{"as_of":"2026-08-20T16:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6983cf6ae13a2be14c57401fdd89dd5f30529aa9f7bb4654e4a42c34d1ae3f0d","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:13:22.702695Z","state":"measured"},{"denominator":50,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":50,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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":"2026-05-08T02:46:34.459345Z","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":"2026-05-11T22:26:13.827521Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"cited_work":{"arxiv_id":"2507.07130","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.07130","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ba360e05-d23f-4b55-868c-fe6e77aaa193","year":2025},"citing_paper":{"arxiv_id":"2604.24468","last_updated":"2026-04-27T13:36:54Z","snapshot_observed_at":"2026-08-15T16:42:40.259851Z","submitted_at":"2026-04-27T13:36:54Z","title":"A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations","version":1},"reference_index":175,"source":"pdf_text","source_observed_at":"2026-05-08T02:46:34.459345Z"},"links":{"cited_paper":"/paper/2507.07130","citing_paper":"/paper/2604.24468"},"observation_digest":"sha256:8d86c1a4683bfd8f14a6334767413c7408ec12efe815fe12203665c4b323a8a5","observation_id":"ec375b67-75a7-4143-bb97-a1d73bb3f0f5","resolution":{"observed_at":"2026-05-11T22:26:13.829650Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.07130/citation-record","integrity":"/paper/2507.07130/integrity","json":"/paper/2507.07130/citation-record.json","paper":"/paper/2507.07130"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:32.971686Z","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data,","venue":null,"work_id":"513e3b39-ffb9-42f1-9023-e2ecd734159d","year":2016},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:18.766069Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:9f74081efd33cb4ea1890630a83a64781b8503310fdbc089fec0562281c4f57f","observation_id":"cc70f505-c66a-4b47-8e3e-0e4c3f1bc3c5","resolution":{"observed_at":"2026-08-06T19:13:33.056975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:32.780393Z","title":"Federated Optimiza- tion: Distributed Optimization Beyond the Datacenter,","venue":null,"work_id":"c7a0362a-2d13-46c5-bc1a-04e620474afd","year":2015},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:18.834411Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:284a7bf30702146c39c1233b84cb069be69fa2bd42b33e338940aacac20baa52","observation_id":"48370a9f-1008-4339-8487-0f1b7e86b83e","resolution":{"observed_at":"2026-08-06T19:13:32.870674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1610.02527","last_updated":"2016-10-08T13:25:15Z","snapshot_observed_at":"2026-08-17T09:22:54.525990Z","submitted_at":"2016-10-08T13:25:15Z","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02527","snapshot_observed_at":"2026-08-06T19:13:18.970240Z","title":"Feder- ated Optimization: Distributed Machine Learning for On-Device Intelligence,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:18.970240Z"},"links":{"cited_paper":"/paper/1610.02527","citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:2f0e7e72eba0292bf634a1208e4974cb3956279b9468684f65201918427cbad7","observation_id":"42955b8f-bef0-4e42-ab0c-97f6f8fe03ae","resolution":{"observed_at":"2026-08-06T19:13:18.970240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.05492","last_updated":"2017-10-30T20:52:14Z","snapshot_observed_at":"2026-08-13T17:19:46.488095Z","submitted_at":"2016-10-18T09:11:51Z","title":"Federated Learning: Strategies for Improving Communication Efficiency","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.05492","snapshot_observed_at":"2026-08-06T19:13:19.036042Z","title":"Federated Learning: Strategies for Improving Communication Efficiency,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:19.036042Z"},"links":{"cited_paper":"/paper/1610.05492","citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:759d2f5bc6a2b89383c9a5a2aca50452bd9da3d37031c9833d4bbf2881c9d46b","observation_id":"461dd6a4-e42a-4e34-950c-40fd82831713","resolution":{"observed_at":"2026-08-06T19:13:19.036042Z","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":"2026-08-06T19:13:32.583067Z","title":"SplitFed: When Federated Learning Meets Split