{"as_of":"2026-08-10T03:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:81c7b077a4385b18be6412aee72c0ef83520532842b1c58355d5894d741f1897","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:58:08.042634Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T16:34:01.766196Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.04327","snapshot_observed_at":"2026-08-04T16:34:01.766196Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.18171","last_updated":"2026-07-30T06:29:57Z","snapshot_observed_at":"2026-08-08T00:42:05.608636Z","submitted_at":"2025-09-17T13:04:11Z","title":"Dissecting Federated-Graph Aggregation under Domain Shift: Importance-Aware Aggregation via Empirical Analysis","version":5},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T16:34:01.766196Z"},"links":{"cited_paper":"/paper/2507.04327","citing_paper":"/paper/2509.18171"},"observation_digest":"sha256:34b556d23c949f69f98e14613eed3508d388c0bba1519110b2dbb92c42c08510","observation_id":"cced5eb0-e204-4d87-b03b-54d4bfdf0bf3","resolution":{"observed_at":"2026-08-04T16:34:01.766196Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2507.04327/citation-record","integrity":"/paper/2507.04327/integrity","json":"/paper/2507.04327/citation-record.json","paper":"/paper/2507.04327"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:58:13.413302Z","title":"A closer look at memorization in deep networks","venue":null,"work_id":"f1dbea87-f0f4-4872-9ac7-3caef6d00fc1","year":2017},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:02.411193Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:509bdc3282d646f0d8d106aa4983601cb71b4945bbabc95cc821261c1b56da0f","observation_id":"d4045c70-4eb5-46ba-8bf7-2e44f5287ccb","resolution":{"observed_at":"2026-08-06T19:58:13.466468Z","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":"2107.00778","last_updated":"2022-07-11T02:47:28Z","snapshot_observed_at":"2026-08-09T03:11:40.819888Z","submitted_at":"2021-07-02T00:25:48Z","title":"On Bridging Generic and Personalized Federated Learning for Image Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.00778","snapshot_observed_at":"2026-08-06T19:58:02.524288Z","title":"On bridging generic and personalized federated learning for image classification","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:02.524288Z"},"links":{"cited_paper":"/paper/2107.00778","citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:18ade6c4452858b22546da12b87ffb56c60713f889b233b5fc1ed0862bcbab6b","observation_id":"5d440f1a-c9d8-4f5b-b24b-e82a7b8f3cab","resolution":{"observed_at":"2026-08-06T19:58:02.524288Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-06T19:58:02.676986Z","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:02.676986Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:bbcdafd2e333e36bfcc176471d15b430543fa72c2247b71d802a4730f057f271","observation_id":"3b38c31c-bfd5-46bf-9856-a648ab3e6a2a","resolution":{"observed_at":"2026-08-06T19:58:02.676986Z","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":"2026-08-06T19:58:13.231027Z","title":"Learning both weights and connections for efficient neural network","venue":null,"work_id":"669f8f57-a85f-4070-bebe-5141af24dde0","year":2015},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:02.788523Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:9933583980f414d13a42f4c258e043c6d97756b492179751516d5f989ba39ced","observation_id":"901d3977-9a0f-420f-a891-e2c76f7f4406","resolution":{"observed_at":"2026-08-06T19:58:13.273919Z","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":"2026-08-06T19:58:13.017161Z","title":"Adaptive gradient sparsification for efficient federated learning: An online learning approach","venue":null,"work_id":"d36a41ca-3982-4206-9603-9d8056c53964","year":2020},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:02.935992Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:301f9ae116f6154ea7ba415e73d52a1cb09046e183d40d6affdc5ece15d4af82","observation_id":"0bc48bfe-3640-46b9-b7e6-3b8d4c2f4507","resolution":{"observed_at":"2026-08-06T19:58:13.117541Z","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":"1811.11479","last_updated":"2023-10-19T14:11:11Z","snapshot_observed_at":"2026-07-06T07:17:33.790455Z","submitted_at":"2018-11-28T10:16:18Z","title":"Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.11479","snapshot_observed_at":"2026-08-06T19:58:03.078462Z","title":"Communication-efficient