{"as_of":"2026-08-10T04:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7e1c957119b42900bec20a22079a5b4814a4c79aee3290d0e8dc1a022970ed11","coverage":[{"denominator":75,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":75,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:27:53.028375Z","state":"measured"},{"denominator":77,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":77,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T00:24:55.763468Z","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":"2026-05-14T23:23:15.956970Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"cited_work":{"arxiv_id":"2505.21847","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.21847","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Repavit: Scalable vision transformer acceleration via structural reparameterization on feedforward network layers","venue":null,"work_id":"88975185-c0ba-4293-ade8-20897f85225c","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":43,"source":"pdf_text","source_observed_at":"2026-05-14T23:19:53.767212Z"},"links":{"cited_paper":"/paper/2505.21847","citing_paper":"/paper/2604.09648"},"observation_digest":"sha256:a9ec7cb46cdb85594f161d31dcdea8473b9e90353b7de4c24f03afebd2f68b94","observation_id":"7959b44c-82ad-4bc6-9a81-2769acef33da","resolution":{"observed_at":"2026-05-14T23:23:15.961256Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.21847","snapshot_observed_at":"2026-08-06T00:24:55.763468Z","title":"RePaViT: Scalable vision transformer acceleration via structural reparameterization on feedforward network layers,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.01343","last_updated":"2026-08-02T16:08:44Z","snapshot_observed_at":"2026-08-09T05:55:04.247198Z","submitted_at":"2026-08-02T16:08:44Z","title":"DeVIT: Low-Power Vision Transformer Acceleration Using Delta Computation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T00:24:55.763468Z"},"links":{"cited_paper":"/paper/2505.21847","citing_paper":"/paper/2608.01343"},"observation_digest":"sha256:16b3243f36b9ea4644b8dc6793aea35e3a4e7929ef1b6aa71f26bea2fe0f9578","observation_id":"8ba57d15-e1cb-49b7-97bb-3520375753b0","resolution":{"observed_at":"2026-08-06T00:24:55.763468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.21847/citation-record","integrity":"/paper/2505.21847/integrity","json":"/paper/2505.21847/citation-record.json","paper":"/paper/2505.21847"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:28:03.243097Z","title":"Token merging: Your vit but faster","venue":null,"work_id":"1e96e65e-c4c6-4d31-83cc-eaa84d676f09","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.005435Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:6f12862652d6ca354fa2bde609aa6119a933379c2c0b1aeed19bfb1db465eb9d","observation_id":"9f72e720-c5fe-41da-a60a-1f84b4dd89f4","resolution":{"observed_at":"2026-08-07T13:28:03.324248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:03.075381Z","title":"B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al","venue":null,"work_id":"7627038c-4775-4a0c-b9f5-f8a92c829fe2","year":2020},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.078005Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:a121d86c1513105597906b38ca01497c74e5cb2b75305404f05fbc286e35cba9","observation_id":"e39ff7ba-7241-44d0-8076-3477bb150985","resolution":{"observed_at":"2026-08-07T13:28:03.163821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:02.912716Z","title":"Efficientvit: Multi-scale linear attention for high-resolution dense prediction","venue":null,"work_id":"9f10fb81-3d45-468b-9825-d158ee3e8ec8","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.148509Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:7c52a44809fc22767fb0bc5544d2b122ec45b788d8c6ddd2c7690b6f126d3394","observation_id":"46c3df74-c7e2-429a-9732-855b8aacf71e","resolution":{"observed_at":"2026-08-07T13:28:02.958549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:45.217463Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.217463Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:a930b99b491d7122b8f851f7781f043203ec957db3885eab0179ebd5a58c9cb7","observation_id":"9e66d914-440c-49a4-973b-b5d0fc9adb94","resolution":{"observed_at":"2026-08-07T13:27:45.217463Z","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":"2026-08-07T13:27:45.287973Z","title":"C., and Lin, D","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.287973Z"},"links":{"cited_paper":"/paper/1906.07155","citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:2d76560d063954bc32059e1d801ede1ba2de6f5980b37c68e5443bd029c0b4d4","observation_id":"100ccb8b-8646-472b-a642-03c32402a6d8","resolution":{"observed_at":"2026-08-07T13:27:45.287973Z","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":"2026-08-07T13:28:02.806777Z","title":"Mobile-former: Bridging mobilenet and