{"as_of":"2026-08-10T05:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:352eb387731a32a728bcc33e7f4b55cff0c9c626cad12ea65b2508fc47dcf748","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T14:58:29.856095Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.17228/citation-record","integrity":"/paper/2507.17228/integrity","json":"/paper/2507.17228/citation-record.json","paper":"/paper/2507.17228"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T14:58:35.887029Z","title":"P3sl: Personalized privacy-preserving split learning on heterogeneous edge devices,","venue":null,"work_id":"31f7047a-8676-4eb6-b5a0-cd74b7fa2ea8","year":2025},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:25.485629Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:59c787af8ce3d3ac41a185fa8da73b742a3636b6a11c8a0799337073b20fa3e0","observation_id":"bc766592-ee27-4f10-a1aa-0498a9adc303","resolution":{"observed_at":"2026-08-06T14:58:35.993818Z","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":"2026-08-06T14:58:35.672053Z","title":"Asteroid: Resource- efficient hybrid pipeline parallelism for collaborative dnn training on heterogeneous edge devices,","venue":null,"work_id":"984c9db5-3eb5-4c3a-8226-3577021619cb","year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:25.567984Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:de7994464274e738e57333f96e55886da594f105b5acefd8055a198aee64e84d","observation_id":"bdf53569-2621-43fd-9136-01703890d585","resolution":{"observed_at":"2026-08-06T14:58:35.789742Z","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":"2026-08-06T14:58:35.408423Z","title":"Deepiot: Compressing deep neural network structures for sensing systems with a compressor-critic framework,","venue":null,"work_id":"c5e8c66f-d898-4210-b552-df94c7b67441","year":2017},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:25.668101Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:3d4a05c12ba8c616428c32230fb4293958e5b3dfc447e5030d487b1e043b7551","observation_id":"d68bf119-6dd8-46ca-8c62-07d4d4fb7b87","resolution":{"observed_at":"2026-08-06T14:58:35.524470Z","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":"2026-08-06T14:58:35.214326Z","title":"Splitfed: When federated learning meets split learn- ing,","venue":null,"work_id":"89413c1c-34d1-4d60-a760-06f07d6d5ea0","year":2022},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:25.828101Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:9c19226998c937327a3a7f8a4c1166043f4344efdfe63f37df0e06da91408129","observation_id":"366fc478-9148-4d45-b032-2c91e2158b5f","resolution":{"observed_at":"2026-08-06T14:58:35.317082Z","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":"2212.00824","last_updated":"2024-09-23T07:59:38Z","snapshot_observed_at":"2026-08-09T08:44:53.976734Z","submitted_at":"2022-12-01T19:22:29Z","title":"On-device Training: A First Overview on Existing Systems","version":3},"cited_work":{"arxiv_id":"2212.00824","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.00824","snapshot_observed_at":"2026-08-06T14:58:30.363601Z","title":"On-device Training: A First Overview on Existing Systems","venue":"cs.LG","work_id":"ad1c1d66-290f-4309-ae37-3b01fe9973f7","year":2022},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:25.961889Z"},"links":{"cited_paper":"/paper/2212.00824","citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:e21107239d18a086f6b98fa844679b472d3183b1b6330bf1d049834f4259ace7","observation_id":"5e3c0ca3-81e0-4a69-bdac-d9e587f8c4f4","resolution":{"observed_at":"2026-08-06T14:58:30.435927Z","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":"2026-08-06T14:58:34.954865Z","title":"Distributed learning of deep neural network over multiple agents,","venue":null,"work_id":"4451f662-a91e-4ce1-a8f5-79ab273745d4","year":2018},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:26.053418Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:b93041333ef95310b33ea23f1c26f2ff7242655c8e1242afa11afbc6ce3a6708","observation_id":"52684d5f-298d-43fe-9b40-4ba749dd270f","resolution":{"observed_at":"2026-08-06T14:58:35.098039Z","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":"2026-08-06T14:58:34.840051Z","title":"Data-free one-shot federated learning under very high statistical