{"as_of":"2026-08-07T23:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3bde206e4f141b7f085a892359d3ee5aaac9fbaa98b9b164941d04d1c10f6342","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T13:45:04.770557Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2509.25906/citation-record","integrity":"/paper/2509.25906/integrity","json":"/paper/2509.25906/citation-record.json","paper":"/paper/2509.25906"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T13:45:01.153994Z","title":"On safeguarding privacy and security in the framework of federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.153994Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:4361e3b04075616a4e2b7730dcfe6a9a0248647882fc0df6ade71aad6fd0bf2d","observation_id":"380cc082-3f55-4bb7-bc52-62066c694e64","resolution":{"observed_at":"2026-08-04T13:45:01.153994Z","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":"2026-08-04T13:45:01.234861Z","title":"Differentially private federated stochastic primal-dual learning for internet of vehicles,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.234861Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:49c37e370c84ab1f5a09f7a7c099bf637f8b911d63258bc80cad812768accfaf","observation_id":"8c5cf39b-9c1c-41f5-9dc5-dede8cbeedfc","resolution":{"observed_at":"2026-08-04T13:45:01.234861Z","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":"2026-08-04T13:45:01.361908Z","title":"FedPD: A federated learning framework with adaptivity to non-IID data,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.361908Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:76a42b70ac12b8ab8da0b5124d4ad93676cec52bfefb4a818491ed7523c5f46a","observation_id":"b37c63d4-c621-4836-b070-9229abb7e650","resolution":{"observed_at":"2026-08-04T13:45:01.361908Z","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":"2026-08-04T13:45:01.392372Z","title":"On the convergence of FedAvg on non-IID data,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.392372Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:823c624b89528ab66a7b06af53061641852d06d63d7d9979c96e3ee806e4bc83","observation_id":"51da869d-7b1a-4930-bb2f-898d14f267fa","resolution":{"observed_at":"2026-08-04T13:45:01.392372Z","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":"2026-08-04T13:45:01.486555Z","title":"Differentially private and heterogeneity-robust federated learning with theoretical guarantee,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.486555Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:fc35ede7c29cbd00fe30ac7ffacb94cfda04017e91d0e4be6fdf43c3b091a8b2","observation_id":"cf9b570d-9620-49b3-bf5c-6d9ea3460463","resolution":{"observed_at":"2026-08-04T13:45:01.486555Z","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":"2026-08-04T13:45:01.547233Z","title":"Privacy-preserving federated primal-dual learning for non-convex and non-smooth problems with model sparsification,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.547233Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:131e35a0963ae11e134b9334695e698d058796effc2ac1649c4c1ff2fdf648a7","observation_id":"96663dc6-20a4-4a14-839e-a5c9f769fa34","resolution":{"observed_at":"2026-08-04T13:45:01.547233Z","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":"2026-08-04T13:45:01.584514Z","title":"Differentially private federated clustering over non-iid data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.584514Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:d7c760b4478c83140fd4300b10f78ac46a43d2655f131ce3ffecee9464d0ab2a","observation_id":"4d7a9e21-2a57-4495-88b8-e620cdddf261","resolution":{"observed_at":"2026-08-04T13:45:01.584514Z","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":"2026-08-04T13:45:01.631077Z","title":"Robust and secure federated learning with verifiable differential privacy,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.631077Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:b749c86996548c3dccf9f4fafbbb8a1e607c75cf9dcec1e8c32406e0cc1db2c9","observation_id":"2e26ff66-dd3a-49db-8255-aa9f0749d5a2","resolution":{"observed_at":"2026-08-04T13:45:01.631077Z","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":"2026-08-04T13:45:01.673872Z","title":"Heterogeneous differential-private federated learning: Trading privacy for utility