{"as_of":"2026-08-08T17:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1c6b317e8b14d4925b0f42aec8dbec0256cde43472d872c3a289abee269856ab","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T10:49:44.518622Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2607.28338/citation-record","integrity":"/paper/2607.28338/integrity","json":"/paper/2607.28338/citation-record.json","paper":"/paper/2607.28338"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T10:49:42.259082Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.259082Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:ead0595a2c7cc8865739cb081b5a6ff636457fc7627a0b39f12aba9a67d4478a","observation_id":"37983617-0e83-4d9c-a2e0-f322842d7f72","resolution":{"observed_at":"2026-07-31T10:49:42.259082Z","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":"2026-07-31T10:49:42.321771Z","title":"k-means++: The advantages of careful seeding","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.321771Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:07590474227d11614546c6d339118363a48e891bbc3613ea373a2ec583ed008f","observation_id":"015b92f0-7507-4361-b66a-28833721e07b","resolution":{"observed_at":"2026-07-31T10:49:42.321771Z","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":"2026-07-31T10:49:42.354584Z","title":"A systematic survey on clustering in federated learning","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.354584Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:d09319e96fd9ccd00da4b2dfc97da5cd62379cfff955360f426bdd9e340a637d","observation_id":"129df1ef-0ae5-4cef-ae20-0b1cf16645a3","resolution":{"observed_at":"2026-07-31T10:49:42.354584Z","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":"2026-07-31T10:49:42.409558Z","title":"A survey on clustered federated learning: Taxonomy, analysis and applications","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.409558Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:b7c99b10ce416dd6a9e19381a80e8f2d9a3c9df0c18f197224a7a4ce3d636c30","observation_id":"1711d2a3-277f-4b51-a077-6ead8ff91134","resolution":{"observed_at":"2026-07-31T10:49:42.409558Z","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":"2026-07-31T10:49:42.470341Z","title":"Practical secure aggregation for privacy-preserving machine learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.470341Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:cb982f78919a9b856a0ac8bc92dcb1a4b4f03a1bbd35387502993e4c0f987556","observation_id":"90bbe04f-5829-43c9-be2f-49fac6f043b2","resolution":{"observed_at":"2026-07-31T10:49:42.470341Z","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":"2026-07-31T10:49:42.531797Z","title":"Federated learning with hierarchical cluster- ing of local updates to improve training on non-iid data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.531797Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:9268b550ecef5c386d65384c2d5788c52f1597db6d2a4eaa736d314c2ca08f0f","observation_id":"27da4ca3-13fe-4bc9-bfee-4711dd8c9d30","resolution":{"observed_at":"2026-07-31T10:49:42.531797Z","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":"2026-07-31T10:49:42.592388Z","title":"Homomorphic encryption for arithmetic of approximate numbers","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.592388Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:3e877b7f2cb5c1735e0b9d395393ceb73203ae6d179bea56108ed2d7673fac0d","observation_id":"1a9966f2-0193-4349-a56a-4dab68c7c924","resolution":{"observed_at":"2026-07-31T10:49:42.592388Z","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":"2026-07-31T10:49:42.623399Z","title":"Maximum likelihood from incomplete data via the em algorithm","venue":null,"work_id":null,"year":1977},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.623399Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:abaefac2e9c3d2cd03971800e0abd287cb3f32059aaf4989ec11c77cf16b16e4","observation_id":"ceeadf5f-c917-400c-af5b-49ac6e3d959e","resolution":{"observed_at":"2026-07-31T10:49:42.623399Z","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":"2026-07-31T10:49:42.683462Z","title":"Heterogeneity for the win: One-shot federated clustering","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.683462Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:7008412ee8cc59443e72868bd2d9ea142035ee53fb3d1e20f5c224bed2434d8d","observation_id":"52c34ce4-1589-4cb5-8f84-3c2707887c6a","resolution":{"observed_at":"2026-07-31T10:49:42.683462Z","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":"2026-07-31T10:49:42.745727Z","title":"Concept decompositions for large sparse text data using clustering","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.745727Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:d6765889085bacfcf9a21e7de8001252b6260ec9303513afe78640621a49987a","observation_id":"e71442b0-59f4-4c5a-9789-49038a8b58a8","resolution":{"observed_at":"2026-07-31T10:49:42.745727Z","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":"2026-07-31T10:49:42.808712Z","title":"Federated-em