heterogeneity,","venue":null,"work_id":"a909ef98-e2da-4a80-a236-93c58fdf8610","year":2023},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:26.165572Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:dd62b8cbf1717b647b58c9f4fe9d43b28d1dd1cfab8f2a3733fec4bac51e505e","observation_id":"fdf89bea-0da0-4add-93fe-4ffe5bf04fbd","resolution":{"observed_at":"2026-08-06T14:58:34.898011Z","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":"2026-08-06T14:58:34.723272Z","title":"Thapa, M","venue":null,"work_id":"e017e9d4-0ee6-4923-9fa0-b5d95c9aaa7b","year":2021},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:26.319820Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:2acd755cc48b9f234e2da27274b5a622dc9eaca66ae377242af634a43473b93a","observation_id":"193bef02-01ca-44ea-85fe-d9f6a4b890ab","resolution":{"observed_at":"2026-08-06T14:58:34.782980Z","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":"2026-08-06T14:58:34.577890Z","title":"End-to-end evaluation of feder- ated learning and split learning for internet of things,","venue":null,"work_id":"38584bbe-6688-48a6-975a-b77f3f68ee7f","year":2020},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:26.406645Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:1f21815e17e0d2729037d0b4b7d681186ddbe1668b468814b27033cc1fc2401b","observation_id":"6b1eda8e-f5d4-41c7-980a-d229fa76e37f","resolution":{"observed_at":"2026-08-06T14:58:34.647614Z","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":"2026-08-06T14:58:34.409324Z","title":"Split learning in 6g edge networks,","venue":null,"work_id":"f8e2af0b-9770-488d-a943-a99a85831937","year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:26.461860Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:62df99ad67c4aad021b93ca7a68983a429ca708699802b31684634d7e6894546","observation_id":"a5753080-883d-4347-8c2b-caeec6711410","resolution":{"observed_at":"2026-08-06T14:58:34.495931Z","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":"2026-08-06T14:58:34.252316Z","title":"Vepakomma and R","venue":null,"work_id":"aaec46a9-3eb7-4ba2-80d6-d1145324b3e3","year":2022},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:26.518401Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:7f452ce9178bc02e5a685269270ecee14fc700ad87edc383e63788ba241818d3","observation_id":"0cfd57ad-58c8-40b7-80f3-9e384ae63e6e","resolution":{"observed_at":"2026-08-06T14:58:34.318639Z","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":"2026-08-06T14:58:34.111940Z","title":"Improving the commu- nication and computation efficiency of split learning for iot appli- cations,","venue":null,"work_id":"2b8a0e0b-44a4-415c-b861-69af640b6400","year":2021},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:26.636930Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:dded8c4e6c8d756d05f0a78cf318ba51c74ce4aa4d87c74c05865494aa8f0349","observation_id":"3253f67f-8a48-48cf-b965-084f22ffb15d","resolution":{"observed_at":"2026-08-06T14:58:34.176267Z","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":"2026-08-06T14:58:33.949111Z","title":"Privacy-sensitive parallel split learning,","venue":null,"work_id":"f89e4896-7eda-444d-b0cd-53cd65355b1a","year":2020},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:26.772063Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:2a0bd1c17358276007b8915f356134882369caa7cdffe4ab1dcbf7d442b55f91","observation_id":"bcade690-7549-44d2-9491-ed00928db9dc","resolution":{"observed_at":"2026-08-06T14:58:34.033754Z","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":"2026-08-06T14:58:33.851973Z","title":"Inside the AI care home: the smart tech making old people safer,","venue":null,"work_id":"c0605a92-430b-48f8-8297-87d963ff02d5","year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:26.904749Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:2f9c59f607af290e241fa58a7452012c6707670a0373d6e0a8e62ee8facbfea9","observation_id":"87194a6e-404d-4d48-a5d3-ad3f6f35c240","resolution":{"observed_at":"2026-08-06T14:58:33.897294Z","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":"2026-08-06T14:58:33.704629Z","title":"Ares: Adaptive resource- aware split learning for internet of things,","venue":null,"work_id":"9976341a-3198-40a9-843a-0a6621da0feb","year":2022},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:26.990267Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:b38421cd4539139b7dae895ad14bcd4bf0c34ad7a44e5990cfd8e944e46b81a5","observation_id":"d194326e-2e55-4d15-9ca6-39deeeb00c97","resolution":{"observed_at":"2026-08-06T14:58:33.772969Z","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":"2026-08-06T14:58:33.508615Z","title":"Adaptive split learning over energy-constrained wireless edge