truthfully,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.673872Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:91cbde4eadc933f98d91f3b0750207cd540e57551291991fc02346188ae4dd67","observation_id":"401cefdd-64a2-4b86-bf1d-1cf1fc6100e8","resolution":{"observed_at":"2026-08-04T13:45:01.673872Z","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":"2026-08-04T13:45:01.716133Z","title":"Differentially private deep learning with dynamic privacy budget allocation and adaptive optimization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.716133Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:035406b1603c70ad9b2e863f9c3012039422dc6e7a31624ad6c61c00ec3e9d3a","observation_id":"aa50b0ff-da08-4d0a-94ea-7ec6ec31964c","resolution":{"observed_at":"2026-08-04T13:45:01.716133Z","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":"2026-08-04T13:45:01.770576Z","title":"Differentially private federated learning in edge networks: The perspective of noise reduction,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.770576Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:e0ea8c1450947cbece41d7727409e69ac599bfb8619b118d205ef79f7550948e","observation_id":"6f6927f8-60f2-4e24-9aba-7d6ae46a54ea","resolution":{"observed_at":"2026-08-04T13:45:01.770576Z","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":"2026-08-04T13:45:01.895538Z","title":"Shuffled model of differential privacy in federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.895538Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:ead82b8d833c1d33b522397a4d718eb87484010ce5e7d6db72714d2bd85bb026","observation_id":"a6ee2417-583c-4766-807d-b49cb663b5d9","resolution":{"observed_at":"2026-08-04T13:45:01.895538Z","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":"2026-08-04T13:45:01.994784Z","title":"Privacy amplification by iteration,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:01.994784Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:fbf75a5841d9a06ad538501cd0acbdab0d6e2add95e6b49d1a5c3bf359d42fb3","observation_id":"f6121d76-19b7-46bc-8540-b8c9b566ade8","resolution":{"observed_at":"2026-08-04T13:45:01.994784Z","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":"2026-08-04T13:45:02.150383Z","title":"Privacy amplification by subsampling: Tight analyses via couplings and divergences,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:02.150383Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:be21f91e9318b290b2658bb3240b15a9bb836855ed854dfd889e7335a70bcdc8","observation_id":"6a96a427-1b44-4511-8d15-b813b49af446","resolution":{"observed_at":"2026-08-04T13:45:02.150383Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.00597","last_updated":"2022-10-26T16:13:14Z","snapshot_observed_at":"2026-08-03T10:21:08.508642Z","submitted_at":"2022-10-02T18:22:31Z","title":"Composition of Differential Privacy & Privacy Amplification by Subsampling","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.00597","snapshot_observed_at":"2026-08-04T13:45:02.268040Z","title":"Composition of differential privacy & privacy amplification by subsampling,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:02.268040Z"},"links":{"cited_paper":"/paper/2210.00597","citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:c590900165b823db39192f38b7c76ad65a0024119e648459e903138d016c8640","observation_id":"c3aad46a-fa57-44b7-a123-cb1822290752","resolution":{"observed_at":"2026-08-04T13:45:02.268040Z","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":"2026-08-04T13:45:02.412230Z","title":"Amplification by shuffling: From local to central differential privacy via anonymity,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:02.412230Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:f4739690f6b84909300a70490462d9ad1344e048222d8e54406a2e154fdee209","observation_id":"188c5549-eb2c-462c-8c4c-92fb923e9264","resolution":{"observed_at":"2026-08-04T13:45:02.412230Z","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":"2026-08-04T13:45:02.522918Z","title":"Distributed differential privacy via shuffling versus aggregation: A curious study,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:02.522918Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:447cbe0aeb5bccb444c0c7bb3ff9363a57d66c61a1c5cb4bfae9a71100a58174","observation_id":"587fbd37-a976-47e8-80d6-c28a92d4bc41","resolution":{"observed_at":"2026-08-04T13:45:02.522918Z","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":"2026-08-04T13:45:02.632009Z","title":"Shuffle differential private data aggregation for random