on-device machine learning: Federated distillation and augmentation under non-iid private data","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:03.078462Z"},"links":{"cited_paper":"/paper/1811.11479","citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:771cee5ab35b3a7e2c4cefdffcf00dae0bd5bf55f383c0469d44d62df03c68e3","observation_id":"edc44092-28c0-4a53-9df2-8b9a18b18023","resolution":{"observed_at":"2026-08-06T19:58:03.078462Z","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":"2026-08-06T19:58:12.753348Z","title":"Model pruning enables efficient federated learning on edge devices","venue":null,"work_id":"495b995f-7a05-40fb-bcfd-5ae98bcc3561","year":2022},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:03.195505Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:d969d98a5834ce95d4e4d9fbaf893e748e66e627110325a22947b9b46e4fcadb","observation_id":"c5c1fcc7-e6e2-4417-aeb5-336ab6be5b19","resolution":{"observed_at":"2026-08-06T19:58:12.893976Z","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":"2026-08-06T19:58:12.574283Z","title":"Scaffold: Stochastic controlled averaging for federated learning","venue":null,"work_id":"b6c45332-6c18-4597-9c74-e4c8e5797353","year":2020},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:03.317764Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:d24053c81713e3dbc9318dfe64850e5618f6661a869e122408df46d1d4ed27d5","observation_id":"b821cb1b-46af-4192-bd22-20738002f114","resolution":{"observed_at":"2026-08-06T19:58:12.637286Z","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":"2026-08-06T19:58:12.394579Z","title":"Generalization in deep learning","venue":null,"work_id":"3549e3cc-899b-4ac2-aae8-8758d9bf9251","year":2022},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:03.461395Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:fdb460cda002ef0c5a602af94fe0c32dba8c2407b621e4844d18fd5ce41dc480","observation_id":"a3136115-a661-43ed-9ef1-fbbdd2ddc028","resolution":{"observed_at":"2026-08-06T19:58:12.434851Z","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":"2026-08-06T19:58:03.620208Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:03.620208Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:dbe240e37d02883e5ab3c352d433d80e3d34786beb3841b1ffbd06485f65842e","observation_id":"d3696532-da5c-457d-bf64-97cd09a4cfb9","resolution":{"observed_at":"2026-08-06T19:58:03.620208Z","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":"2026-08-06T19:58:12.217165Z","title":"Tiny imagenet visual recognition challenge","venue":null,"work_id":"6b723ee0-429a-4089-9848-51c6ac3cb06f","year":2015},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:03.746666Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:691f947bfc9d123fb429aceb45da4fb53c10fa7975b06df732c22d19a05ca5c5","observation_id":"4ce182b3-8232-4b24-be9d-c94de59e2aa6","resolution":{"observed_at":"2026-08-06T19:58:12.284304Z","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":"1910.03581","last_updated":"2019-10-08T18:00:00Z","snapshot_observed_at":"2026-08-08T12:31:54.297762Z","submitted_at":"2019-10-08T18:00:00Z","title":"FedMD: Heterogenous Federated Learning via Model Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.03581","snapshot_observed_at":"2026-08-06T19:58:03.877147Z","title":"Fedmd: Heterogenous federated learning via model distillation","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:03.877147Z"},"links":{"cited_paper":"/paper/1910.03581","citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:4335b20bb91cfc4373091524b0f48074356987077bb2fe23f220ea3716a8d484","observation_id":"9ebd229b-ba65-45e6-a435-78762dbdfb95","resolution":{"observed_at":"2026-08-06T19:58:03.877147Z","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":"2026-08-06T19:58:11.991921Z","title":"Fedmask: Joint computation and communication-efficient personalized federated learning via heterogeneous