networks,","venue":null,"work_id":"d2151945-6fcf-45f0-b21e-fa3548686ec6","year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:27.092433Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:e82f034fcc1fe761e84edc8ccd6bd119d1a60270cea525530cb6ef46e2600803","observation_id":"56c51354-a45a-4653-990f-45cf82e77c0b","resolution":{"observed_at":"2026-08-06T14:58:33.586462Z","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":"2403.15815","last_updated":"2024-03-23T12:09:16Z","snapshot_observed_at":"2026-08-08T08:47:41.885618Z","submitted_at":"2024-03-23T12:09:16Z","title":"Resource-efficient Parallel Split Learning in Heterogeneous Edge Computing","version":1},"cited_work":{"arxiv_id":"2403.15815","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.15815","snapshot_observed_at":"2026-08-06T14:58:30.195893Z","title":"Resource-efficient Parallel Split Learning in Heterogeneous Edge Computing","venue":"cs.DC","work_id":"dc9e4c96-0418-4d4a-bb24-dd36d14a7bc0","year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:27.204287Z"},"links":{"cited_paper":"/paper/2403.15815","citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:91d895ab9e6cc9ff28b237fecacd3f3ef22cc2e4a5b44ca486ad882b0195f28d","observation_id":"db5b361e-aa49-4d6c-bbac-8b57c8345be6","resolution":{"observed_at":"2026-08-06T14:58:30.254660Z","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":"2026-08-06T14:58:33.367667Z","title":"Unsplit: Data-oblivious model inversion, model stealing, and label inference attacks against split learning,","venue":null,"work_id":"b18aa376-5b6a-47af-ac70-de3d3bf1f10b","year":2022},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:27.340663Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:1f51e41b8c575d5e53508cdcbdb6133c81d12da06d549dad8a2f8cef0a8c7243","observation_id":"b68a4f98-037d-4016-8992-c566698d41f0","resolution":{"observed_at":"2026-08-06T14:58:33.440268Z","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":"2026-08-06T14:58:33.229120Z","title":"A review on bilevel optimization: From classical to evolutionary approaches and applications,","venue":null,"work_id":"3e8ff917-11bf-4b5c-a6b7-cbb0048e5a21","year":2018},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:27.495986Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:3bf2ef68a30efb5aeeac5ce2597cbda8048a6efd981d2f4f1dfc79124500c91e","observation_id":"eb18733f-821b-46a9-95c0-2dde517490be","resolution":{"observed_at":"2026-08-06T14:58:33.297287Z","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":"2401.16164","last_updated":"2024-01-29T13:50:56Z","snapshot_observed_at":"2026-08-09T16:36:17.571417Z","submitted_at":"2024-01-29T13:50:56Z","title":"Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.16164","snapshot_observed_at":"2026-08-06T14:58:27.570144Z","title":"Constrained bi-level optimization: Proximal lagrangian value function approach and hessian-free algorithm,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:27.570144Z"},"links":{"cited_paper":"/paper/2401.16164","citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:dcf5bafe1aa5a547e08223dca4ef28892c3bd892d1e85a72ee58858b69bdf68d","observation_id":"ee625632-a9d9-4047-a969-ed1295c1b04d","resolution":{"observed_at":"2026-08-06T14:58:27.570144Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-06T14:58:27.640378Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:27.640378Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:6392d26b92d39db245b3ab5a4ba2c4c9c072a364999905ad71e1b7c12c40a132","observation_id":"2a40fd70-5384-4f8c-9e78-c3ac3429f1aa","resolution":{"observed_at":"2026-08-06T14:58:27.640378Z","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":"2026-08-06T14:58:27.811657Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:27.811657Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:3b71325f41bb68b2ef1d0cecc964f9325d04b67c031eb6f43befa4adb2417fdc","observation_id":"0cd50877-b319-4d3a-be67-9281370e2b07","resolution":{"observed_at":"2026-08-06T14:58:27.811657Z","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":"2026-08-06T14:58:33.089230Z","title":"Automated flower classifi- cation over a large number of classes,","venue":null,"work_id":"75a8c777-64ce-4f91-b88d-f5e6dc810d7a","year":2008},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:27.943264Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:5c47e725a277603f5ac1aac768172b090cd39ed05f32fb9d202aad2544288636","observation_id":"61227525-5837-4136-a04d-5481161218ce","resolution":{"observed_at":"2026-08-06T14:58:33.143605Z","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":"2026-08-06T14:58:28.022407Z","title":"Fsim: A feature similarity index for image quality