transformer","venue":null,"work_id":"ee0db7ca-166d-4df0-b871-fe599190c9a7","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.357089Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:a3eb76dd63e9fc54a57a9e7676301690d0bd5d21d4cc96589eab813ad0797139","observation_id":"72540cce-a55e-48b5-bd4e-1820d0b6c9d7","resolution":{"observed_at":"2026-08-07T13:28:02.852775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:02.648310Z","title":"Improved feature distillation via projector ensemble","venue":null,"work_id":"c88d3eff-3cc0-4a99-b6a7-6aaa335a3d03","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.439229Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:9addb6ce3c6fd96495e62dfbcae8284970a21520e5a1a06934500269b895619c","observation_id":"f21975cf-6cef-4b0b-99db-7fae7383546c","resolution":{"observed_at":"2026-08-07T13:28:02.708513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:02.455563Z","title":"Reproducible scaling laws for contrastive language-image learning","venue":null,"work_id":"b59655a4-1873-4c55-8f88-c05427cdd53a","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.505134Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:ac6f9586b1324bb353419a68648022df90de8b450a5522e149342db6612f10ef","observation_id":"885c1f45-f0dc-4280-9185-2a5d07d83883","resolution":{"observed_at":"2026-08-07T13:28:02.522153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:02.324852Z","title":"MMSegmentation : Openmmlab semantic segmentation toolbox and benchmark","venue":null,"work_id":"7c6c4d0b-a00a-43ab-aa3f-5c0abf3da9a1","year":2020},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.556904Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:d752f7c63b905a28980a7ccf21c40a312b3d6dae4ffbdaddc960ee50a92eb282","observation_id":"141a2893-5439-4802-b290-ca7940c93b5d","resolution":{"observed_at":"2026-08-07T13:28:02.402922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:02.178347Z","title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","venue":null,"work_id":"e36e5f2d-41d6-4bcc-8ef9-5ab2505bbd1a","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.623094Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:64224fdde0f39ae117dfc54a84b5ba234ac2d50859e3a4352dbcac5ec789431c","observation_id":"208860e0-422c-4ad6-8577-283af8f730df","resolution":{"observed_at":"2026-08-07T13:28:02.231331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:01.986684Z","title":"P., Caron, M., Geirhos, R., Alabdulmohsin, I., et al","venue":null,"work_id":"be4c9ec1-96fc-4d2f-aa23-b50f0d8abb61","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.726126Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:80b6589b90005312a6e6441f452e6f39f18d82f783bf800f02116c4ac7e473eb","observation_id":"7a7d3319-d2a7-4104-923a-d3cd56bea5ae","resolution":{"observed_at":"2026-08-07T13:28:02.080751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:45.802701Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.802701Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:1fc3cb170da81615955501e5412e0415ca131c8c1e345b2292e825bfada366b4","observation_id":"2a879326-452a-46b1-9d0b-5353a0dc34c8","resolution":{"observed_at":"2026-08-07T13:27:45.802701Z","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":"2026-08-07T13:28:01.836551Z","title":"Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks","venue":null,"work_id":"a0208b1b-a0b0-4e9c-9845-30f515d39539","year":2019},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.874654Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:e4683077ba5e1f12be4af56976f494ac52f17051cdb08b5c54b2680033c6f023","observation_id":"e39f7842-c5c1-47c9-8bd3-60cc395b71d3","resolution":{"observed_at":"2026-08-07T13:28:01.897203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:01.728971Z","title":"Diverse branch block: Building a convolution as an inception-like unit","venue":null,"work_id":"07c23c7e-c0cd-41d0-8953-7bbcff68b60a","year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.944759Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:d5ed914c129bf243dbbde6b32e09549518b266c77e372d06100acc4265b9e077","observation_id":"6fc45d22-443e-480c-972a-8c2472add66c","resolution":{"observed_at":"2026-08-07T13:28:01.764041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:01.562202Z","title":"Repvgg: Making vgg-style convnets great