population,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:02.632009Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:f37b0414e84c8e8fa22b70505d3e958f89f7412a40ec8e46135d5da3d249df0c","observation_id":"5afabe32-dc55-47b0-8df7-28a1f21fb43e","resolution":{"observed_at":"2026-08-04T13:45:02.632009Z","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":"2026-08-04T13:45:02.881998Z","title":"Community-oriented duplex privacy amplification and active poisoning resistance for heterogeneous federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:02.881998Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:6a17d45e928dfb46140708608bb486a2718b0c9645dd84640e524858d03dd91c","observation_id":"96737974-e83c-4169-9b17-8af4e0b498e3","resolution":{"observed_at":"2026-08-04T13:45:02.881998Z","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":"2026-08-04T13:45:02.975735Z","title":"SLDP-LoRA: A privacy-preserving split learning framework with low-rank adaptation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:02.975735Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:3264a6dc8d610ac05d82ffe7d66483cd9dc7b6df0b87493b94899da9e837cd04","observation_id":"23938f51-1709-4748-9dce-4c787541e463","resolution":{"observed_at":"2026-08-04T13:45:02.975735Z","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":"2026-08-04T13:45:03.130174Z","title":"Enhancing accuracy-privacy trade-off in differentially private split learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.130174Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:3e319a315e689c5d724423120c9ef0c3a723f4f267ec3cb79c7ea82355a04c47","observation_id":"3587b8a2-d79a-40fa-899b-95c48d689492","resolution":{"observed_at":"2026-08-04T13:45:03.130174Z","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":"2026-08-04T13:45:03.225740Z","title":"Deep learning with differential privacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.225740Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:8456f85a86ccded1d022f8424054692131a5bfeca7b453638f8195c69fffad12","observation_id":"7b31d730-1301-48ac-9951-8c662fd78319","resolution":{"observed_at":"2026-08-04T13:45:03.225740Z","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":"2026-08-04T13:45:03.327296Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.327296Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:44d86172583c5ed45d4f1ba77407e27088d54afa1b426a021c464bc0d25ec200","observation_id":"52a1815d-4bf7-458d-83d7-3c28eeb3a4a8","resolution":{"observed_at":"2026-08-04T13:45:03.327296Z","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":"2026-08-04T13:45:03.472526Z","title":"Secure federated averaging algorithm with differential privacy,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.472526Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:e1b974b2099905a50b9c12fb3a82ec1d0d3462f27b767040e12ee9215886a37d","observation_id":"1a34b066-20ea-43e7-8f3e-59eefd8dd850","resolution":{"observed_at":"2026-08-04T13:45:03.472526Z","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":"2026-08-04T13:45:03.581900Z","title":"Federated learning with differential privacy: Algorithms and performance analysis,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.581900Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:ad961ba3352e379538e69a4315dc6a85cd771f2337e2cc5c8203e67a09883322","observation_id":"bc51937c-8373-4c7d-bce1-1a0bb220069b","resolution":{"observed_at":"2026-08-04T13:45:03.581900Z","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":"2026-08-04T13:45:03.656961Z","title":"Advances and open problems in federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.656961Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:9678e89ade63d9d0c92aec4bc974d7bef09554ceafe34c32f96b81bafb82a72c","observation_id":"fd5a9a41-99dd-4894-a2a3-7c2e0bb55535","resolution":{"observed_at":"2026-08-04T13:45:03.656961Z","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":"2026-08-04T13:45:03.681031Z","title":"Federated learning with Bayesian differential privacy,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.681031Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:982934ab52a961246280ccdad74dab199136bf74454aadc7af8577ddbfd347ec","observation_id":"7c71aeb7-1eac-4656-a40d-1c0ad6bd79ae","resolution":{"observed_at":"2026-08-04T13:45:03.681031Z","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":"2026-08-04T13:45:03.727681Z","title":"LDP-Fed: Federated learning with local differential