Learning,","venue":null,"work_id":"7284952e-379a-4368-a08c-63ebef2ee909","year":2022},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:19.182534Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:35a995c0ddde8c9e356b8154c6013369010ceee58e41c9aa5972e283306b46d5","observation_id":"1e67f638-5d90-40e9-beb0-141ae5db9aba","resolution":{"observed_at":"2026-08-06T19:13:32.691499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:32.374838Z","title":"BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems,","venue":null,"work_id":"ce35e0eb-58c2-4151-acaf-3ee6885cb89f","year":2020},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:19.322638Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:da70c33b420416789fc6ac66bb44b4af3bc16918c4291a151b912199adb8f8cc","observation_id":"8e6b2c1a-c577-41d4-88ff-ea4f105d7f01","resolution":{"observed_at":"2026-08-06T19:13:32.466825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:32.133700Z","title":"C3-SL: Circular Convolution-Based Batch-Wise Compression for Communication- Efficient Split Learning,","venue":null,"work_id":"afe77081-24a6-4df0-bed7-fc961c8c16fc","year":2022},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:19.404280Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:4d306daef39286cba0e7bd7316ee88805dc75bb57ddf3fe053e7ddb9e6cf6f29","observation_id":"ea06af95-15b3-42dd-82fd-727de8c020c3","resolution":{"observed_at":"2026-08-06T19:13:32.265806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:31.950484Z","title":"Back-And-Forth Prediction for Deep Tensor Compression,","venue":null,"work_id":"65701d22-c07c-46f8-b599-be65042c7e47","year":2020},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:19.538610Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:d88283613af781ca25fd6c4a11c2dcaa823ac4bb091d66e719bf4cebf3edf424","observation_id":"e204a302-1c95-42ff-80eb-0790d49f6980","resolution":{"observed_at":"2026-08-06T19:13:32.032455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:31.784088Z","title":"Reducing Communication for Split Learning by Randomized Top-k Sparsification,","venue":null,"work_id":"b70363fe-3b11-4ab2-8f4f-34de49ffad80","year":2023},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:19.706504Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:5f53e2633a466bb90fed319c797857fd46a0d94db0c6d332badeda0cffc6f234","observation_id":"a2cde4b6-e341-4e05-a8e7-9fa392a4ba7a","resolution":{"observed_at":"2026-08-06T19:13:31.864170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:31.581924Z","title":"EcoFed: Efficient Communication for DNN Partitioning- Based Federated Learning ,","venue":null,"work_id":"f777033e-7ba3-46d1-8da6-f6b14fcc2913","year":2024},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:19.919814Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:c455eef1b0c93700d24f69490e5a02a4775b39b9766c41565f148744ee49d0f8","observation_id":"647224bd-c856-4986-aaf6-b5d4469ae0fa","resolution":{"observed_at":"2026-08-06T19:13:31.661012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:31.296728Z","title":"PiPar: Pipeline Parallelism for Collaborative Machine Learning,","venue":null,"work_id":"5d6b4117-a97a-4650-ad40-191e765f13ad","year":2024},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.046251Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:33d02a60f4d365df4dacb8a85eb89e8c0c2bf0fd5ff28f761ef534298735cbc9","observation_id":"0b574e7c-0289-4300-b54f-f5c482cd07ce","resolution":{"observed_at":"2026-08-06T19:13:31.426709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:31.074007Z","title":"SplitGP: Achieving Both Generalization and Personalization in Federated Learning,","venue":null,"work_id":"483eac30-1072-4fbe-afbe-74655b9fc6c0","year":2023},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.150391Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:6e321ecddb46a9babffc8afafa266de963775f64f9bb6da4dad61a873a4862f4","observation_id":"efce2553-8b0a-4650-b7a5-5523067f9c14","resolution":{"observed_at":"2026-08-06T19:13:31.182399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:30.787693Z","title":"Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge,","venue":null,"work_id":"a3620370-9518-4665-8e4d-e847c94efa94","year":2020},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.223240Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:438da17d6192840d5f9743880caa927ffb947aa5dae5fa83833696e2be514a38","observation_id":"96b63008-bb54-46c4-8155-bb67b4b456c0","resolution":{"observed_at":"2026-08-06T19:13:30.941635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06335","last_updated":"2019-09-13T17:26:20Z","snapshot_observed_at":"2026-08-16T05:00:17.345539Z","submitted_at":"2019-09-13T17:26:20Z","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.06335","snapshot_observed_at":"2026-08-06T19:13:20.311415Z","title":"Measuring the Effects of Non- Identical Data