again","venue":null,"work_id":"1b08fb10-8b03-4f03-8b74-2c0ddb9aebc6","year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:45.994253Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:dc6fd936a769ac10d5bb3678cf5d1f3f18502b97cfed69b38aa3586ee8f6fc8a","observation_id":"c6d97798-378c-41d3-af77-528396fbcab9","resolution":{"observed_at":"2026-08-07T13:28:01.636099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:46.050615Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:46.050615Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:7587676a469c9ba1d075de27cbc426cea438474d6cdfd1fe95a3a498bff7df09","observation_id":"586e35d0-a13d-4d6c-a29c-2faa2603e593","resolution":{"observed_at":"2026-08-07T13:27:46.050615Z","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":"2026-08-07T13:28:01.382330Z","title":"A., Jafari, F","venue":null,"work_id":"ac728ccc-81a6-4708-bdd3-23afc751cc31","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:46.116886Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:2270bd8f0e4cfb98edef620f82030ca4f65f991b62f98044eb8818ed3819fb4f","observation_id":"107d7008-27b5-4789-88dd-31151b5be27d","resolution":{"observed_at":"2026-08-07T13:28:01.464000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:01.189603Z","title":"Levit: a vision transformer in convnet's clothing for faster inference","venue":null,"work_id":"2ed79254-2cff-41cd-a83f-4ce22b82c899","year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:46.215126Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:8004129b551b0432a8710ea8568e4f355a613dc9faac1fb7c5303fc8065a866e","observation_id":"7e416a1f-1cb1-42d6-bbe5-5f15dfc842d2","resolution":{"observed_at":"2026-08-07T13:28:01.280521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:01.058122Z","title":"Slab: Efficient transformers with simplified linear attention and progressive re-parameterized batch normalization","venue":null,"work_id":"a6af4fa2-d3df-4166-888d-1683b4f8bc9b","year":2024},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:46.318270Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:049bcf7a8d886ba131a8f6e25fc6837fbd7fbdcea25644ac9bfe3f7c09d9f641","observation_id":"276eee30-f9b5-47d9-8816-6668376fc167","resolution":{"observed_at":"2026-08-07T13:28:01.107677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:00.907519Z","title":"M., and Salzmann, M","venue":null,"work_id":"b2894ce8-a2aa-49ce-83eb-b5c92a0cb247","year":2020},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:46.444120Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:9fc1bbbc6e09ee410b6369247ce776f5bf26f9d44f7c6c2a2f563d83a430cecb","observation_id":"e41b8e09-14fe-4d83-9d2c-4905aabd6f7b","resolution":{"observed_at":"2026-08-07T13:28:00.956968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:00.710665Z","title":"Learning efficient vision transformers via fine-grained manifold distillation","venue":null,"work_id":"64025f33-246f-4ecb-ad1d-51d058b00ad2","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:46.546244Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:10dd2e8d632f80ba5bcee52558d55c7bae4c3cd0468671b97557c70513612153","observation_id":"58314a25-db5f-497b-8631-a5f4851ebb12","resolution":{"observed_at":"2026-08-07T13:28:00.819100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:00.582128Z","title":"Mask r-cnn","venue":null,"work_id":"6168dfa9-0f6d-4e69-8f23-d4310998e24d","year":2017},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:46.637831Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:2253799e6dc7220f031e9e2a6580f25a27f54a154f404b31b351661112fdd558","observation_id":"001aa655-7d4d-4920-8ff9-396881e675f7","resolution":{"observed_at":"2026-08-07T13:28:00.630452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:00.406405Z","title":"and Zhou, J","venue":null,"work_id":"d5072955-3cc1-415b-a8eb-71656a081455","year":2024},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:46.806769Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:06625c9083831ec2574c87b47e7df7579fb012c19badc27c5436908aa746a0f4","observation_id":"80b4a332-4a87-44bd-b65b-bff09d8dd2e1","resolution":{"observed_at":"2026-08-07T13:28:00.516499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.08415","last_updated":"2023-06-06T01:53:32Z","snapshot_observed_at":"2026-07-06T05:01:27.910364Z","submitted_at":"2016-06-27T19:20:40Z","title":"Gaussian Error Linear Units (GELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.08415","snapshot_observed_at":"2026-08-07T13:27:46.959811Z","title":"and Gimpel, K","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:46.959811Z"},"links":{"cited_paper":"/paper/1606.08415","citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:d4b25e32bbfc61d6d897a7817a819ac60698642cb9aee0400265685cf3cb6495","observation_id":"8b6147a6-db25-4f52-8ceb-9c1ff9fdd652","resolution":{"observed_at":"2026-08-07T13:27:46.959811Z","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":"2026-08-07T13:27:47.077445Z","title":"and Szegedy, C","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:47.077445Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:9609f318c6c0e3cb5182601238ccab3af212669bfa913293f3b5b741f8f31317","observation_id":"8be553f8-3dc9-4720-858c-ad1d51358fc3","resolution":{"observed_at":"2026-08-07T13:27:47.077445Z","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":"2026-08-07T13:28:00.268191Z","title":"All tokens matter: Token labeling for training better vision