privacy,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.727681Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:506507aad2b398f3bdc8388abef5b7d80cb759a6c5b92876035f36a4555b8863","observation_id":"d3da6930-ad2d-449a-8b8c-577a7782cfe8","resolution":{"observed_at":"2026-08-04T13:45:03.727681Z","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":"2026-08-04T13:45:03.779213Z","title":"Stronger privacy amplification by shuffling for r´enyi and approximate differential privacy,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.779213Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:02340f625000bf85165d990bcb436dc1daac33959d8e397ab65bb6e063b7ff43","observation_id":"41699ad1-4b77-4a92-8558-b0fc71f2c2c9","resolution":{"observed_at":"2026-08-04T13:45:03.779213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.15526","last_updated":"2024-05-04T18:49:50Z","snapshot_observed_at":"2026-08-05T16:29:59.562168Z","submitted_at":"2023-10-24T05:16:52Z","title":"Privacy Amplification for Matrix Mechanisms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.15526","snapshot_observed_at":"2026-08-04T13:45:03.835098Z","title":"Privacy amplification for matrix mechanisms,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.835098Z"},"links":{"cited_paper":"/paper/2310.15526","citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:280e7257e123401543e946c739a816049852272c0953a49ad2e40942aefc315d","observation_id":"735b3317-01fb-4036-a5e3-0f742233cfaa","resolution":{"observed_at":"2026-08-04T13:45:03.835098Z","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":"2026-08-04T13:45:03.873669Z","title":"Privacy amplification by sampling under user-level differential privacy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.873669Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:f1f7893a357546d7463595c465ab9fc648a37a6524619a88aedb5dc9f5896487","observation_id":"558fa6c3-5cd9-4c24-aa2f-3c12dcd059ba","resolution":{"observed_at":"2026-08-04T13:45:03.873669Z","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":"2026-08-04T13:45:03.922155Z","title":"Privacy amplification by random allocation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.922155Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:52001292a3ba50fe527b74109932b92158c33df2691fdd692a83a6674fb89ac2","observation_id":"2fa0c679-daf3-424e-97e4-88146c64e44a","resolution":{"observed_at":"2026-08-04T13:45:03.922155Z","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":"2026-08-04T13:45:03.969666Z","title":"Privacy amplification via random check-ins,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:03.969666Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:99ccc9447356d88fd5d2a164a5c46668b9fa17d6d566c7f037c4543f819ff2e1","observation_id":"f0d3411b-54b1-4c3d-bd40-c24f4e5bcdd5","resolution":{"observed_at":"2026-08-04T13:45:03.969666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-04T13:45:04.010780Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.010780Z"},"links":{"cited_paper":"/paper/1812.00564","citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:6f96c49222c4bc211d7fadab2fa4eddd468cd04c6de5af5a0859a10e4eb3f36c","observation_id":"17297df7-74ba-48a2-b9db-8ca198c7e34f","resolution":{"observed_at":"2026-08-04T13:45:04.010780Z","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":"2026-08-04T13:45:04.087552Z","title":"Splitfed: When federated learning meets split learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.087552Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:d115c14fb9fa1a2e79101dfee51561259f0f259016648b2665a1495634dbbcc7","observation_id":"429dedac-4c57-44f9-9327-d9a7195e9ec3","resolution":{"observed_at":"2026-08-04T13:45:04.087552Z","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":"2026-08-04T13:45:04.147279Z","title":"Privacy and efficiency of communications in federated split learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.147279Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:c25777a14b65d465a9087490e0653a23462481134b50aa612cef9ccd521e3460","observation_id":"e70a34ad-89a9-45f3-95c9-daff9c730080","resolution":{"observed_at":"2026-08-04T13:45:04.147279Z","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":"2026-08-04T13:45:04.196650Z","title":"The effectiveness of a simplified model structure for crowd counting,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.196650Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:3db9980fa6e6e109c9b99ff511db4d7c49dfb8e445dc1775b626335eacffb668","observation_id":"f9fa8ca5-a7b5-4e4d-8f5e-b7dd901b4caf","resolution":{"observed_at":"2026-08-04T13:45:04.196650Z","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":"2026-08-04T13:45:04.250538Z","title":"Split