Distribution for Federated Visual Classification,","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.311415Z"},"links":{"cited_paper":"/paper/1909.06335","citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:5a33aef508f897f644a2038323fe7d2958d9071f60b9d2d7128c04ffbb29eb98","observation_id":"09656b19-d1d8-4033-bec4-6b2f22a4df0b","resolution":{"observed_at":"2026-08-06T19:13:20.311415Z","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":"2026-08-06T19:13:30.487588Z","title":"Federated Optimization in Heterogeneous Networks,","venue":null,"work_id":"083b78e9-1aac-404e-a2b5-f6af858677a9","year":2020},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.414441Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:ec834b6766c779fefa16e0e97dfe91956d07760d74d6f5b8d35e139f000381fa","observation_id":"22758b9f-aa42-4e52-81c1-14b6fdc5ccc3","resolution":{"observed_at":"2026-08-06T19:13:30.605644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:30.211121Z","title":"SCAFFOLD: Stochastic Controlled Averaging for Feder- ated Learning,","venue":null,"work_id":"4d01fbbf-460a-4146-9a68-6f40b0c06a07","year":2020},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.449196Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:2ada70624a1b974031d50dc66d79634e1cdae650bec3d2758889d545e98a1f54","observation_id":"8a6ab77c-f024-4984-b758-6a0507a23fe8","resolution":{"observed_at":"2026-08-06T19:13:30.365534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:29.883811Z","title":"Searching for MobileNetV3,","venue":null,"work_id":"b2513930-9953-485a-ad09-b9c09f109c22","year":2019},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.508237Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:4a2ed0a6b21de37337b0db498ad5829bff25633ebf3e5fd39ef52cabfe4398df","observation_id":"652208fb-2343-4418-8e98-3fbe5a69f403","resolution":{"observed_at":"2026-08-06T19:13:30.030185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:29.545951Z","title":"CIFAR-10 (Canadian Institute for Advanced Research),","venue":null,"work_id":"87dc2b40-87b7-46ff-bc38-f19b559b1ac7","year":2009},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.585055Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:7e4b658a260ace935bc4d9f164d5de6aaab465d45d7756a5d83f88edb7a3c336","observation_id":"326e916f-2fde-4adb-a984-94ff45a81049","resolution":{"observed_at":"2026-08-06T19:13:29.714754Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:29.238683Z","title":"Learning Multiple Layers of Fea- tures from Tiny Images,","venue":null,"work_id":"761ff805-33d8-4f28-ae4f-411ef930ed55","year":2009},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.649444Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:95a0a01bf179e8d101b9948b947457fac2d0967faab8dbc0cb48f89584963f28","observation_id":"ea2d6c04-018a-4489-ac25-1b2ecfdc4f89","resolution":{"observed_at":"2026-08-06T19:13:29.385935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:28.933555Z","title":"FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning,","venue":null,"work_id":"bd05f73e-35b2-4e60-a0d3-03d2c3bcaa51","year":2022},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.716467Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:ed8366b866f21c2ebe775b79ebe54c1cb612c232ed33cbb30e42553e2dc8e4e3","observation_id":"4707c891-1cf8-42cb-af97-64f1428751be","resolution":{"observed_at":"2026-08-06T19:13:29.099974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:28.621881Z","title":"Visualizing and Understanding Con- volutional Networks,","venue":null,"work_id":"4ada4861-c1f0-44d7-bdb6-ab7a44befb6a","year":2014},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.766777Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:15ebd950543ad8f1e7276b579e85837f8308761764a60c17c6bb46dc2f6331da","observation_id":"93ecfa01-e8be-4ebb-adff-c15922b02b01","resolution":{"observed_at":"2026-08-06T19:13:28.778597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:28.395063Z","title":"How Transferable Are Features in Deep Neural Networks?","venue":null,"work_id":"57342928-9ea0-4f9a-b0fa-09faeffe571b","year":2014},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.837403Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:bb14091b69ac0cea9821112bae6d860a4ac85fdbdfb849d92510905f75e5c531","observation_id":"ef816cdf-df51-4e4a-b644-87969848252e","resolution":{"observed_at":"2026-08-06T19:13:28.458652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:20.936271Z","title":"Deep