assessment,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.022407Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:7e35695eb48dc6bc2ddd2984c86aba021a9f1d112c4e2d103c8f8bda2354afdf","observation_id":"e665bcc8-c951-40bf-a36e-b337e64e6d15","resolution":{"observed_at":"2026-08-06T14:58:28.022407Z","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":"2026-08-06T14:58:32.963247Z","title":"Membership inference attacks from first principles,","venue":null,"work_id":"718dbd79-c46a-4239-b55b-64cff542b318","year":2022},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.118999Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:18137832a2aeabfa8964b808260b7b2b2cdffec2b0a999b540efc2a8e075eba0","observation_id":"07b6b981-3d8f-4417-9fbe-7f6a5a6e6934","resolution":{"observed_at":"2026-08-06T14:58:33.018236Z","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":"1812.00564","last_updated":"2018-12-03T05:43:20Z","snapshot_observed_at":"2026-08-04T04:23:43.839800Z","submitted_at":"2018-12-03T05:43:20Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00564","snapshot_observed_at":"2026-08-06T14:58:28.252517Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.252517Z"},"links":{"cited_paper":"/paper/1812.00564","citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:be1cbe877cf81a6c45cc5cdc9fd38a8db87a10c408d21bfb4f510cc808ba0dd2","observation_id":"47fd095f-d31b-41be-ad32-976c28bcb2b9","resolution":{"observed_at":"2026-08-06T14:58:28.252517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.05929","last_updated":"2021-12-11T08:33:25Z","snapshot_observed_at":"2026-08-09T08:43:36.214455Z","submitted_at":"2021-12-11T08:33:25Z","title":"Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.05929","snapshot_observed_at":"2026-08-06T14:58:28.372116Z","title":"Server-side local gradient averaging and learning rate acceleration for scalable split learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.372116Z"},"links":{"cited_paper":"/paper/2112.05929","citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:4858a89805394bcabdd350007621aebbe901d1b58dc0763be809b8a55e45093e","observation_id":"cb37b700-7e46-4ce7-9177-5069f3bb0961","resolution":{"observed_at":"2026-08-06T14:58:28.372116Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.13907","last_updated":"2024-11-21T07:46:01Z","snapshot_observed_at":"2026-07-06T19:53:34.670694Z","submitted_at":"2024-11-21T07:46:01Z","title":"Split Federated Learning Over Heterogeneous Edge Devices: Algorithm and Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.13907","snapshot_observed_at":"2026-08-06T14:58:28.426602Z","title":"Split federated learning over heterogeneous edge devices: Algorithm and optimization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.426602Z"},"links":{"cited_paper":"/paper/2411.13907","citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:00c2edaf826a64cf669b7b551feb02dd7fa8513ed23cb02bddd7fd41c1f2961f","observation_id":"43cd6282-df1e-435c-9301-1234a3dfe6ef","resolution":{"observed_at":"2026-08-06T14:58:28.426602Z","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":"2026-08-06T14:58:32.834004Z","title":"Unleashing the tiger: Inference attacks on split learning,","venue":null,"work_id":"b89dd123-6f93-44a1-8d44-c589dff71648","year":2021},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.527506Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:292c6145e536d0a2521f71a7aa1dd3d4f196b9ab0b837f2c165e3c05a8a0d7a0","observation_id":"d0b793db-1673-4588-b42b-0cbfb2e1757e","resolution":{"observed_at":"2026-08-06T14:58:32.899267Z","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":"2026-08-06T14:58:32.672413Z","title":"Get your foes fooled: Proximal gradient split learning for defense against model inversion attacks on iomt data,","venue":null,"work_id":"a24643e2-be99-4ae6-b381-3c013a22a95b","year":2022},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.593772Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:bb35b9b586aaed6f89bdcdd3e3c495a9de67253aa5e762e36f30cf1985f44321","observation_id":"ee59897c-15ec-4411-93ef-86eb8b593bdf","resolution":{"observed_at":"2026-08-06T14:58:32.731452Z","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":"2026-08-06T14:58:32.529082Z","title":"Label leakage and protection in two-party split learning,","venue":null,"work_id":"057dd61a-4515-45fb-a053-eab8fb5588f6","year":2022},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.651155Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:bd5e96a3f9d201bed0d0f2996e3f8d52d16140f130964a67e12ddaf04d8ffaff","observation_id":"7654f23e-a23d-4cb8-a393-f7ba32b4bfcb","resolution":{"observed_at":"2026-08-06T14:58:32.609514Z","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":"2026-08-06T14:58:32.371341Z","title":"Prac- tical