masking","venue":null,"work_id":"d6191220-05a1-4160-b79e-29f98ae4666b","year":2021},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:03.989584Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:9a81d19477108351ad030c5095b2f285a0f9eb3963e8b1ea9f81ce6510eae93f","observation_id":"78a4d471-2467-4048-bcca-6410c45f09e8","resolution":{"observed_at":"2026-08-06T19:58:12.087417Z","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":"2001.01523","last_updated":"2020-07-14T08:12:35Z","snapshot_observed_at":"2026-08-04T05:35:18.088525Z","submitted_at":"2020-01-06T12:40:21Z","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.01523","snapshot_observed_at":"2026-08-06T19:58:04.102767Z","title":"Think locally, act globally: Federated learning with local and global representations","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:04.102767Z"},"links":{"cited_paper":"/paper/2001.01523","citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:bf4e8baf54ed2ceb8b9ee190c680f27c29abba8a0ac26c9a4e59a5eb6ed76e96","observation_id":"b0cc8246-dfdf-465e-bdb2-229ae921c9ab","resolution":{"observed_at":"2026-08-06T19:58:04.102767Z","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":"2026-08-06T19:58:11.830426Z","title":"Ensemble distillation for robust model fusion in federated learning","venue":null,"work_id":"1470acaa-4e2c-4b25-a3d3-48b5f283dfad","year":2020},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:04.147898Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:f02d2eff7141e24ba97de65a59e739ee57553268a529fab5960766d79330a364","observation_id":"fb342a09-8ea3-4dfd-95d6-084fb8e79c03","resolution":{"observed_at":"2026-08-06T19:58:11.897390Z","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":"1903.06733","last_updated":"2020-10-21T19:19:02Z","snapshot_observed_at":"2026-07-06T07:39:37.521800Z","submitted_at":"2019-03-15T18:23:55Z","title":"Dying ReLU and Initialization: Theory and Numerical Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.06733","snapshot_observed_at":"2026-08-06T19:58:04.270657Z","title":"Dying relu and initialization: Theory and numerical examples","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:04.270657Z"},"links":{"cited_paper":"/paper/1903.06733","citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:fa215c3caee88abb6ebc080a7e3e5dce17a784a1da1c6478f45360483b0e30f7","observation_id":"d717e8d7-65e4-46d2-a40c-dc2188495c62","resolution":{"observed_at":"2026-08-06T19:58:04.270657Z","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":"2026-08-06T19:58:04.468063Z","title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:04.468063Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:017cd79088269cc15fe1470e42fabee131829b29fef11205fa4d0d01194d3c30","observation_id":"829ca56c-eaae-427b-a421-8ad2931befdc","resolution":{"observed_at":"2026-08-06T19:58:04.468063Z","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":"2026-08-06T19:58:04.673717Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:04.673717Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:39d243d24d8473be1e46c046589e8ebf60cfe7a026fadb74d940c4ea2b484d6c","observation_id":"1b451d9c-2482-4c2f-bbe5-fb3b8cc138bc","resolution":{"observed_at":"2026-08-06T19:58:04.673717Z","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":"2026-08-06T19:58:11.622893Z","title":"Federated learning for internet of things: A comprehensive survey","venue":null,"work_id":"528b433c-996b-4ad3-8101-bb5d39fb6c0c","year":2021},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:04.808335Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:8e9562b45840d87db2768f01753143bb16d46b116bacfe83edf64a3dc6a68998","observation_id":"0fc3b891-44f5-4fe0-9eec-fd780e0ed7ce","resolution":{"observed_at":"2026-08-06T19:58:11.712432Z","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":"2026-08-06T19:58:04.996681Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:04.996681Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:c5148fe9e800d0652c876ac1eb32760bd869ef9fd5fc9ca772ffe09b3228f816","observation_id":"683fd920-b804-4bf8-a429-62fc3c7ee4e1","resolution":{"observed_at":"2026-08-06T19:58:04.996681Z","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":"2026-08-06T19:58:11.440950Z","title":"Robust and communication-efficient federated learning from non-iid