{"as_of":"2026-08-16T12:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1828983232527c5ef8d5a6ec96635269e507c338008486775caccfd90210453c","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T03:50:09.401292Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2602.06838/citation-record","integrity":"/paper/2602.06838/integrity","json":"/paper/2602.06838/citation-record.json","paper":"/paper/2602.06838"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:06.622053Z","title":"Cellular traffic prediction via byzantine- robust asynchronous federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:06.622053Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:a7c07f5909cfbd101dd6855cf1472a29154f5ae8fe5c0dd6d94dc7157319a068","observation_id":"7387d9eb-638b-48bc-b68e-77cdb90f6ed1","resolution":{"observed_at":"2026-08-03T03:50:06.622053Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:06.633511Z","title":"Image classification using federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:06.633511Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:c2db37c12a1c638112b7bbd7ac6e28af0c48e55b41fc1a39459da348d904378e","observation_id":"790243bb-bf65-484d-a681-a2c66e1de137","resolution":{"observed_at":"2026-08-03T03:50:06.633511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:06.718563Z","title":"Enhancing medical image classification via federated learning and pre-trained model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:06.718563Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:7da1cfe4fd412ec1f61e40dc6003e255e9469766d5d5b732b642090696df4b49","observation_id":"95da676e-173d-4d3a-a6f5-bbd8c5b3b8b0","resolution":{"observed_at":"2026-08-03T03:50:06.718563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:06.828878Z","title":"FGS-FL: Enhancing federated learning with differential privacy via flat gradient stream,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:06.828878Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:bd23cc8836f4be7ebf07f032c0c5b5ba8f4a86b0178bfcbdd39d3f591ebd6cac","observation_id":"ca661e90-5447-477a-ae42-d19c15756d73","resolution":{"observed_at":"2026-08-03T03:50:06.828878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:06.900138Z","title":"Federated semi-supervised medical image classification via inter-client relation matching,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:06.900138Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:0e6b01e1608d9a587cf0284fdb0b1f7be4bb5c28f339acd7a70115cca39a3414","observation_id":"d47e7db8-fdf4-4db8-933a-f7b5bc6078e7","resolution":{"observed_at":"2026-08-03T03:50:06.900138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:06.989851Z","title":"Uldp-FL: Federated learning with across-silo user-level differential privacy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:06.989851Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:914398e7836845fa60df1bc322f560ffa171e93b337f5d11db651440b2269e8f","observation_id":"15592a0f-9b23-4b2e-b33c-cdbe7c6c6ede","resolution":{"observed_at":"2026-08-03T03:50:06.989851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.080852Z","title":"Dyn-D2P: Dynamic decentralized differential privacy for peer-to-peer federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.080852Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:a5856f85c4ac7402d0ea928019fc56353b4805dbad72dcf59d0590dbc0488907","observation_id":"8f20d7a9-4316-44b4-9575-dafda53fe1bd","resolution":{"observed_at":"2026-08-03T03:50:07.080852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.154735Z","title":"Toward the flatter landscape and better generalization in federated learning under client-level differ- ential privacy,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.154735Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:ecc1fffd14cf37a9e726016c512ab9e0dcd0e9efba9a725aa15fdca1a1ad9059","observation_id":"b8653961-69e9-4d12-84d8-58809f363d1c","resolution":{"observed_at":"2026-08-03T03:50:07.154735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.259711Z","title":"One-shot empirical privacy estimation for federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.259711Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:e4363784445964b032689cd92cf10ca42b85b8bf8ecc643e008aeebe4ea65d76","observation_id":"f521b761-95de-457d-8ec7-0bb122919b85","resolution":{"observed_at":"2026-08-03T03:50:07.259711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.335057Z","title":"Asynchronous decentralized federated anomaly detection for 6G networks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.335057Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:34ca4693f846a9bdb85ce3e8a5119e7dda304cf4786044914a2ae7fbf8ad9eb6","observation_id":"32556e75-868c-4b42-a4a3-187d26e88f34","resolution":{"observed_at":"2026-08-03T03:50:07.335057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.415337Z","title":"Belt and braces: When federated learning meets differential