defences against model inversion attacks for split neural net- works,","venue":null,"work_id":"b2263df0-56e9-443c-89c6-ba63ccd820c6","year":2021},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.734061Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:930d3175c17147e9459f1b6e37c1bf145242409f5cb3204433d86c619472a97e","observation_id":"0aae97a6-1b38-4f8a-8016-a5560b20d8d7","resolution":{"observed_at":"2026-08-06T14:58:32.455687Z","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":"2026-08-06T14:58:32.191562Z","title":"Recon- structing training data from trained neural networks,","venue":null,"work_id":"dc871116-2922-4660-8b71-b94b3908d9bd","year":2022},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.796785Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:f572708c8e0f58d8d5a6e613304ed0ba3afa32d71be16780795bb3a8451ee521","observation_id":"69fcd6dc-dba6-4fb9-924a-58b346c25907","resolution":{"observed_at":"2026-08-06T14:58:32.286253Z","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":"2026-08-06T14:58:28.890740Z","title":"Deep leakage from gradients,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.890740Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:6e85838eeff9515f8cf32382a5a2cf46e1c3059f29dfd810e3967c6312d1b89f","observation_id":"3ddba253-db0b-4869-ba73-b775e24e0657","resolution":{"observed_at":"2026-08-06T14:58:28.890740Z","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":"2026-08-06T14:58:32.028979Z","title":"Ppsfl: Privacy-preserving split federated learning for heterogeneous data in edge-based internet of things,","venue":null,"work_id":"fe165117-6327-4cf7-a04c-e4d10fd35cb6","year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:28.983014Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:473aa056cfe7ce663c7249044711e69096f649f5bf076c81f292a461bb84bc25","observation_id":"f567e64a-9547-4ce5-bd24-c0fc3cb3f671","resolution":{"observed_at":"2026-08-06T14:58:32.104774Z","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":"2407.08977","last_updated":"2026-07-22T15:11:30Z","snapshot_observed_at":"2026-07-25T23:21:22.284030Z","submitted_at":"2024-07-12T04:10:19Z","title":"CURE: Privacy-Preserving Split Learning Done Right","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.08977","snapshot_observed_at":"2026-08-06T14:58:29.056082Z","title":"Cure: Privacy-preserving split learning done right,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.056082Z"},"links":{"cited_paper":"/paper/2407.08977","citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:6175bd63a367fe238cf1d4829bcbe6ddb31f34ab50e3f334a37af0775c048ccc","observation_id":"d32648ea-f3ce-47b3-be67-21b4e70d9fb3","resolution":{"observed_at":"2026-08-06T14:58:29.056082Z","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":"2026-08-06T14:58:31.863864Z","title":"Split learning without local weight sharing to enhance client-side data privacy,","venue":null,"work_id":"effa0d9b-f6dc-4da5-9fd8-0f0203c1a2e9","year":2025},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.114962Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:e82e080a22bf87a634ec6611c0754dcfc661c89ba21b379f6dacb14500276ddf","observation_id":"71fa9bac-26dd-4982-8426-4d458b35c9c1","resolution":{"observed_at":"2026-08-06T14:58:31.942718Z","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":"2026-08-06T14:58:31.699766Z","title":"Very deep convolutional net- works for large-scale image recognition,","venue":null,"work_id":"57cc699f-692c-42e3-8a5f-87ba48b9edbd","year":2015},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.178369Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:0e54d107befa8ff3add9211944e6b1aee23bb19917d1d65d10d98476ae077622","observation_id":"07c30f22-906e-4860-87fe-a95b38b89535","resolution":{"observed_at":"2026-08-06T14:58:31.782853Z","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":"2026-08-06T14:58:31.545800Z","title":"Jetson nano - power- ful ai at your edge","venue":null,"work_id":"a63a4ce1-1e7b-4be2-ad18-ddf1b12a0d37","year":null},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.257622Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:182c8bb580b4347fe41bb53bff088888728fef1468bf22f4189d5020e25cbf25","observation_id":"16b47548-6215-451c-9456-cbbf9335e695","resolution":{"observed_at":"2026-08-06T14:58:31.621814Z","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":"2026-08-06T14:58:31.397382Z","title":"Talbi, A Taxonomy of Metaheuristics for