data","venue":null,"work_id":"8ca89363-de0a-432e-8a0b-69c2b8f321e3","year":2019},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:05.143424Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:22190e9b3e266401868a5a8354f457dbbe58fee7c2d5377f077d92dde29ef3ef","observation_id":"eb6a18fd-c09e-40c3-80d7-e38dadbe3e5c","resolution":{"observed_at":"2026-08-06T19:58:11.538679Z","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":"2006.16765","last_updated":"2020-09-17T06:10:24Z","snapshot_observed_at":"2026-08-06T16:08:53.133968Z","submitted_at":"2020-06-27T09:35:03Z","title":"Federated Mutual Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.16765","snapshot_observed_at":"2026-08-06T19:58:05.327855Z","title":"Federated mutual learning","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:05.327855Z"},"links":{"cited_paper":"/paper/2006.16765","citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:1a49bc060e4d65aaec7b9233e01122d75e6969bb4f8990b1f59b6319280f59c3","observation_id":"5d864a07-255b-44c4-a23b-9a0acb88fbf5","resolution":{"observed_at":"2026-08-06T19:58:05.327855Z","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":"2026-08-06T19:58:11.186814Z","title":"Sparsified sgd with memory","venue":null,"work_id":"3e5c0e1d-0d36-4127-9655-7256d144b53b","year":2018},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:05.420685Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:17c81c6af13e1270d15df52248f0064d8673f363bdf3155561cc21242c6c487f","observation_id":"543c51ca-132d-46b7-a1e0-0380b9f9c4d3","resolution":{"observed_at":"2026-08-06T19:58:11.337581Z","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":"2026-08-06T19:58:11.012015Z","title":"Going deeper with convolutions","venue":null,"work_id":"36e205be-5b38-4ef3-88d4-82c9502c1e3f","year":2015},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:05.563029Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:5bf37f9fe2986a69f1356543f4d260cea1c7b5a8b48323db0e88fffcc71a89d1","observation_id":"a2128a58-ac7f-4534-80ef-c2acf95a54cc","resolution":{"observed_at":"2026-08-06T19:58:11.093312Z","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":"2026-08-06T19:58:10.819068Z","title":"Fedproto: Federated prototype learning across heterogeneous clients","venue":null,"work_id":"f83fc89e-2687-49a9-8733-9b758fed380c","year":2022},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:05.711301Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:15aea8fae8a58f4fd77c1c2ac47e99cf735954445f298b652fcc3f02d5890279","observation_id":"df3dffa6-554c-4400-9fa7-31134059fa3f","resolution":{"observed_at":"2026-08-06T19:58:10.901001Z","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":"1905.11946","last_updated":"2020-09-11T05:08:01Z","snapshot_observed_at":"2026-08-06T22:36:56.473526Z","submitted_at":"2019-05-28T17:05:32Z","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11946","snapshot_observed_at":"2026-08-06T19:58:05.874253Z","title":"Efficientnet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:05.874253Z"},"links":{"cited_paper":"/paper/1905.11946","citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:35d60e44f2051b7d9faf0d29cbadc7341d90977a545d08a0eb13927845c11ef9","observation_id":"504c5b3d-4b2c-484b-8168-48ef408e73a9","resolution":{"observed_at":"2026-08-06T19:58:05.874253Z","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":"2026-08-06T19:58:10.598803Z","title":"Adaptive communication strategies to achieve the best error-runtime trade-off in local-update sgd","venue":null,"work_id":"977e8d59-144e-4912-836e-547fb546fb59","year":2019},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:06.084557Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:8d9198541c6e5052e51d8816064840441024ea0215ec568df5ef2d8fedd28e34","observation_id":"dc41ef2a-6b5c-44c8-8cc5-9f72379846dd","resolution":{"observed_at":"2026-08-06T19:58:10.669895Z","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":"2026-08-06T19:58:10.429107Z","title":"Adaptive federated learning in resource constrained edge computing