transformers","venue":null,"work_id":"bede973d-1964-4c3a-a85b-32ab7cad968e","year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:47.246475Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:3f2d69da2309074f5ed588b08e285850c8c1d94aa7330e93389ef1aa48cf39c6","observation_id":"5871e259-b89f-4649-a3d0-58f4943f4c90","resolution":{"observed_at":"2026-08-07T13:28:00.302547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:28:00.173239Z","title":"Token fusion: Bridging the gap between token pruning and token merging","venue":null,"work_id":"e5377ace-bb86-41fc-9c43-ce54bb067d84","year":2024},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:47.376598Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:275b52d9b38db1f58e66eab2c452fa732b39b7ef68505b455bff24cf1fa27d29","observation_id":"583a81f1-72c5-4dc6-97f8-18d27408e5b2","resolution":{"observed_at":"2026-08-07T13:28:00.211461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:47.552353Z","title":"C., Lo, W.-Y., et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:47.552353Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:80cc86a826bd3629d5681dc546881ca35723c48c486d674580f6171bcc3405fd","observation_id":"31521059-d2e2-4c46-ada8-d1204e846bf3","resolution":{"observed_at":"2026-08-07T13:27:47.552353Z","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":"2026-08-07T13:27:59.955516Z","title":"Spvit: Enabling faster vision transformers via latency-aware soft token pruning","venue":null,"work_id":"57868a34-c19e-4269-9731-4191b3666a83","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:47.690572Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:7410abc0d8588d9523d8c5c1a82924dc64490be4eab7a061def2a6656b4124f9","observation_id":"68faef66-af34-4bd9-acdb-f08dd434f0d5","resolution":{"observed_at":"2026-08-07T13:28:00.057259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:59.744358Z","title":"Peeling the onion: Hierarchical reduction of data redundancy for efficient vision transformer training","venue":null,"work_id":"4c28dfa8-755b-47ef-acd0-ac7b622bf13b","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:47.838915Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:fa063dfcf6ecb7608eab121f58d01ae25e48c41bad8cc95a713a37d227e6a499","observation_id":"84aa4104-373a-44a9-adc9-22026226a860","resolution":{"observed_at":"2026-08-07T13:27:59.834091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-07T13:27:47.977714Z","title":"R., and Hinton, G","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:47.977714Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:fd7ecc04c03c3c96e6705a2e5bc7bca1994805920f30078de0b84caa19b3bfc4","observation_id":"21e8091d-0c9c-4465-aace-e3674f08da32","resolution":{"observed_at":"2026-08-07T13:27:47.977714Z","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":"2026-08-07T13:27:59.631041Z","title":"Efficientformer: Vision transformers at mobilenet speed","venue":null,"work_id":"ad0ffbeb-177a-4d1d-8eaf-2d1553e1689f","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:48.111751Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:a01c471dd922b2b33bd10c1db06bc47d36a81c0488808e428b225895667aabd0","observation_id":"2fb3272e-e312-49e2-9f84-cb9a7248ed6e","resolution":{"observed_at":"2026-08-07T13:27:59.694685Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:59.491993Z","title":"Evit: Expediting vision transformers via token reorganizations","venue":null,"work_id":"cc67faf9-e593-4262-9937-9d999f8ba835","year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:48.201879Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:9d266d6757aad30ca7ea302209d5071aa158bc51a98878179af004feea66b9ee","observation_id":"ad50d6bf-0615-4e30-b282-3cbb5624d3f5","resolution":{"observed_at":"2026-08-07T13:27:59.553606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:48.327152Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:48.327152Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:8e96fb3024c559cc368db7afa6ee52edfd0f84300b146aa016fd188039eba2fc","observation_id":"adf8f4e0-881b-4bc0-ac86-28cfd651d7ec","resolution":{"observed_at":"2026-08-07T13:27:48.327152Z","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":"2026-08-07T13:27:59.260489Z","title":"Focal loss for dense object detection","venue":null,"work_id":"e0f77d7a-9fe1-41b7-b72c-2278660462cf","year":2017},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:48.446370Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:a0632ca1d12922fc856cfa33721579c3405e4fa076a115bf9514fc3294b4aadd","observation_id":"c81e5e95-9bde-4820-95af-385fd44a0a0d","resolution":{"observed_at":"2026-08-07T13:27:59.338012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:48.547213Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:48.547213Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:8292e3572f9620df0fa06db7dd763c03bd2073fd5e1efcb9c77d5b7131040735","observation_id":"93879e39-691f-432c-a73d-8ec681ce0156","resolution":{"observed_at":"2026-08-07T13:27:48.547213Z","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":"2026-08-07T13:27:59.120724Z","title":"Swin