privacy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.415337Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:cb23c72a8c6541cf25175a8a19e0733bd15e361786d5f1b2c2efcd5285ee32d8","observation_id":"1ed85561-e5f1-4a13-a242-023909b15fa5","resolution":{"observed_at":"2026-08-03T03:50:07.415337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.509291Z","title":"Siren ++: Robust federated learning with proactive alarming and differential privacy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.509291Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:f9c85bae523d5db86b3b416d0779427136d0fc71698c56592f95bb523445d912","observation_id":"52ed07b8-4cf7-47b3-ad69-1311d76ff0b4","resolution":{"observed_at":"2026-08-03T03:50:07.509291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.620056Z","title":"CAMEL: Communication-efficient and maliciously secure federated learning in the shuffle model of differential privacy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.620056Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:e008e0b8585765da8276b868fe5414c0958dba2be804461aadfb715251606a66","observation_id":"82393375-ff9d-40a4-aa0d-1141467babe3","resolution":{"observed_at":"2026-08-03T03:50:07.620056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.751703Z","title":"Noise-aware algorithm for heterogeneous differentially private federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.751703Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:547498e5e6906c000696f736243a0e1f03c6575d94ffc3a149c1ba77a2745215","observation_id":"7e247b6e-5190-49a1-b979-691a20c33dc7","resolution":{"observed_at":"2026-08-03T03:50:07.751703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.801399Z","title":"Federated learning with sparsified model perturbation: Improving accuracy under client-level differential privacy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.801399Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:c71bb0e12c609b87e9238e5e528a09dd161ff1b496fd4229c5d4e5df14568e10","observation_id":"39ad4457-193f-45de-9572-1a476c05829c","resolution":{"observed_at":"2026-08-03T03:50:07.801399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.912145Z","title":"Harnessing sparsification in federated learning: A secure, efficient, and differentially private realization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.912145Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:718b81e56856b84dda6156184f6db65105aa00ad89c6341f4eb1ce4deb9c66b9","observation_id":"81cf1190-e101-4b55-aaf7-8b137fec1718","resolution":{"observed_at":"2026-08-03T03:50:07.912145Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:07.986974Z","title":"Efficient federated learning privacy preservation method with heterogeneous differential privacy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:07.986974Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:ea4f03e3df276bad20b5aa1f133a47aa34b44efdf5a54698f9cd5bfbb5fccf0b","observation_id":"e02d0716-0720-4028-8b0a-0bdea981037d","resolution":{"observed_at":"2026-08-03T03:50:07.986974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:08.097614Z","title":"Differentially private fed- erated learning with time-adaptive privacy spending,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:08.097614Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:806ad032e2c4a71f47057507d63f3981088c1b949daf7ab02f4194419e1aeafd","observation_id":"429dbc70-a947-47a3-9007-60ce8889df0d","resolution":{"observed_at":"2026-08-03T03:50:08.097614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:08.186451Z","title":"Privacy-preserving federated learning for industrial edge computing via hybrid differential privacy and adaptive compression,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:08.186451Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:5b6d0275a4673dae5e29005cadb53c1e8a3d810fc6daaa25a8134c840ece9d38","observation_id":"33bd615c-d803-4dc3-ada2-d14de84fd3d1","resolution":{"observed_at":"2026-08-03T03:50:08.186451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:08.294097Z","title":"Local differential privacy feder- ated learning based on heterogeneous data multi-privacy mechanism,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:08.294097Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:2312db1cb47196e186ab6d0a903cbe749d83f130bc7ef6283051bb2592d8dea0","observation_id":"cd933790-498d-417d-8076-f1b6e10859c1","resolution":{"observed_at":"2026-08-03T03:50:08.294097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:08.417546Z","title":"DP-PSAC-FL: Differentially private federated learning based on per-sample adaptive clipping and layer- wise gradient perturbation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:08.417546Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:9c6ee856e7eb13430e8bfcbd1193d2dc9d3cd4901cf783b3362446ed258a41de","observation_id":"49ad84a0-654f-4003-ab12-697623c9f958","resolution":{"observed_at":"2026-08-03T03:50:08.417546Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:08.512274Z","title":"Towards the robustness of dif- ferentially private federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:08.512274Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:698786cf57d8d82210661c1be11c1b5fad6e3b289e6ffcc8c3d7214678bfd1b5","observation_id":"950b792f-b382-40ef-af3d-6ca48b9f4de2","resolution":{"observed_at":"2026-08-03T03:50:08.512274Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:08.594033Z","title":"Dynamic sparse training with structured sparsity,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:08.594033Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:77e30c23525a15f05ea66656678fe42d6a404edcc5e7181b9a90d1c7b6fd78f5","observation_id":"c787abaa-ffc4-4099-9428-b7e66d19b242","resolution":{"observed_at":"2026-08-03T03:50:08.594033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:08.677693Z","title":"An improved analysis of per- sample and per-update clipping in federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:08.677693Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:112da4eee3cdf70225b8d4dc0bdce771c6b081fd237e4b404de7e83caed6c66b","observation_id":"ce16e84c-79c6-4adf-8369-73e3f28ccc49","resolution":{"observed_at":"2026-08-03T03:50:08.677693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:08.747905Z","title":"Adaptive clipping for differential private federated learning in interpolation regimes,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:08.747905Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:d19562280d473f4d161f5197b3b6c0f63039ee8efae1faa72cddee83323292dd","observation_id":"0f905731-2457-4b41-b7fb-4cf85db38be1","resolution":{"observed_at":"2026-08-03T03:50:08.747905Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:08.843884Z","title":"Exponential moving average of weights in deep learning: Dynamics and benefits,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:08.843884Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:c71334c341707a2024be58727ddd37b5f15d5cb56007a88a1a47261ac8c49765","observation_id":"213bcdfe-a834-4934-91c3-af1ec409b0ae","resolution":{"observed_at":"2026-08-03T03:50:08.843884Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:08.940439Z","title":"Distributed distributionally robust optimization with non-convex objectives,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:08.940439Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:112d4b4bc4b705e39788fb0386e7e24ffa56107a6d56a076111cc0bc35e0c141","observation_id":"59e71677-0701-491c-9ace-7b888c05318c","resolution":{"observed_at":"2026-08-03T03:50:08.940439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:09.016322Z","title":"Understanding global ag- gregation and optimization of federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:09.016322Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:5602742844423ab21f4d8a9e4190fd79aa8c678da83589aa1a0ed88e71895b6f","observation_id":"c4d85b92-8a28-45cb-96e6-ecb21a19dee5","resolution":{"observed_at":"2026-08-03T03:50:09.016322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:09.118906Z","title":"Self-adaptive asynchronous federated optimizer with adversarial sharpness-aware minimization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:09.118906Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:86128c334922787bcffdf61ff2e14b81c1d1fb097578a3431531158cd4f683b8","observation_id":"0527c60d-6b99-4ff7-b1ed-c1ebf98d8fe6","resolution":{"observed_at":"2026-08-03T03:50:09.118906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:09.216921Z","title":"Differentially private federated learning with an adaptive noise mechanism,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:09.216921Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:8f8312ce67de2adcee96013b260315f7582254dcb6666bbf8465681a97a739ab","observation_id":"a9452bbc-3139-4fb7-8b94-7a797e8f52f7","resolution":{"observed_at":"2026-08-03T03:50:09.216921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:09.354033Z","title":"Differentially private federated learning on Non-IID data: Convergence analysis and adaptive opti- mization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:09.354033Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:2aaaca53d89387522c858e0a1b266bfc22eef71f1c1dcf7a5a1b23c0a61ab7c6","observation_id":"0286cad9-a0e7-4b14-bff8-7679db4d75de","resolution":{"observed_at":"2026-08-03T03:50:09.354033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T03:50:09.401292Z","title":"A lightweight differentially private federated learning framework for edge intelligence,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T03:50:09.401292Z"},"links":{"citing_paper":"/paper/2602.06838"},"observation_digest":"sha256:6425f1503a83de7cecdb171f2db4d8d792b851504b6a222fd7620c71319dbe4c","observation_id":"b353b11e-0355-488e-9b87-3fd871287a03","resolution":{"observed_at":"2026-08-03T03:50:09.401292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2602.06838","last_updated":"2026-07-08T05:17:01Z","latest_version":3,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-09T03:08:08.907026Z","submitted_at":"2026-02-06T16:27:33Z","title":"An Adaptive Differentially Private Federated Learning Framework"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":32},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2602.06838."}