Learning,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.936271Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:1a1378abbbe5440c58aace1f49465faa4755f40ce964477fb6469d62bd502189","observation_id":"c791cc88-bc50-426f-a15e-89846d8b2735","resolution":{"observed_at":"2026-08-06T19:13:20.936271Z","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":"2026-08-06T19:13:28.218072Z","title":"On the Convergence of FedAvg on Non-IID Data,","venue":null,"work_id":"e4215ced-038d-486d-9ff2-ad5bba7cd3c6","year":2020},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:20.999497Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:7cb33ff31ee59a5ee0483a688a7d68606e2e90d33bd1bcbd99fd0821322ffd6c","observation_id":"785d7fdd-a1f7-4b60-bd35-4bde6bfa7807","resolution":{"observed_at":"2026-08-06T19:13:28.321320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:27.990865Z","title":"Decoupled Greedy Learning of CNNs,","venue":null,"work_id":"ec1219c9-1d2f-408e-ba50-2c919ac7ed82","year":2020},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.085892Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:f2841891ed2ccabf70a82c6becb1998f10520b3ae0e05e82f55bd27a5199c81d","observation_id":"aba6a8f7-c195-4942-a335-22e4755b5377","resolution":{"observed_at":"2026-08-06T19:13:28.077649Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:27.786542Z","title":"Optimization Methods for Large-Scale Machine Learning,","venue":null,"work_id":"050b4a3f-2433-4ccd-b628-346486e5178c","year":2018},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.151938Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:86a7f192bf29245617fa4726f402dae0facf305c7060a5160417321f175454ea","observation_id":"1a9db59a-e894-45a0-b2fd-9180fb39dc68","resolution":{"observed_at":"2026-08-06T19:13:27.874400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:27.535290Z","title":"Training Neural Networks Using Features Replay,","venue":null,"work_id":"31e7b216-5584-4430-9d3e-eb71c10851a9","year":2018},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.210080Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:99f5e6e96ec0c3e4eaa4923f24d809f4a6eb525cc93bd039a111fb31c94797e0","observation_id":"bdd629d8-530c-4ba8-9919-d2aa4e6fbac6","resolution":{"observed_at":"2026-08-06T19:13:27.671400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:27.267708Z","title":"Communication- Efficient Algorithms for Statistical Optimization,","venue":null,"work_id":"a8c1e3f7-35c8-4abb-b185-ff15de799f5e","year":2013},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.290861Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:e09e87ae5602324c54fe256c7d611e44cf3f7d5c06785356fb2070a25d0c86c8","observation_id":"b9bf4ee0-5859-4b40-b3ed-8c8ea9ada699","resolution":{"observed_at":"2026-08-06T19:13:27.408728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:27.067937Z","title":"Local SGD Converges Fast and Communicates Little,","venue":null,"work_id":"d5ec5cb1-ce6c-48d2-ab53-7643dca21dcb","year":2019},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.347500Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:0240e5fe3b7052ee32669862a0086c264a2db4f472ef47bd429d22811a06a20b","observation_id":"693818fe-946e-4365-b2fc-eda4621a4a1b","resolution":{"observed_at":"2026-08-06T19:13:27.172947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:26.858162Z","title":"Sparsified SGD with memory,","venue":null,"work_id":"80468a93-f61c-4056-afa6-4e9db02dc112","year":2018},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.415131Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:e801931cb0b19c61b87c36677a40964848d6d36e28cf737dc825c99290104560","observation_id":"feadbc2d-75b2-4c28-91dd-be6a270616c5","resolution":{"observed_at":"2026-08-06T19:13:26.961967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:26.534577Z","title":"Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning,","venue":null,"work_id":"f2fcfc92-4aeb-4f03-ba0f-84d51b38dbc9","year":2019},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.488142Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:d4d39c2eb16e123782d461a2611f292d0b99003cf6c5c1816f447f825cd23a9e","observation_id":"e3072f1a-6c9c-4cff-9036-964b8941554d","resolution":{"observed_at":"2026-08-06T19:13:26.733181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:26.263825Z","title":"A Stochastic Approximation Method,","venue":null,"work_id":"ea5d9423-39ff-48c3-8372-9b83098c96fd","year":1951},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.545881Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:972368e41a00a16531e63f842ed5f690438da53b3e2fdc9e88922b0ec1532a59","observation_id":"64e4d054-f586-49fd-aceb-8d8227582539","resolution":{"observed_at":"2026-08-06T19:13:26.375842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:26.034603Z","title":"Scal- ability