{"as_of":"2026-08-18T22:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:440b8163f792fc33d20b3a2c2671039f6d47d1789aa53a71a066fee9f6d88ae3","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":"2026-05-10T00:29:43.521902Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T00:29:43.521902Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-05-10T00:29:46.932769Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"cited_work":{"arxiv_id":"2604.20596","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.20596","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","venue":"cs.LG","work_id":"70113a2b-364a-469d-b732-8387edfb4801","year":2026},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"cited_paper":"/paper/2604.20596","citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:bc4d9310a994d9b6f45f3c495676e0e3e0f498b50d829b15c5f627723674939f","observation_id":"dc28dd6d-dbf0-4af9-a089-fb85799118f0","resolution":{"observed_at":"2026-05-10T00:29:46.934433Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2604.20596/citation-record","integrity":"/paper/2604.20596/integrity","json":"/paper/2604.20596/citation-record.json","paper":"/paper/2604.20596"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"cited_work":{"arxiv_id":"2604.20596","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.20596","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","venue":"cs.LG","work_id":"70113a2b-364a-469d-b732-8387edfb4801","year":2026},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"cited_paper":"/paper/2604.20596","citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:bc4d9310a994d9b6f45f3c495676e0e3e0f498b50d829b15c5f627723674939f","observation_id":"dc28dd6d-dbf0-4af9-a089-fb85799118f0","resolution":{"observed_at":"2026-05-10T00:29:46.934433Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Federated Learning (FL) Overview of FL: At the start of each communication roundt, a global modelW t is provided by the server and a randomly sampled user setK t is constructed","venue":null,"work_id":"8323d1db-b2c2-459e-b500-fe44d82bc0fb","year":null},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:302655b6ee12309323e1d11cdeca45c398385a65936bae58568dcc5b144c43fe","observation_id":"48d00eca-e915-49d8-8b5e-874afb360dfe","resolution":{"observed_at":"2026-05-23T11:15:36.504177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Overview Our proposed method PINA consists of two stages: (1) Cluster Model Initialization and (2) Clustered Model Training","venue":null,"work_id":"1a80f7c0-16e7-4b9e-b91d-885e596b10a0","year":2034},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:a5ec48373927aba05d7a25ba4700fe0002f8f3e8565a06d6838b9023448a6fc2","observation_id":"4572a58a-8d89-448a-9ece-8ae95ebdb237","resolution":{"observed_at":"2026-05-23T11:15:36.490131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fol- lowing [2, 31, 26], we simulate a cohort size of 10k with a smaller cohort size to achieve a more realistic signal-to-noise ratio which represents industry scale more closely","venue":null,"work_id":"9fd0277a-79ee-451f-a422-7e1031a3d84f","year":null},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:643df5fc3c5d563a92c6a4732a2f7d9fb91a63626e2e97c32775d0e60489121a","observation_id":"c95a18ee-6f51-4820-bc32-d8e9a9999e76","resolution":{"observed_at":"2026-05-23T11:15:36.496358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"d3075ef8-f299-4241-bb5e-dea4a3039829","year":null},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:cb6f0f00d017ba518275206bd42317813d21d6d547059346610c9d9e5f7893c8","observation_id":"b73cf14f-5627-48f2-bee9-04e6030b3f8d","resolution":{"observed_at":"2026-05-23T11:15:36.484517Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Communication-efficient learning of deep net- works from decentralized data","venue":null,"work_id":"7bff6949-d6ce-42ff-a604-ae233dba7739","year":2017},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:087775480db52ae75f99cbbe5e7ad02ee9e653258cb51aed641d64d25f43ec5d","observation_id":"58611dd8-c01e-4b7b-8425-c79cf4ef8368","resolution":{"observed_at":"2026-05-23T11:15:36.500363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning differentially private recurrent language models","venue":null,"work_id":"d813551e-041d-4d77-8707-ef126938d0b7","year":2018},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:4a844e53434d95796eac7b957ef6808761e9522a30456b694f8e3befe7dc2525","observation_id":"05a05117-a72a-40a4-a395-b07444ab9122","resolution":{"observed_at":"2026-05-23T11:15:36.508891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Calibrating noise to sensitivity in private data analy- sis","venue":null,"work_id":"e88fdcf3-1800-4ba4-842e-e9c47d51d4e5","year":2006},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:2296762ecc64b35fbded4a528b462b59f1fa6ad353e238b4c86d9b97bcd1d099","observation_id":"dd00ad72-caef-47a7-b63d-b743494188ef","resolution":{"observed_at":"2026-05-23T11:15:36.480932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"What