systems","venue":null,"work_id":"31754260-0aba-49dc-9f2c-b98829c3ef39","year":2019},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:06.202668Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:2f6f4b1cfa25f766d28834967e14bdb1b28c59663265ae64ad9e99e2e944fedb","observation_id":"9b4e727c-7e1b-41ce-ac9b-683cec4353ad","resolution":{"observed_at":"2026-08-06T19:58:10.511700Z","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":"2026-08-06T19:58:10.231555Z","title":"Svdfed: Enabling communication-efficient federated learning via singular-value-decomposition","venue":null,"work_id":"f641ad1b-9b07-4816-a956-387bfda4e7e6","year":2023},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:06.320204Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:a1cd6f4c0d09be7b0641d412e42036b37d9e14b6b25d8056f2eb6aef0a7f7224","observation_id":"8fea26e8-b2ae-4c65-a4fc-0412f3f4a546","resolution":{"observed_at":"2026-08-06T19:58:10.337255Z","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":"2026-08-06T19:58:10.029164Z","title":"Why go full? elevating federated learning through partial network updates, 2024","venue":null,"work_id":"e62f8575-681d-4497-bdd1-1cf9e2d10c12","year":2024},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:06.444688Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:ae84fd65afd98fad2f41e8575269bb9ca1f29ea740e935aa42aea40099db8807","observation_id":"f4e7dba8-54ce-4287-b115-2202127864bb","resolution":{"observed_at":"2026-08-06T19:58:10.116155Z","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":"2026-08-06T19:58:09.875414Z","title":"Learning structured sparsity in deep neural networks","venue":null,"work_id":"c5faf830-2f83-44ed-bd00-9bf2b0e95d3d","year":2016},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:06.646535Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:57b86c1a780be2847ab2a9287a180dbd9e64d06b8b72ad4ed38d6dd7c5e0d23c","observation_id":"914d7d3e-4ae8-4684-b9a3-fe609b05eaa7","resolution":{"observed_at":"2026-08-06T19:58:09.924163Z","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":"2026-08-06T19:58:09.720845Z","title":"Communication-efficient federated learning via knowledge distillation","venue":null,"work_id":"22735ac2-95a0-442e-a7a0-af717a564c52","year":2022},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:07.171896Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:ec97047699e63c8b9f424b51d66eeaebce9c1154ad7b373a13214f09a43e83ea","observation_id":"f3282917-d449-4674-92c8-395f556399e2","resolution":{"observed_at":"2026-08-06T19:58:09.776984Z","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":"2026-08-06T19:58:09.538779Z","title":"Efficient federated learning on resource-constrained edge devices based on model pruning","venue":null,"work_id":"48d9f1b9-6832-4e9e-b448-95c69260a76d","year":2023},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:07.357156Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:99797dac809c48051e1c17fa8ef09e4117fd987d20b933f172f53de18a739e36","observation_id":"2cb3fdb0-ccbb-4f60-912e-bc5376e3e6f4","resolution":{"observed_at":"2026-08-06T19:58:09.590838Z","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":"2026-08-06T19:58:09.400613Z","title":"Decoupling general and personalized knowledge in federated learning via additive and low-rank decomposition","venue":null,"work_id":"179fc20a-a620-4d5e-a97e-40865b6a1ea0","year":2024},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:07.425519Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:1222ab26ea9cd10309c19a2ee81de75e855cf5f372c7f018b3c933a2da4ef8d7","observation_id":"b72ecaf8-f28c-4ee1-bdb7-a55b0a8177ad","resolution":{"observed_at":"2026-08-06T19:58:09.463497Z","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":"2026-08-06T19:58:09.257423Z","title":"Deep mutual learning","venue":null,"work_id":"886a8dbc-5b31-4507-96ef-560c8569e2ed","year":2018},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:07.505838Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:1770aa7b6994114c6dfaf9abc1cfee8fe59cf5d2ba35316517f625e8efbeff5d","observation_id":"b8c005eb-ca68-45a9-9bd8-507abe73ea2a","resolution":{"observed_at":"2026-08-06T19:58:09.305216Z","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":"2026-08-06T19:58:09.020255Z","title":"A survey on federated