and Performance Evaluation of Edge Cloud Systems for Latency Constrained Applications,","venue":null,"work_id":"0e1ef532-958d-4b83-ab22-662c90999116","year":2018},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.637183Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:e044518e62ba067fcad226f66759284331a2544eb6b55706ca92b58ef55b34c3","observation_id":"7264ac62-7f5a-4601-bb85-a5ac467f89de","resolution":{"observed_at":"2026-08-06T19:13:26.142646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:25.788643Z","title":"Very Deep Convolutional Net- works for Large-scale Image Recognition,","venue":null,"work_id":"1a74af9d-4eb2-48f2-93f1-c4d938becc12","year":2015},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.716634Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:fbe418d6212ae7471a8edee68d48b12dd8c07cef5b6a0297dbdaa3157898599a","observation_id":"2a963d3d-176f-4dba-a7d0-c9a91ea8d747","resolution":{"observed_at":"2026-08-06T19:13:25.916506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:25.565765Z","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows,","venue":null,"work_id":"441deae8-6db5-487f-98f7-1343d1565221","year":2021},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.769854Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:d1036a1baf0aa65a2bb6164441766ad7e25b94236c3300c60d7cf435434daeac","observation_id":"1d0af53e-08a2-4294-a5b2-8754295b4106","resolution":{"observed_at":"2026-08-06T19:13:25.672820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:25.327000Z","title":"How to Train Your ViT? Data, Augmentation, and Regularization in Vision Transformers,","venue":null,"work_id":"e79c8bd1-7be9-4bf1-bf5a-49bb79649e45","year":2022},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.816799Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:55142df5d2acaeba29b39cfe72c6dadc5ea17aca2635f933bd786acc7d360aab","observation_id":"5885abf2-018c-44e6-a470-50e5b4ded25c","resolution":{"observed_at":"2026-08-06T19:13:25.452109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:25.242021Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,","venue":null,"work_id":"a3527df0-38f0-4bd8-8203-b16866d34bda","year":2021},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.879687Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:797dc27ec7f7b52f4ce08f43fc00e4b23f92a36831fe367bb796e6a84bc5a242","observation_id":"4db76730-e9c4-4a17-8463-6d8d99140e08","resolution":{"observed_at":"2026-08-06T19:13:25.302467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:25.082905Z","title":"ImageNet Large Scale Visual Recognition Challenge,","venue":null,"work_id":"05bc8508-0b01-46ce-bcc4-a2274b6e7267","year":2015},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:21.939501Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:e8f63349389c6962d063b849ec6839491a4fc6d9cf14478ac51f76532e3da42f","observation_id":"cf583858-ddb8-49e7-a9e7-43b4a32bd3c2","resolution":{"observed_at":"2026-08-06T19:13:25.112182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:24.893775Z","title":"Federated Learning Based on Dynamic Regulariza- tion,","venue":null,"work_id":"67c2f1a4-6867-435e-a9f9-c43c4a201d2f","year":2021},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.003603Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:74932a764974892ac18bd9d7ea9506922d38758f19c3fb138aaaf1f2077d1bf9","observation_id":"89876217-a04a-48fa-8940-4ca583206f2f","resolution":{"observed_at":"2026-08-06T19:13:24.965834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:24.677152Z","title":"Early Stopping—But When?","venue":null,"work_id":"fc353b18-cd97-4a5a-8429-c11dc1fe636b","year":2012},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.083952Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:92198528c2b61ef04015d3264968533ecc3be42b5132f403583c048c02e10d29","observation_id":"84036139-31b2-4976-93ca-f06e1e75bad6","resolution":{"observed_at":"2026-08-06T19:13:24.766035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:24.390709Z","title":"Accelerating Federated Learning with Split Learning on Locally Generated Losses,","venue":null,"work_id":"7cd2f80d-a32e-4b91-b454-0d1018321074","year":2021},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.148543Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:dfa25de78835f3ffa3f3c88ede919cb435d41e1646960d353fe506e8f64cbc24","observation_id":"e2c10b3f-ad03-4dc0-b857-fa10f51338a7","resolution":{"observed_at":"2026-08-06T19:13:24.583137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:24.167494Z","title":"ParallelSFL: A Novel Split Federated Learning Framework Tackling Hetero- geneity Issues,","venue":null,"work_id":"97c39761-d873-431e-ba3c-bddd50bd6cba","year":2024},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.253343Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:a1585e90f8d2c96b071601803cb122fb302ded21d6c90d63334e0b2e879ccfe9","observation_id":"8d524260-4174-475f-aca5-7a53ed79ccec","resolution":{"observed_at":"2026-08-06T19:13:24.280995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:23.983286Z","title":"Hermes: An Ef- ficient Federated Learning Framework for Heterogeneous Mobile Clients,","venue":null,"work_id":"7b3b657a-19ba-44a9-9959-bab0eec9e762","year":2021},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.316883Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:1bf800d59a97c0615355ed07938c9b42f4b2afa5e77c0f8450d63a91f632ed82","observation_id":"9346bad1-3b6e-483e-81f8-4c7d5aac186e","resolution":{"observed_at":"2026-08-06T19:13:24.074093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:23.782317Z","title":"Billion-Scale Federated Learning on Mobile Clients: a Submodel Design with Tunable Privacy,","venue":null,"work_id":"579d5097-9815-4a15-9b43-b018720031a4","year":2020},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.391287Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:007ca61c9b5efacb7cbd1f9c9e1a0d0b3e852d05a127389e3e429e2ebb366688","observation_id":"6b96c7d1-6b64-40d0-89ec-9688de53562f","resolution":{"observed_at":"2026-08-06T19:13:23.861411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:23.579215Z","title":"FedHD: Federated Learning with Hyperdimensional Computing,","venue":null,"work_id":"e9f6e800-8030-4faa-9537-773d010531c9","year":2022},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.453236Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:8e7f7a3066537ab9e7cd1ab7cb191abe0574473a3b5c0b70d4d21d4f7d3c2090","observation_id":"5edfc7b3-7056-4449-8d4c-9fbb38415537","resolution":{"observed_at":"2026-08-06T19:13:23.669368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:23.250853Z","title":"Understanding Deep Image Representations by Inverting Them,","venue":null,"work_id":"5807e719-85ab-4539-ba76-9a4885d3ec2d","year":2015},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.506976Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:5681c873d5f9f1307da7dad73787cd878284a283d7531d4aac9257d8c114b42e","observation_id":"37c1fa80-0cf3-4397-80b5-66a13cb85a07","resolution":{"observed_at":"2026-08-06T19:13:23.402806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:23.139114Z","title":"Deep Learning with Differential Pri- vacy,","venue":null,"work_id":"be35b0b3-89d2-47e1-83ec-b56c4822fc20","year":2016},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.572773Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:6fbd7de139df9771b69b28cd3969222e2eac2ce8dea7232799c04cc2ed926c75","observation_id":"74a25c40-a478-4a51-bdd2-ca50b112d9c7","resolution":{"observed_at":"2026-08-06T19:13:23.169261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:22.963845Z","title":"Homomorphic Encryption for Arithmetic of Approximate Numbers,","venue":null,"work_id":"8cf5fdc1-bec8-4fb6-a835-2e7b6b59c4f7","year":2017},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.640196Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:e989f080e7ca2176c583bc79eee7a6071cc19af778a7153c9403aa448588d3be","observation_id":"f2073418-0c22-47b3-bfd6-090f575650d7","resolution":{"observed_at":"2026-08-06T19:13:23.060067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T19:13:22.819770Z","title":"Certified Robustness to Adversarial Examples with Differential Privacy,","venue":null,"work_id":"a6f1ed95-d49d-49b9-b1fd-d6adefaf9b3c","year":2019},"citing_paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:22.702695Z"},"links":{"citing_paper":"/paper/2507.07130"},"observation_digest":"sha256:a9c680797c57fcbfd7ebf9da8c9afebe4ea29fa3eef1cf3d5580d60296f9d3a8","observation_id":"d85aa615-2243-4630-97a9-f551001e1891","resolution":{"observed_at":"2026-08-06T19:13:22.872679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.07130","last_updated":"2025-07-08T20:54:43Z","latest_version":1,"primary_category":"cs.DC","snapshot_observed_at":"2026-08-20T15:47:43.975480Z","submitted_at":"2025-07-08T20:54:43Z","title":"Ampere: Communication-Efficient and High-Accuracy Split Federated Learning"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":45},"total_outbound_references":49},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 1 inbound Pith citation observation for arXiv:2507.07130."}