with heterogeneity mitigation and variance reduction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.808712Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:262d48591d5cc7f5677d40f6bde28b99313556ec8e954066ee5be4df87fcbc6e","observation_id":"8090d542-5d66-44b2-9f3e-dc0ff7821bbc","resolution":{"observed_at":"2026-07-31T10:49:42.808712Z","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":"2026-07-31T10:49:42.857400Z","title":"Flexible clustered federated learning for client-level data distribution shift","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.857400Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:2bcebc7f0fd7b386e813acbdd4cf609421d466d5411055029419cb5ea106cbb8","observation_id":"c4d5dbf1-32f2-48b6-b59f-33318378d63e","resolution":{"observed_at":"2026-07-31T10:49:42.857400Z","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":"2026-07-31T10:49:42.908919Z","title":"Lane, Marc Langheinrich, and Mar- tin Gjoreski","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.908919Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:4d2b0b37fd236a3c98823c8da095209517ab3b4dfdf7e81339ec0889c578ab09","observation_id":"8a360489-de62-47b7-8a32-c4ccc6fd3498","resolution":{"observed_at":"2026-07-31T10:49:42.908919Z","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":"2026-07-31T10:49:42.960078Z","title":"An efficient framework for clustered federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:42.960078Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:9705c72bb9b77ced8e19071bf7cdf7c561edbd399a0fb7ba9c116b76e84465e0","observation_id":"0eafd5a0-25f6-4603-a8bc-ad6cec7bec92","resolution":{"observed_at":"2026-07-31T10:49:42.960078Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.06629","last_updated":"2019-10-09T22:53:13Z","snapshot_observed_at":"2026-07-06T08:00:37.173898Z","submitted_at":"2019-06-16T00:14:53Z","title":"Robust Federated Learning in a Heterogeneous Environment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.06629","snapshot_observed_at":"2026-07-31T10:49:43.018688Z","title":"Robust federated learning in a heterogeneous environment","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.018688Z"},"links":{"cited_paper":"/paper/1906.06629","citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:eadc2078e54b0e465969c22cb400e8d94d24d1e5cc585c2c90dffcb4ab00d2b3","observation_id":"70fe5fcc-4d86-44bb-8617-b4b7b68555a5","resolution":{"observed_at":"2026-07-31T10:49:43.018688Z","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":"2026-07-31T10:49:43.072388Z","title":"Deep neural networks with random gaussian weights: A universal classification strategy? IEEE Transactions on Signal Processing, 64(13):3444–3457, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.072388Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:0fd23a1b798811ab709ea86b4080cad784de13b12a526c1439cc1da9640631eb","observation_id":"845d2e44-0a31-4c1f-9de6-cff2814c5cc7","resolution":{"observed_at":"2026-07-31T10:49:43.072388Z","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":"2026-07-31T10:49:43.102547Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.102547Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:1bcef8b684eec00ea445fcdf0e2330ffd68309059be4d4fad1677bf650627fb7","observation_id":"a647bc8c-fbdf-4c34-99d8-10db37956b30","resolution":{"observed_at":"2026-07-31T10:49:43.102547Z","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":"2026-07-31T10:49:43.219669Z","title":"Advances and open problems in federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.219669Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:71d968c117e0f9297d64e04bfae7c0291a28b6d8782dd474c7f10bc3b5e9a116","observation_id":"637df27b-9907-4cff-b071-76531c322372","resolution":{"observed_at":"2026-07-31T10:49:43.219669Z","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":"2026-07-31T10:49:43.264452Z","title":"Federated hyperparameter tuning: Challenges, baselines, and connections to weight-sharing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.264452Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:c9da22801a39fc716c2084e1e99f10f1fa0d225d035c0257040d1858524f7fbc","observation_id":"70700bcb-97dc-4e49-b838-fec56f0aa976","resolution":{"observed_at":"2026-07-31T10:49:43.264452Z","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":"2026-07-31T10:49:43.301774Z","title":"Recent advances on federated learning: A systematic survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.301774Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:284edf8cfe1adcb4552baf99dc61c50f47c22cccc7b7be7ddf4c8b0c2f965c1f","observation_id":"cf830bd1-2a97-4110-8db0-630cc3d2bfc1","resolution":{"observed_at":"2026-07-31T10:49:43.301774Z","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":"2026-07-31T10:49:43.328606Z","title":"T-friedman