transformer v2: Scaling up capacity and resolution","venue":null,"work_id":"990a739b-cffe-416b-a218-d3468735cfc7","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:48.698722Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:f862c59d7288522cce631e6999c586d405f26e5dfbece8e87e621dab94aa928f","observation_id":"10865df5-a497-4bb3-91fa-978eeb2854ed","resolution":{"observed_at":"2026-08-07T13:27:59.197755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:58.935056Z","title":"and Hutter, F","venue":null,"work_id":"b2007dd8-0741-40e7-bd53-04c7ff9b666c","year":2017},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:48.803361Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:84855bbb2accaa5da1e8426e5c83913039d652656d83990e5d3589a6423c0ad1","observation_id":"9c7bac21-6077-4886-ac1e-535ae15e0c25","resolution":{"observed_at":"2026-08-07T13:27:59.022633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:58.773906Z","title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design","venue":null,"work_id":"cd02c081-d7e0-4f62-832c-b427b3823696","year":2018},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:48.898547Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:74b72789107e256e51d4bb235abd342f128da95553afbcdfc409031a9a4c38c5","observation_id":"ea23cbc8-37b1-4916-820c-11a6e864b438","resolution":{"observed_at":"2026-08-07T13:27:58.824559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:58.516900Z","title":"W., Anwer, R","venue":null,"work_id":"b6f9bf04-92c0-4c79-a775-4a185515e48f","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:48.984726Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:a8916d433fbc6a5aafb90e1b37e2b2af8d1b3248bad52be42a216ae4c9cae762","observation_id":"b6617482-8fdb-4917-a0aa-ba957599c1fa","resolution":{"observed_at":"2026-08-07T13:27:58.648782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:58.307643Z","title":"R., Ranjan, A., Prabhu, A., Rastegari, M., and Tuzel, O","venue":null,"work_id":"4a28018d-6d16-4efe-8332-4e1f52f354a8","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:49.103051Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:4ec4ce37bc5f2e1099f01ba4e00947da1cc5bc6fdb2389c1af09fdbbbb2b6084","observation_id":"67f50afa-18df-4970-ad0d-5896990e517d","resolution":{"observed_at":"2026-08-07T13:27:58.396689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:58.122496Z","title":"and Rastegari, M","venue":null,"work_id":"4a4864d2-e7e2-4c97-8418-5a4c9a96b1dc","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:49.262507Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:589fc15651b9fac7edd09676231b14f04a152edb1be620554ccf08da8ad084c6","observation_id":"762ebb6e-a574-4ae1-949a-d2d4967fbdf5","resolution":{"observed_at":"2026-08-07T13:27:58.174781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.02680","last_updated":"2022-06-06T15:31:35Z","snapshot_observed_at":"2026-08-03T05:32:57.281028Z","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":"2026-08-07T13:27:49.390514Z","title":"and Rastegari, M","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:49.390514Z"},"links":{"cited_paper":"/paper/2206.02680","citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:06d94669819dacb99d012681bfcbf4be7bc9b8eecbe221bd109f3e7fa062718f","observation_id":"a08e2317-556b-433d-b4ad-0f93a07ecdb3","resolution":{"observed_at":"2026-08-07T13:27:49.390514Z","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":"2026-08-07T13:27:57.957819Z","title":"Adavit: Adaptive vision transformers for efficient image recognition","venue":null,"work_id":"4a914a12-3606-4e63-ad7e-789cf779eb96","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:49.489537Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:ad064b2e0c0534bcc3c1c9bcf69f1e0f42c525e990f3debd6998716952f65027","observation_id":"d3ace4f7-c42a-45be-b18d-3aff0346496e","resolution":{"observed_at":"2026-08-07T13:27:58.058235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:49.576398Z","title":"Language models are unsupervised multitask learners","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:49.576398Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:7a7830611dc4582f7e60ebb320222b22940d2774c6e6cfb53dd2b713954b4afb","observation_id":"ecb10f29-70bd-434d-b93c-a7a2524a82bc","resolution":{"observed_at":"2026-08-07T13:27:49.576398Z","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":"2026-08-07T13:27:49.667378Z","title":"W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:49.667378Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:08ef299231cec14782e3bee6c4b9d60c5c65141bf803f484fdbaa99c70e641d6","observation_id":"9c0918c6-d211-48a6-88f9-1737db1fa045","resolution":{"observed_at":"2026-08-07T13:27:49.667378Z","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":"2026-08-07T13:27:57.770523Z","title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","venue":null,"work_id":"635e2417-10bb-4282-b2d3-920d799f3104","year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:49.805577Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:44a3dd0d78ea7ce9f3be9fbc026743581a3118c350ad3024ef296530516e3e90","observation_id":"cef82201-63f8-4b26-a072-5b84f5c0fac0","resolution":{"observed_at":"2026-08-07T13:27:57.855534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:57.600309Z","title":"Tokenlearner: Adaptive space-time tokenization for videos","venue":null,"work_id":"ea84d977-27f7-4942-bd77-e7ad6b1054db","year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:49.915029Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:9e872a58b16f3b553eb00469588a345066f769b4a13bfb8d747e44cd0f7b6ed1","observation_id":"51aa05e4-0e6f-46bd-9a94-95740ae5c9fe","resolution":{"observed_at":"2026-08-07T13:27:57.668346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:57.439369Z","title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","venue":null,"work_id":"b7b39ae5-be03-4c6d-b05a-b74b3d176aa4","year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:50.020909Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:2ce9cce45c315ae290ef6ff1e54667af080f90f48500202fc8b59406b4e7f575","observation_id":"7ce0a290-1548-4e63-8aaf-be3e24e30ec1","resolution":{"observed_at":"2026-08-07T13:27:57.517771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:57.207486Z","title":null,"venue":null,"work_id":"f554aa49-7a0e-4dda-aa03-1f94683b3f47","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:50.148153Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:e0610df7c86391b0eae81e64cd577c5246839ff424f13a38aaa7e105bdef4831","observation_id":"44543590-2e41-4d79-af94-b4121503f056","resolution":{"observed_at":"2026-08-07T13:27:57.313663Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:56.998841Z","title":"Boosting vanilla lightweight vision transformers via re-parameterization","venue":null,"work_id":"20121c5b-eda7-4647-9d07-6841b4c7acba","year":2024},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:50.292668Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:0f02c67145f4c1dbd72d59f5076112de03ef250099d30ed07ec21f8a65a92184","observation_id":"47baca31-c13a-46fd-a72e-77c254869a79","resolution":{"observed_at":"2026-08-07T13:27:57.100436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:56.854177Z","title":"Patch slimming for efficient vision transformers","venue":null,"work_id":"bd6467d5-1573-4124-b786-4bc45ac0ff8d","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:50.382882Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:f685f4f406fddefe666caabaeb03b59800736c08390d4ef68a39a4bd71550d79","observation_id":"c7e0cc52-2aeb-4d18-8508-c54c23b93fd2","resolution":{"observed_at":"2026-08-07T13:27:56.899339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:50.487356Z","title":"O., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., et al","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:50.487356Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:88f2f76857c1a78858bbe84fdb19ff5f53d794039b39aee95b1ecc9c6cc67a6e","observation_id":"ac2fefad-a2ef-4db3-9f13-51155ba56c63","resolution":{"observed_at":"2026-08-07T13:27:50.487356Z","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":"2026-08-07T13:27:50.589425Z","title":"Training data-efficient image transformers & distillation through attention","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:50.589425Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:4769e5f36d3bfa58e3b68d04bcd1bc6214386c0b26363e89696868fa306e80d7","observation_id":"54b9af9f-ecc3-4fdf-b9f3-0de8c149e7bd","resolution":{"observed_at":"2026-08-07T13:27:50.589425Z","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":"2026-08-07T13:27:56.680515Z","title":null,"venue":null,"work_id":"8accd4b8-6230-42fa-9fcb-8efbf8dcfdd9","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:50.682653Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:018b869f351115c93785af446bb01d11d318fe1a887773f4e461e1ead24a34a9","observation_id":"56638012-8504-442d-b086-80653ce9b30a","resolution":{"observed_at":"2026-08-07T13:27:56.717237Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:56.524456Z","title":null,"venue":null,"work_id":"fc8e65bf-e74e-4d31-8a00-85921e145f65","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:50.786098Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:b20a96153f2806708c96b3cf781805caeb368371c7b1ea1df2493fd2aa0fd280","observation_id":"ed1f0c29-1b8d-42d9-a0dd-ba745c2890ef","resolution":{"observed_at":"2026-08-07T13:27:56.579863Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:56.428383Z","title":null,"venue":null,"work_id":"be74c9d8-218b-4a3c-8a54-e67f43788450","year":2017},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:50.930776Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:53ca71c4b85e73f8a1bc18f21617ac2f850c962441b6e17a8de4e38cd31be667","observation_id":"fad1a498-d8ac-43bc-a93a-65ece657a40d","resolution":{"observed_at":"2026-08-07T13:27:56.457303Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:56.330363Z","title":"Repvit: Revisiting mobile cnn from vit perspective","venue":null,"work_id":"db7ec5cc-7faa-4f4f-8323-c2d5857ad75f","year":2024},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:51.030146Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:61d28b907a91a624a606a8a56dededc450e272628f5d4004539a089db3662274","observation_id":"578024ba-7d68-4a1e-885c-6a10efcfbbe3","resolution":{"observed_at":"2026-08-07T13:27:56.374338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:56.250601Z","title":"Tinyvit: Fast pretraining distillation for small vision transformers","venue":null,"work_id":"62cae724-cf97-4549-a504-3894cba782a7","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:51.145314Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:ea40c77f1073fdc0663db3744d8c55058984878b9f3c10565ed213867c505de5","observation_id":"c337ad37-fbbc-487e-9174-ae239a0cbacf","resolution":{"observed_at":"2026-08-07T13:27:56.290161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:56.142027Z","title":"Unified perceptual parsing for scene understanding","venue":null,"work_id":"e02fa380-ba4b-4f32-82a0-1a84d936a704","year":2018},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:51.252746Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:3bb054e72d92be7c77718eb24e300d49b4905bc31a7fb8c8ea9f954a3195865c","observation_id":"ad20b943-0dc2-46bc-9cd0-d7b74bd3ba8d","resolution":{"observed_at":"2026-08-07T13:27:56.190669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:56.033736Z","title":"Lpvit: Low-power semi-structured pruning for vision transformers","venue":null,"work_id":"240e78e5-2740-4fa1-868f-9a5e34b78e3a","year":2024},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:51.371560Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:973ffb88847fa0fbde95b094a1901acdaadc1827e0609b3ba4840cc50e8d11ce","observation_id":"62a26267-f6b7-4464-bd8d-a0228ad2db9a","resolution":{"observed_at":"2026-08-07T13:27:56.084181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:55.932146Z","title":"No token left behind: Efficient vision transformer via dynamic token idling","venue":null,"work_id":"b82a4eef-11c6-4e89-82e3-12747209ef87","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:51.472356Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:1df33c46b9d2f3534e3aac750e61f7b3382a85476567979508ae0d7d8afc956a","observation_id":"fcba0f38-2ad7-4226-8eaf-b09535648e71","resolution":{"observed_at":"2026-08-07T13:27:55.967534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:55.854305Z","title":"Gtp-vit: Efficient vision transformers via graph-based token propagation","venue":null,"work_id":"a02e0bb6-1dbb-4ad7-b10d-12b45864b559","year":2024},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:51.595649Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:cf524b7eced2ba8a2b2eea2197ae4971f7ee996c9a57a64273c4427e6eb45348","observation_id":"992f239b-c57b-4534-a46f-5282e8b0f7bf","resolution":{"observed_at":"2026-08-07T13:27:55.889411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:55.698977Z","title":"Evo-vit: Slow-fast token evolution for dynamic vision transformer","venue":null,"work_id":"1534b23b-ea9f-4483-b7fb-d79a1a4822e5","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:51.738104Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:aeca30e14eac0d6ae3c473ebda5cb0480f8cdf38eb0ebf94d366c80d165f5f26","observation_id":"20cd2ca3-0c6d-45fa-bd68-31c7d96c778b","resolution":{"observed_at":"2026-08-07T13:27:55.787076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:55.561764Z","title":"Leveraging batch normalization for vision transformers","venue":null,"work_id":"13c97936-54a0-45e1-8148-3a51fb108311","year":2021},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:51.870741Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:8db0b742d6e8c993525a6d608425a0868956721bd9aca4812c8ec11041fbb91d","observation_id":"7f95e591-944e-453d-88d7-d918a7186e96","resolution":{"observed_at":"2026-08-07T13:27:55.594717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:55.435976Z","title":"Large batch optimization for deep learning: Training bert in 76 minutes","venue":null,"work_id":"4b8cf4b5-cd5f-4243-b9ec-fdb7a064358b","year":2020},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:51.959625Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:4e057239e756c20cad1ceac200d8b906c7938f674108852be732593f8773dedb","observation_id":"142e6176-d48b-4ab0-82de-ae8065d4b708","resolution":{"observed_at":"2026-08-07T13:27:55.477732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:55.297185Z","title":"Width & depth pruning for vision