Bi-level Optimization","venue":null,"work_id":"3274f58a-0a74-4f22-bd2a-f106dce9197d","year":2013},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.330515Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:6796988fc7197da7eac760fa111ba974504c12627443c33e34a4fe034172f0a2","observation_id":"28dd0912-b1e9-4261-967a-d2a6b7ff14f9","resolution":{"observed_at":"2026-08-06T14:58:31.475116Z","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":"2026-08-06T14:58:31.214653Z","title":"python-kasa: Python api for tp-link smarthome products","venue":null,"work_id":"cadc6a0b-f8c1-479f-a935-2a04ee922f97","year":null},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.395414Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:f7e6e665581cde002b65219dbd49470593af20c56851635d6e718305b23aaffd","observation_id":"131ca2be-5477-4519-ba8a-967e51aa262e","resolution":{"observed_at":"2026-08-06T14:58:31.325816Z","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":"2026-08-06T14:58:31.054044Z","title":"Vta- smac: Variable traffic-adaptive duty cycled sensor mac protocol to enhance overall qos of s-mac protocol,","venue":null,"work_id":"aad3acdc-f15d-4ca6-b3f7-560503497bb9","year":2021},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.456393Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:f2288f1c7410131b9f47da64869af5048b2f791edcd2fc3c1a40d77db0ae8267","observation_id":"4684c9b6-aece-461d-a269-01efdca27a38","resolution":{"observed_at":"2026-08-06T14:58:31.142133Z","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":"2026-08-06T14:58:30.867532Z","title":"Gradient leak- age attacks in federated learning: Research frontiers, taxonomy, and future directions,","venue":null,"work_id":"1f576f38-d8d8-4f8b-b45e-86096d62b21e","year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.559381Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:59bf464ea7a925ec2b5a045312faf3ba8d364a255c8d9945473074a275147bfe","observation_id":"e2265f18-52f0-4251-8d7e-e34860a246fe","resolution":{"observed_at":"2026-08-06T14:58:30.947925Z","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":"2407.05285","last_updated":"2025-01-06T14:37:01Z","snapshot_observed_at":"2026-07-06T18:42:30.828375Z","submitted_at":"2024-07-07T07:06:49Z","title":"Mjolnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion","version":4},"cited_work":{"arxiv_id":"2407.05285","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.05285","snapshot_observed_at":"2026-08-06T14:58:29.961218Z","title":"Mjolnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion","venue":"cs.LG","work_id":"ceb200d8-a634-4ecb-9f5a-3cb67e13d3b2","year":2024},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.673465Z"},"links":{"cited_paper":"/paper/2407.05285","citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:81be28aeeff851b467704eaa20b2fa9b3ea49bead1ffaf9bb1d5f4df789a5942","observation_id":"7846283e-68d3-4f39-9b0c-6ea598038a0b","resolution":{"observed_at":"2026-08-06T14:58:30.033908Z","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":"2026-08-06T14:58:30.691585Z","title":"U-shaped split federated learning: An efficient cross-device learning frame- work with enhanced privacy-preserving,","venue":null,"work_id":"85bf1def-cd67-4e61-b83a-a00e0083a55a","year":2023},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.771252Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:af79ecb0d943404a58fb262b3d573b931067ae5dbb3dc3d486a684d3dbc728d5","observation_id":"9b7caef2-0f70-4c2c-a323-972295bcb0bc","resolution":{"observed_at":"2026-08-06T14:58:30.776384Z","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":"2026-08-06T14:58:30.517914Z","title":"Active client selection for clustered federated learning,","venue":null,"work_id":"a09dcba5-921f-46ff-8238-07024ff649b5","year":2023},"citing_paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T14:58:29.856095Z"},"links":{"citing_paper":"/paper/2507.17228"},"observation_digest":"sha256:84c20ff8ced7ff4c658fac45d7c7c1cc41a7f355034fe14bb07734114815297a","observation_id":"d19d4a26-fd2f-4ebd-86a3-dbe6f4292a59","resolution":{"observed_at":"2026-08-06T14:58:30.603388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.17228","last_updated":"2025-08-05T02:08:01Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T08:43:55.185204Z","submitted_at":"2025-07-23T05:50:33Z","title":"P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":3,"verified_fuzzy":34},"total_outbound_references":46},"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 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2507.17228."}