test: A new statistical test for multiple comparison with an adjustable conservativeness measure","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.328606Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:8552f4dcf95093a61f0294b3593e1548f1b7131a70a51f6f30bc938448bb10ed","observation_id":"261ec8e9-26db-43fa-a849-574dba544667","resolution":{"observed_at":"2026-07-31T10:49:43.328606Z","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":"2026-07-31T10:49:43.387975Z","title":"Multi-center federated learning: clients clustering for better personalization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.387975Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:05141c68c153aca1a7341529c407494f1c825e4728f027b79a5f765b893bb380","observation_id":"6d89d34e-1024-4d1b-8d77-d8524600117f","resolution":{"observed_at":"2026-07-31T10:49:43.387975Z","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":"2026-07-31T10:49:43.448761Z","title":"Privacy- preserving clustering federated learning for non-iid data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.448761Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:0be7f2bbd07b4898cb8c2ce1c930871a810c18b828e711fb18959af1fdd1106a","observation_id":"6cb4ffe1-6956-44cc-a350-1215bd963311","resolution":{"observed_at":"2026-07-31T10:49:43.448761Z","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":"2026-07-31T10:49:43.508799Z","title":"Structured federated learning through clustered additive modeling","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.508799Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:f01bbcec26c93b9c29bd942364ccc7c3460e5bd0d31314c44c4b090e7e490cc9","observation_id":"c8cbf52b-68e9-4d7b-beda-7cb72942622d","resolution":{"observed_at":"2026-07-31T10:49:43.508799Z","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":"2026-07-31T10:49:43.563778Z","title":"Differentially private clustered federated learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.563778Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:6c319d05f7311483ce3af32cb58f143ac8c32f710d2cd8c7a4090f77d93e3f78","observation_id":"b0020e3a-dbb3-432f-a83b-c084c31d3fab","resolution":{"observed_at":"2026-07-31T10:49:43.563778Z","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":"2026-07-31T10:49:43.626004Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.626004Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:7696a5b8de4f7cf49d2f79b95ea2a96d5ddcd1456a1fdf98bc11977cd571a376","observation_id":"54b839be-412f-46e2-9e52-cec75fdf263b","resolution":{"observed_at":"2026-07-31T10:49:43.626004Z","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":"2026-07-31T10:49:43.692234Z","title":"A survey on security and privacy of federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.692234Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:67a605b08d440f19fd2e6a5b8396888c0eeb0fd3a1b558dfd2b3c3680059b939","observation_id":"50dec6d2-375d-422d-93ab-2bd49786316d","resolution":{"observed_at":"2026-07-31T10:49:43.692234Z","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":"2026-07-31T10:49:43.743021Z","title":"Machine learning: a probabilistic perspective","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.743021Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:0d2ab09f7c237bbecf5b75e2901a54827a5489dc190756fd938c8196a1c7b159","observation_id":"100c5898-d17a-453f-ba54-d17153caa83b","resolution":{"observed_at":"2026-07-31T10:49:43.743021Z","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":"2026-07-31T10:49:43.801827Z","title":"Fedshe: privacy pre- serving and efficient federated learning with adaptive segmented ckks homomorphic encryption","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.801827Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:415960060a9adb54573c232a44937a0b542c8dcdc6b5823b3778e075cce441dd","observation_id":"db0a9593-a4e8-4d60-89c6-83d2a913eb1d","resolution":{"observed_at":"2026-07-31T10:49:43.801827Z","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":"2026-07-31T10:49:43.860186Z","title":"Clustered federated learning: Model- agnostic distributed multitask optimization under privacy constraints","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.860186Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:2f78a007169f9708ba0552b315ccdab7b59b261bb761cdf3b48ac0dd055fdbe8","observation_id":"46af694a-974b-4d8e-9a53-057532cb5a8b","resolution":{"observed_at":"2026-07-31T10:49:43.860186Z","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":"2026-07-31T10:49:43.915383Z","title":"Contrastive encoder pre-training-based clustered federated learning for heterogeneous