learning","venue":null,"work_id":"90d5c12b-cd0c-4e20-9dc2-4c0ff9b7734f","year":2021},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:07.570897Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:4033d6e942a72e6175903a0ae9cfea893044a3e4f77672a3b54050d86b63d597","observation_id":"832b6537-f95b-4e1e-886b-5e3bb9b6779f","resolution":{"observed_at":"2026-08-06T19:58:09.117064Z","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":"2026-08-06T19:58:08.897377Z","title":"Understanding deep learning (still) requires rethinking generalization","venue":null,"work_id":"676c5265-6353-4f54-99c1-ea6534d32726","year":2021},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:07.652956Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:9b49a17966d7dc8a42faf2bebf071687e6b99f2fb693d876103161f71c6b15dc","observation_id":"5c1533fb-a585-412b-8cf4-6ed9b1301f76","resolution":{"observed_at":"2026-08-06T19:58:08.956480Z","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":"2204.11536","last_updated":"2022-04-25T10:00:00Z","snapshot_observed_at":"2026-07-06T13:03:26.093481Z","submitted_at":"2022-04-25T10:00:00Z","title":"FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server","version":1},"cited_work":{"arxiv_id":"2204.11536","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.11536","snapshot_observed_at":"2026-08-06T19:58:08.162265Z","title":"FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server","venue":"cs.DC","work_id":"54865bbc-2b7a-4894-b48f-efb3c54cd44a","year":2022},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:07.750187Z"},"links":{"cited_paper":"/paper/2204.11536","citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:7223ee4d152d93af9e7972d55754e7766c7de98b1d0b50166ffef4faa1b310e2","observation_id":"4984c758-471c-4f4c-9dfd-1e33819bd3e4","resolution":{"observed_at":"2026-08-06T19:58:08.218163Z","resolver_source":"local_arxiv","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:58:08.736561Z","title":"Fedtgp: Trainable global prototypes with adaptive-margin-enhanced contrastive learning for data and model heterogeneity in federated learning","venue":null,"work_id":"e79c83f3-d5d3-4d2f-ac53-68b3c612bb0a","year":2024},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:07.824937Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:e81a91f6d5914219453426d10630b9ad3bff177d3c5734a5c723b98937fc17e5","observation_id":"b26abde1-92d7-40cf-a295-bbb59b16b9ed","resolution":{"observed_at":"2026-08-06T19:58:08.821914Z","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":"2026-08-06T19:58:08.566314Z","title":"Deep residual networks for hyperspectral image classification","venue":null,"work_id":"d99c05a9-a2e8-4092-95ac-05127d22ccc7","year":2017},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:07.886678Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:d58e6ee87abf7164cd9a82c27a966f404f8c9becc9c0df9808bf13c7691401a3","observation_id":"dd3a3136-5241-4e3e-8b87-c2875a2a84d3","resolution":{"observed_at":"2026-08-06T19:58:08.669715Z","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":"2026-08-06T19:58:08.459759Z","title":"Data-Free Knowledge Distillation for Heterogeneous Federated Learning","venue":null,"work_id":"20ac4528-c0e6-4b49-850b-ca83351bbc4a","year":2021},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:07.957911Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:efb5b09c34ef0931e618df932b63bf6d02e61360c7b3dbf51b6cd01e2cfee6d1","observation_id":"ebf3137c-04a2-4171-bd2e-c791c3bac591","resolution":{"observed_at":"2026-08-06T19:58:08.500797Z","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":"2026-08-06T19:58:08.042634Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-06T19:58:08.042634Z"},"links":{"citing_paper":"/paper/2507.04327"},"observation_digest":"sha256:1e07778ba563876b057d9ef48828377aac870c94ca97374ac7a794b1ad475d97","observation_id":"468c7c52-6981-43f1-9137-5f1279b08a0c","resolution":{"observed_at":"2026-08-06T19:58:08.042634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.04327","last_updated":"2025-07-06T10:24:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T09:08:49.273243Z","submitted_at":"2025-07-06T10:24:33Z","title":"TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":1,"verified_fuzzy":28},"total_outbound_references":42},"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 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2507.04327."}