can we learn privately?","venue":null,"work_id":"d6237845-3970-4990-af1d-0673e5c94878","year":2011},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:11a0fdae07fe7024432f39e0b4657107665d835fca9ece2f258182225f9365e9","observation_id":"fa4031e5-81ed-4227-a41b-68e39eee8bfa","resolution":{"observed_at":"2026-05-23T11:15:36.549699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Practical secure aggregation for privacy- preserving machine learning","venue":null,"work_id":"c6ad8804-6c36-4405-8015-b5dcb857aa74","year":2017},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:924957381ca39eaee3ce04cc52b889e2f4e16f8d8fd7e433f0356ebb68164441","observation_id":"79903f06-76ee-430e-936b-40939cd94ad9","resolution":{"observed_at":"2026-05-23T11:15:36.477277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Benchmarking secure sam- pling protocols for differential privacy","venue":null,"work_id":"2aebe885-44b2-4ad4-8048-5080fba11129","year":2024},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:abc90c4c66da53228a467167303ad44a58026c2d8a60b00c0623a94ae1cb43be","observation_id":"d4f675d0-09b3-4288-a9ed-745aa43f8d77","resolution":{"observed_at":"2026-05-23T11:15:36.473150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Federated learning: Challenges, methods, and future directions","venue":null,"work_id":"18a09b51-cff6-4730-9e0b-53d66292101e","year":2020},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:095debee311c49c21ce01502de1fbcbfdfeb4b91b1ad729f9c57f51e531f05b9","observation_id":"fba7236e-cadd-416e-9a0f-62ce54a6174c","resolution":{"observed_at":"2026-05-23T11:15:36.518705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Federated learning with differential privacy: Algo- rithms and performance analysis","venue":null,"work_id":"3c4bd8e0-5ff1-44c8-adc8-c3bb4346d389","year":2020},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:e3db08865949eccce6a8d39993d00361c2eed2fc5102f5882316cbb9480dcfb8","observation_id":"66aa5807-f70b-4346-a43c-12a4e889d9d7","resolution":{"observed_at":"2026-05-23T11:15:36.530278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Differentially private federated learning on heterogeneous data","venue":null,"work_id":"dc008462-7f76-4ff6-b95c-cd3358af19d7","year":2022},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:48c342bd7332e911bff96dabaa467d1e7750a1dc7645790e19f921b829d8d138","observation_id":"789510a0-e0af-47bd-b812-c633f2a27dee","resolution":{"observed_at":"2026-05-23T11:15:36.538594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"{PrivateFL}: Accurate, differentially private federated learning via personalized data transformation","venue":null,"work_id":"ca611ade-0778-42f2-9a42-1585a31ec22c","year":2023},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:ea48632cfe8138e63acac1a30b89ab77e312b7fef3ca33f93b87edbd1d093c74","observation_id":"bfff5f52-c686-44b9-8007-d8897a56f922","resolution":{"observed_at":"2026-05-23T11:15:36.522575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An efficient framework for clustered federated learning","venue":null,"work_id":"0b194c46-3082-4c5b-b6be-5b0fc0afdfa8","year":2020},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:1f854310918a75d3d61b32fc2d043d8bac0204239c0f1aa81f234982dff781da","observation_id":"6a1e15d3-2bf6-4bd3-89c2-fe299cd5f7ac","resolution":{"observed_at":"2026-05-23T11:15:36.561744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Clustered federated learning: Model-agnostic distributed multitask optimization under privacy constraints","venue":null,"work_id":"d7f08e29-5fe6-448f-85ca-50db6fac98e3","year":2020},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:2f108476c641a9533d1a4703a7e0ef1bb367292b5a5d2e3a0c190b6f1e38263b","observation_id":"8d22e7f1-dbe2-47a6-a4c8-fd2e0ff8540d","resolution":{"observed_at":"2026-05-23T11:15:36.514972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The algorithmic foun- dations of differential privacy","venue":null,"work_id":"a18c5596-6a80-4c41-b146-bd2b13412ff0","year":2014},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:faf7db5c8991529632dc7302989e6de9a6442b2199afc15c5cb7ce7ab290bd22","observation_id":"d0ac2a9a-fc77-4cd8-bfc8-1aa6c509e273","resolution":{"observed_at":"2026-05-23T11:15:36.526209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep learn- ing with differential privacy","venue":null,"work_id":"41ce4e36-17d0-422e-b56f-9ddef66760df","year":2016},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:4a3fa35a1e40a6b94a43343c11df229db74e21ab1cb8b0e99a895153d812c48f","observation_id":"f90cd110-596f-4b0e-a28d-2b881112ba7f","resolution":{"observed_at":"2026-05-23T11:15:36.534469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"R ´enyi differential