data","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.915383Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:bdf08b4171effb9b7efbf25e7deb38bf0af24696acc65baf7935f5add743d416","observation_id":"20760c2a-6c5c-4d51-83af-ab88773c0ea7","resolution":{"observed_at":"2026-07-31T10:49:43.915383Z","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":"2026-07-31T10:49:43.976263Z","title":"Efficient distribution similarity identification in clustered federated learning via principal angles between client data subspaces","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:43.976263Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:988137828edc11568ac4e420903b549831c151dce4fb050e55c27522ae5547a6","observation_id":"6c22cb62-fdb5-4be6-9fda-a14641e88d78","resolution":{"observed_at":"2026-07-31T10:49:43.976263Z","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":"2026-07-31T10:49:44.048009Z","title":"Fvfl: A flexible and verifiable privacy-preserving federated learning scheme","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:44.048009Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:4a88392b2ee4540c18cac04a8e1ba11e3dcb425fd7af25809a01c64c146f09c4","observation_id":"8043c1ea-3ca9-4b47-b7e2-1bb6f4465723","resolution":{"observed_at":"2026-07-31T10:49:44.048009Z","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":"2026-07-31T10:49:44.069500Z","title":"Priver- ifl: Privacy-preserving and aggregation-verifiable federated learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:44.069500Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:7e5882706fa8501ed19cc822c0220e02cf0a19c2fed17170535dfe5a3981340f","observation_id":"a51a228f-3401-43c5-9862-3158640039e8","resolution":{"observed_at":"2026-07-31T10:49:44.069500Z","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":"2026-07-31T10:49:44.108813Z","title":"Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:44.108813Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:0d97a7a0ca756918ed10e18505e271e540172563ccf48c8397cafe32a7f2b534","observation_id":"81d8ca1b-b8a4-47d4-8509-e7e4ca132aaf","resolution":{"observed_at":"2026-07-31T10:49:44.108813Z","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":"2026-07-31T10:49:44.141631Z","title":"Heterogeneous federated learning: State-of-the-art and research challenges","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:44.141631Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:9c45a91f52941456da2fa1042eb5d90f96dbbb1068e2ee37a4d4323c8e7929a1","observation_id":"231ad297-7b38-4123-b814-e70a23eed8b5","resolution":{"observed_at":"2026-07-31T10:49:44.141631Z","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":"2026-07-31T10:49:44.251712Z","title":"Stocfl: A stochastically clustered federated learning framework for non-iid data with dynamic client participation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:44.251712Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:ba6f9e599aae631765b2ec1a0ab8074b7776e68f27af26b6f7c976a4df5160e2","observation_id":"e61b49c8-10d4-416c-9d73-330ca89c41cb","resolution":{"observed_at":"2026-07-31T10:49:44.251712Z","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":"2026-07-31T10:49:44.350521Z","title":"Efficient clustering on encrypted data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:44.350521Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:1ac8cd91c4ae1ce67414a2232df2da45e8615264358271b9a76e8774d59b2170","observation_id":"e38685d8-c41e-436f-a6c1-a9cedb17f8a1","resolution":{"observed_at":"2026-07-31T10:49:44.350521Z","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":"2026-07-31T10:49:44.410527Z","title":"Em algorithms for gaussian mixtures with split-and-merge operation","venue":null,"work_id":null,"year":1973},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:44.410527Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:a2cc55fa7e2102a8e8e43664b5c087d2c9e52f6317d10543fe366a9e4a57c939","observation_id":"3b8aa655-2a40-43b8-b038-8d3c234880e6","resolution":{"observed_at":"2026-07-31T10:49:44.410527Z","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":"2026-07-31T10:49:44.518622Z","title":null,"venue":null,"work_id":null,"year":1946},"citing_paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-31T10:49:44.518622Z"},"links":{"citing_paper":"/paper/2607.28338"},"observation_digest":"sha256:5d0bc08e4fb0ebe8f34ab5908fd9f472e15c2756308100fd216e742189d455ca","observation_id":"8d025f90-2121-4e72-a80d-34b410fbd677","resolution":{"observed_at":"2026-07-31T10:49:44.518622Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.28338","last_updated":"2026-07-30T15:04:59Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T12:56:43.202970Z","submitted_at":"2026-07-30T15:04:59Z","title":"Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":39,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":40},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2607.28338."}