transformers","venue":null,"work_id":"e47ded8b-b495-4af7-a45d-6af887a9d2eb","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:52.046635Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:be3e8fce9cd4c268bf0598608074d694c51ec5fa33f69a567f828ed7335510d8","observation_id":"b78f0dae-a69b-4b29-8f3e-b797d3f6343a","resolution":{"observed_at":"2026-08-07T13:27:55.384890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:55.073929Z","title":"and Xiang, W","venue":null,"work_id":"a7231de9-4277-40be-bed6-158068389855","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:52.195065Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:8dbe4305ed550d54123ead67eafec282700b8f1ed3b315da72bcf95192cba1c1","observation_id":"305e0de4-e5f0-4e51-a0a7-1ac43ff86ced","resolution":{"observed_at":"2026-08-07T13:27:55.179975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:54.861695Z","title":"Unified visual transformer compression","venue":null,"work_id":"2544c3e9-e12a-4430-a76c-c4367a20a43e","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:52.277117Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:b7213866b974e45dde73227be91f57f8e668d303a7e77494cc7d563c9a435a1e","observation_id":"3ac8b611-267f-4a40-a11e-ee862bb4c0c6","resolution":{"observed_at":"2026-08-07T13:27:54.959345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:54.616125Z","title":"Metaformer is actually what you need for vision","venue":null,"work_id":"27059072-e3cf-4ae0-8520-ce161b3edc8d","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:52.411959Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:84c31e4fa479961f7894f9c1f0ed31df0275eb8ee8af7f5b353d8dc5aaafa611","observation_id":"8b4d8ded-bdd4-42b6-9a3e-060e100cecf5","resolution":{"observed_at":"2026-08-07T13:27:54.749064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:54.246230Z","title":"Dense vision transformer compression with few samples","venue":null,"work_id":"44ca16b2-42db-49a4-9ecb-4b5ef5cd2685","year":2024},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:52.508299Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:af44172b1cdafd66eeb041f6f593a2f91f60a4acdbad719c9977eb8d1409e401","observation_id":"259ca026-1a4e-436c-bc1d-a65ece044b40","resolution":{"observed_at":"2026-08-07T13:27:54.412604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:53.947918Z","title":"Rethinking mobile block for efficient attention-based models","venue":null,"work_id":"17d052d6-b782-4cab-b5c0-0876892f47e1","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:52.594816Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:b8fd9e14c8133783fbccb69f3bc3f2e182e56ba347efe9a3d66b4327e543da7b","observation_id":"43b9cfba-efb7-41c5-b52c-8bebd30db120","resolution":{"observed_at":"2026-08-07T13:27:54.076400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:53.698901Z","title":"Scene parsing through ade20k dataset","venue":null,"work_id":"e3cdd1af-c339-4646-aae0-7d4e7cfdbedd","year":2017},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:52.716081Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:bc14c90336db9b54352fc4d688651b92d6c7d2a39d462b49b32ea3b57e3c0ac0","observation_id":"5c58d379-8672-4e26-93fd-3cf9774fa3fa","resolution":{"observed_at":"2026-08-07T13:27:53.796137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:53.479601Z","title":"Structural reparameterization lightweight network for video action recognition","venue":null,"work_id":"420bcf25-43cd-4eab-b076-161dca6e2772","year":2023},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:52.872038Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:924732b15bf7232f39d350629919597b50d70fd18b0df43759b047c399159c85","observation_id":"3591acdd-0f44-4d43-8dc3-46089805a773","resolution":{"observed_at":"2026-08-07T13:27:53.577698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T13:27:53.213723Z","title":"Self-slimmed vision transformer","venue":null,"work_id":"a976ff8b-0957-40b0-a0f5-140b38f2416f","year":2022},"citing_paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","version":2},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-07T13:27:53.028375Z"},"links":{"citing_paper":"/paper/2505.21847"},"observation_digest":"sha256:5bf9ff6e1977e5fec4b015c36c6fbbba8a544201d0b029cc42509026f5978847","observation_id":"9ad4d017-621f-4db3-9757-9c69379ab265","resolution":{"observed_at":"2026-08-07T13:27:53.313550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.21847","last_updated":"2025-06-02T06:39:14Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T13:19:15.827936Z","submitted_at":"2025-05-28T00:27:18Z","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers"},"reference_resolution":{"displayed":75,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":0,"verified_fuzzy":56},"total_outbound_references":75},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 2 inbound Pith citation observations for arXiv:2505.21847."}