aggregation: Lightweight privacy-preserving federated learning resistant to byzantine attacks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.250538Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:bbfd0f6085b1f9b96dfcc135e25ffdd8f5ff1d3bf92a8228e9e169dd9d97321f","observation_id":"df9b488d-12c1-4c17-9139-8c8b7ed5d385","resolution":{"observed_at":"2026-08-04T13:45:04.250538Z","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":"2026-08-04T13:45:04.317476Z","title":"Exploiting shared representations for personalized federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.317476Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:2f3f2e3a2c3b705b4fe50ce86496d2e0431b5d1a73567b26ecfc6b604652c386","observation_id":"4ee1f803-695c-4a7c-adb6-0ee01228ebf8","resolution":{"observed_at":"2026-08-04T13:45:04.317476Z","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":"2026-08-04T13:45:04.397049Z","title":"Distributed learning over networks with graph-attention-based personalization,","venue":null,"work_id":null,"year":2071},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.397049Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:0d3ee462629f6363678f3251c5ada96b17181b19b1ca33bcd469f214a126b41b","observation_id":"46e7130d-b992-4446-b74b-5b440e0c6905","resolution":{"observed_at":"2026-08-04T13:45:04.397049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16058","last_updated":"2025-09-01T07:15:31Z","snapshot_observed_at":"2026-07-06T18:19:42.946629Z","submitted_at":"2024-05-25T04:56:54Z","title":"A Novel Privacy Enhancement Scheme with Dynamic Quantization for Federated Learning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.16058","snapshot_observed_at":"2026-08-04T13:45:04.489212Z","title":"A novel privacy enhancement scheme with dynamic quantization for federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.489212Z"},"links":{"cited_paper":"/paper/2405.16058","citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:0ce8a9c43b5857413555b9b957bfd97792d24074806ccc338df39080e786b224","observation_id":"b97324aa-48f4-4121-8b7b-26480dbf0fdd","resolution":{"observed_at":"2026-08-04T13:45:04.489212Z","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":"2026-08-04T13:45:04.543884Z","title":"The algorithmic foundations of differential privacy,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.543884Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:e255bfa605ae834ae0180194eec75bb683eb1186440d858c0b530f5bcb714246","observation_id":"535b2626-283f-42d1-af08-0529a9cf9a19","resolution":{"observed_at":"2026-08-04T13:45:04.543884Z","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":"2026-08-04T13:45:04.605212Z","title":"Privacy amplification for federated learning via user sampling and wireless aggregation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.605212Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:d13baa110cbdde285f4bcf14333b56087a5a581e8ac7023938ef81a4c931b847","observation_id":"54482d53-768d-471e-ad31-b93c2b10102c","resolution":{"observed_at":"2026-08-04T13:45:04.605212Z","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":"2026-08-04T13:45:04.694432Z","title":"Boosting and differential privacy,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.694432Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:08df35ea7220aa8b8372d192d9985a922f41c7376bd62e1b48ad76266b63404a","observation_id":"5405d672-ff41-472a-98de-e5b8224ab141","resolution":{"observed_at":"2026-08-04T13:45:04.694432Z","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":"2026-08-04T13:45:04.770557Z","title":"UCI repository of machine learning databases,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T13:45:04.770557Z"},"links":{"citing_paper":"/paper/2509.25906"},"observation_digest":"sha256:79ef536625904aa3dd68a4fe8f8e551a1d73163792a1936c0cd26e309ae82cd3","observation_id":"064dac17-00b1-4ec0-b39d-8b9febe4ed9a","resolution":{"observed_at":"2026-08-04T13:45:04.770557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.25906","last_updated":"2026-05-29T15:06:03Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T13:44:59.284719Z","submitted_at":"2025-09-30T07:51:06Z","title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":45,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":45},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2509.25906."}