:25.755297Z","title":"Fastervit: Fast vision transformers with hierarchical attention","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.755297Z"},"links":{"cited_paper":"/paper/2306.06189","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:9100b0e3a24d622265c0265e04c784b31ae086483dcf18eba88e8f87d390029a","observation_id":"6c52a8c8-07ca-4843-ac6c-761b8f359fae","resolution":{"observed_at":"2026-08-10T14:24:25.755297Z","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":"2026-08-10T01:12:16.468283Z","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":"2026-08-10T14:24:25.745285Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.745285Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:9b853a8e552b9fb38d9681c6210f324d847a8d2b97c0792073e95e44a7bf1c70","observation_id":"437d2063-a54b-45e8-815a-150dd8036cad","resolution":{"observed_at":"2026-08-10T14:24:25.745285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.07155","last_updated":"2019-06-17T17:58:12Z","snapshot_observed_at":"2026-08-03T13:01:27.142233Z","submitted_at":"2019-06-17T17:58:12Z","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.07155","snapshot_observed_at":"2026-08-10T14:24:25.730063Z","title":"Mmdetection: Open mmlab detection toolbox and benchmark","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.730063Z"},"links":{"cited_paper":"/paper/1906.07155","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:f9ef3715b2af7d113e11c55a3fe9441c8cbd0bea8340551eaf1930a7f2206a7e","observation_id":"3026d7bf-2d61-4498-b2f7-b9c589e2b2d1","resolution":{"observed_at":"2026-08-10T14:24:25.730063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-10T14:24:25.719446Z","title":"Layer normalization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.719446Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:ad6d4d0d26df0f5adf9c700a519fba8e057f80160875317ed9d841e1d2644cb3","observation_id":"80efaf35-15d9-41a1-85c2-5f8822c79535","resolution":{"observed_at":"2026-08-10T14:24:25.719446Z","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":"2026-08-10T14:24:26.476795Z","title":"It is possible to further improve performance by adjusting the learning rates for different model variants, which we will explore in the future","venue":null,"work_id":"1152d122-69d7-4049-a2d0-07444addb0c2","year":2017},"citing_paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","version":2},"reference_index":4096,"source":"pdf_text","source_observed_at":"2026-08-10T14:24:25.854093Z"},"links":{"citing_paper":"/paper/2501.15369"},"observation_digest":"sha256:1c85cdb692880b4f2e8156ab4528392ac42dd184d345a9cc39642152b72e0780","observation_id":"ed4b637f-606e-4314-8717-717759189b8a","resolution":{"observed_at":"2026-08-10T14:24:26.482130Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.15369","last_updated":"2025-02-17T15:09:31Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T23:33:08.647810Z","submitted_at":"2025-01-26T02:34:58Z","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":4,"verified_fuzzy":9},"total_outbound_references":34},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 3 inbound Pith citation observations for arXiv:2501.15369."}