privacy","venue":null,"work_id":"d7920f8d-549c-4826-8415-7656f59ab037","year":2017},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:cc331abc5fc61be799b9e5b30618d185b46b7aade381eee671afc9b56b2892de","observation_id":"de8456b4-23d2-4004-9e24-3602232b844d","resolution":{"observed_at":"2026-05-23T11:15:36.542347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hypothesis testing interpretations and Renyi differential privacy","venue":null,"work_id":"4a0d47b8-debe-47e0-bdb3-556b7bdfce94","year":2020},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:fb5d2cbea508d08ff2e9f063d86ffe8457efe58c074cbe1ba9cb2a1a97adbbaf","observation_id":"8e2d26a9-4724-4a93-8a36-a3f5888005ad","resolution":{"observed_at":"2026-05-23T11:15:36.545972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Privacy am- plification by subsampling: Tight analyses via couplings and divergences","venue":null,"work_id":"bf0f196e-bf3a-4732-916e-5455d411d93c","year":2018},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:7c474db2c057e153476549efe1603379044fe24de8aed18e7b100565cf3ce7bb","observation_id":"beead5b1-30e7-43b8-a21e-41133b3e7eb7","resolution":{"observed_at":"2026-05-23T11:15:36.603221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":"b2ef8ecf-780e-42e1-b4d1-9feca90f531c","year":2022},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:2c5287179c935f35d97ae6e33ae1c316f34b20f0b5f127e1d15179c669c49bd0","observation_id":"dbf4c71c-c302-4aac-a847-944de6280825","resolution":{"observed_at":"2026-05-23T11:15:36.619672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient distribution similar- ity identification in clustered federated learning via principal angles between client data subspaces","venue":null,"work_id":"bf234a8a-c60b-43d2-a490-fa3882b6b151","year":2023},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:8ac5a3802f80f1db6a5bc3318b3d8adefb74388852d0f6b9c286f905330d4315","observation_id":"0195b001-240a-4741-9ca0-98781e22dba6","resolution":{"observed_at":"2026-05-23T11:15:36.594982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Clustered feder- ated learning with adaptive local differential privacy on hetero- geneous IoT data","venue":null,"work_id":"63debb9e-7a60-4a4b-94f5-7bf2a8813a40","year":2024},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:1d1014ff2d715a20d35032ce752c3a87a49fa79c558ed28fc9fc292f6e8527d6","observation_id":"79c9f96e-24c8-4f7a-afa9-02f5acf5763e","resolution":{"observed_at":"2026-05-23T11:15:36.591336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mitigating disparate impact of differential privacy in feder- ated learning through robust clustering","venue":null,"work_id":"917aae8d-bf46-43a5-8ac1-68c84dc16d2a","year":2024},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:49a075b92b960a7446c9d8d7af16365e59636ac36228ea4ab6598cb8405c332e","observation_id":"36574306-289a-4772-bbcf-4755b9170605","resolution":{"observed_at":"2026-05-23T11:15:36.598717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scaling language model size in cross-device federated learning","venue":null,"work_id":"32483a0a-36be-483a-8c77-ce88205d7b74","year":2022},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:b0599284c01288cf6953ccc8b6d56974e0aae722c0da8ce5555f99fc10f43475","observation_id":"c47a143b-5707-4e69-a450-219c0c091bc2","resolution":{"observed_at":"2026-05-23T11:15:36.624362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Secure aggregation for clus- tered federated learning","venue":null,"work_id":"75a5075c-fc4f-4e90-bead-75ded51780f0","year":2023},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:24f777aaad2d52eb6d0c5c5a6595facdf345000dcdb20e71950a50ad7423a3d6","observation_id":"11b3f9d2-bc31-45f2-9c34-95a059f064cf","resolution":{"observed_at":"2026-05-23T11:15:36.632675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Clus- terguard: Secure clustered aggregation for federated learning with robustness","venue":null,"work_id":"25e28802-5e78-4300-ae65-147a2cb74846","year":2024},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:b0fd674ab828eb420a85965dc87c51b1521bc94c16e900ca5ddd0905b256b75a","observation_id":"255e88f5-01dc-418a-8f4e-59e698df32e1","resolution":{"observed_at":"2026-05-23T11:15:36.577479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Federated learning from pre-trained models: A contrastive learning approach","venue":null,"work_id":"5438339c-b5d7-48c8-a104-cbac7540edb9","year":2022},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:abb0482123df1aecf1615f53677a64ab448699c0176bdbdd190944948dcba19b","observation_id":"03108170-ac7f-4f55-9149-df9e502dca3a","resolution":{"observed_at":"2026-05-23T11:15:36.583574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.06368","last_updated":"2025-02-17T11:23:32Z","snapshot_observed_at":"2026-08-16T13:53:47.563664Z","submitted_at":"2024-05-10T10:10:37Z","title":"DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation","version":4},"cited_work":{"arxiv_id":"2405.06368","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.06368","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dp-dylora: Fine-tuning transformer-based models on-device under differentially private federated learning using dynamic low-rank adaptation","venue":null,"work_id":"48ee37dc-312e-41e2-9463-adbd7b96cecc","year":2024},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"cited_paper":"/paper/2405.06368","citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:aa38d73251224e6f5f1e7a17b52c7a7f5840e902629b49487a24c948453f5e6c","observation_id":"74063e11-2fcd-4a22-8120-97bc65a464a8","resolution":{"observed_at":"2026-05-10T00:29:46.931363Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Rethinking architecture design for tackling data heterogeneity in federated learning","venue":null,"work_id":"a8f34f7a-c9a6-43f7-9319-843bc42f2985","year":2022},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:3ea21948bcbd9b9497583ed999af6239293de2aabab9805faff46df5afb1c589","observation_id":"e773f537-17b7-4dc0-a9b9-6058a0af7cb5","resolution":{"observed_at":"2026-05-23T11:15:36.573722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A hybrid approach to privacy-preserving federated learning","venue":null,"work_id":"17d4e223-ee6f-4832-96af-1cfd0bb75d88","year":2019},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:364ec09ca7724079478bfec6dcd4d376c4948ecd95ae207d02f1c774b3f23e18","observation_id":"e05b5662-a0ad-4cb1-889e-ec284ca35d6c","resolution":{"observed_at":"2026-05-23T11:15:36.565188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A comprehensive com- parison of multiparty secure additions with differential pri- vacy","venue":null,"work_id":"2d94790d-1985-4f8b-b36a-56b22ccabc7c","year":2017},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:1993485ec26da5765e30b84cbe2dfc631f44a464c13345b3454af3ce3532a9b4","observation_id":"f67304ee-c022-41f3-869e-3d4b17056396","resolution":{"observed_at":"2026-05-23T11:15:36.569222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An analysis of variance test for normality (complete samples)","venue":null,"work_id":"51dca935-288c-4566-b764-dfc3f9857a1b","year":1965},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:fdce87431ec0a1fd2170ecdf0fbf14d106a45bf76720eef329a9e47cea0ab72e","observation_id":"a0b5131c-1d46-4d5d-9acf-955a47bc712e","resolution":{"observed_at":"2026-05-23T11:15:36.587655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"FLAIR: Federated learning annotated image repository","venue":null,"work_id":"f4933d5d-e6a4-441a-90ea-c88b43087a67","year":2022},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:04d53725b9ea5ed670d6dacdfa68a90de7cc144d3bfde5be9ed10239ad3bd176","observation_id":"a5d4c2bc-0ccd-4e17-affb-13508c01b2ea","resolution":{"observed_at":"2026-05-23T11:15:36.628456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Federated optimiza- tion in heterogeneous networks","venue":null,"work_id":"d1262a92-e10f-4110-91b5-57b87ca00bd2","year":2020},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:f8028aa3e53a038c21446df284ecc214992977c2d3cf70b92fd96f17fe264566","observation_id":"452082ce-81bd-42d8-8238-030f00837a95","resolution":{"observed_at":"2026-05-23T11:15:36.640468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","venue":null,"work_id":"f4eb79bd-5625-4898-866f-4eb9df3e91e1","year":2020},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:34f21f32dd5a83fcba386080b419cec25a4df8b38976bd223cbb0832be2d1698","observation_id":"0b1ccbb2-81b0-4c37-81e9-0a839a238340","resolution":{"observed_at":"2026-05-23T11:15:36.636555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scaffold: Stochastic controlled aver- aging for federated learning","venue":null,"work_id":"662ce2d7-63ea-49b2-89d4-9a8a4d0a6723","year":2020},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:7fa11b596bdcff3961bf37e3717a697b621c0ba9dd9d550abe122361c274b729","observation_id":"c388f186-b241-4c15-9eef-e7e3ca27d0e7","resolution":{"observed_at":"2026-05-23T11:15:36.553532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Breaking the centralized barrier for cross-device federated learning","venue":null,"work_id":"eb73ca7f-826a-4f2f-a082-618760e16e21","year":2021},"citing_paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-10T00:29:43.521902Z"},"links":{"citing_paper":"/paper/2604.20596"},"observation_digest":"sha256:56b3978d6ff8ac9b4efc5a85a22c7ad8ec41033cdb6dd93cf3dfe64af2c9b84a","observation_id":"01a3ea5e-2426-40df-8d6c-c03b80536d6c","resolution":{"observed_at":"2026-05-23T11:15:36.557293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.20596","last_updated":"2026-04-22T14:12:18Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T18:04:52.654149Z","submitted_at":"2026-04-22T14:12:18Z","title":"Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":1,"verified_exact":1,"verified_fuzzy":37},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 1 inbound Pith citation observation for arXiv:2604.20596."}