{"as_of":"2026-08-16T15:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f6af1dd6c4c4255bcd5857f4153232bee6781910f7bbba1c64f87314cd3e73b6","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:46:55.757872Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"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/2505.06651/citation-record","integrity":"/paper/2505.06651/integrity","json":"/paper/2505.06651/citation-record.json","paper":"/paper/2505.06651"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.482855Z","title":"Deep learning with differential privacy","venue":null,"work_id":"11c4a290-f451-4cef-92c9-6f800fc85f9a","year":2016},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.539442Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:68d652c9632356a49fe095a5084d5258a51e99932668413382a04297d93a5ad7","observation_id":"105fcaa7-e5ef-4e31-be79-2492ebe94fc4","resolution":{"observed_at":"2026-08-15T22:46:56.487597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.11124","last_updated":"2018-11-27T17:34:27Z","snapshot_observed_at":"2026-08-14T17:52:32.629099Z","submitted_at":"2018-11-27T17:34:27Z","title":"LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning","version":1},"cited_work":{"arxiv_id":"1811.11124","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.11124","snapshot_observed_at":"2026-08-15T22:46:55.871471Z","title":"LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning","venue":"cs.LG","work_id":"82fa503e-9076-440f-bc7e-5b6187e31668","year":2018},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.563329Z"},"links":{"cited_paper":"/paper/1811.11124","citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:53a071f9070fba38e4c9c1022e12e173e6c1758c7efd5944b421d0199b237bae","observation_id":"7a8e9e77-ca57-4f50-8ccc-2bfbcaafd304","resolution":{"observed_at":"2026-08-15T22:46:55.876314Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.02383","last_updated":"2019-05-30T23:51:04Z","snapshot_observed_at":"2026-08-14T16:36:19.666208Z","submitted_at":"2019-05-07T06:57:19Z","title":"Gaussian Differential Privacy","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.02383","snapshot_observed_at":"2026-08-15T22:46:55.573030Z","title":"Gaussian differential privacy","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.573030Z"},"links":{"cited_paper":"/paper/1905.02383","citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:e59d21b6abefd5bcfe34ad01871a82c5c9e74e09de068890a12de6753c03911e","observation_id":"adde7926-fb00-4e0f-9b9f-20d37db0e5b5","resolution":{"observed_at":"2026-08-15T22:46:55.573030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.411679Z","title":"Dynamic differential-privacy preserving sgd","venue":null,"work_id":"36139309-528b-4c36-ac33-9810c0ccb939","year":2021},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.577737Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:f5f1e4f0c2e107fa6f90e1c8476ae2c2227091487f94dc7ef5049b405306575b","observation_id":"da0b32bc-1e00-4a8b-8670-3e7474f0d29c","resolution":{"observed_at":"2026-08-15T22:46:56.416449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.398464Z","title":"Our data, ourselves: Privacy via distributed noise generation","venue":null,"work_id":"0d2d9a8c-896a-4c7a-8c48-9a847409efc2","year":2006},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.582313Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:0226775907933873cac6110158e0f2c91b1aed37e3da573c4d629ee16781551b","observation_id":"562a9478-08a8-4164-9d73-bed4496b7d52","resolution":{"observed_at":"2026-08-15T22:46:56.402768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.334961Z","title":"Towards practical differentially private convex optimiza- tion","venue":null,"work_id":"0d2f8211-acb8-46a5-93b3-29e2dd0978b9","year":2019},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.604430Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:ad03f35f5f543e827e5f93d8d4f0daa163d004461b02fd1bcaede4f8a7066a36","observation_id":"6a895dfc-1a6b-42a0-9ea7-2ed1f333f1a5","resolution":{"observed_at":"2026-08-15T22:46:56.339156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.321750Z","title":"Gossip-based computation of aggregate information","venue":null,"work_id":"baf6d2c0-02d8-4c63-b4d3-b1d30bc7b65d","year":2003},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.608635Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:e6710fb5ddcafc0c05933d15bc7f5f688aa7e5090794dbbb01048af1c5264e23","observation_id":"501e01cd-61f9-49e8-ae35-caaafb7516da","resolution":{"observed_at":"2026-08-15T22:46:56.325948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.294612Z","title":"Learning multiple lay- ers of features from tiny images","venue":null,"work_id":"75395654-4d3d-4d1d-8782-32ad3cb4b826","year":2009},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.616815Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:1c5db0a88bb305c4ee3c7a708282a2505648f10234dc50eb8abbc181d3740374","observation_id":"4ec16b8d-cdab-4ef9-bf00-7b9d65de5b14","resolution":{"observed_at":"2026-08-15T22:46:56.299701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.268445Z","title":"Convergence and privacy of decentralized nonconvex optimization with gradient clipping and communication compression","venue":null,"work_id":"3b15da75-10bd-4fac-b77e-4002bc6cd20b","year":2025},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.625737Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:e674b992e0d323f0fe2468de9e71fba89edab5bf33a670419f5cd0a1371a568d","observation_id":"bb1480b0-901f-4970-82b9-0ae4014ff85e","resolution":{"observed_at":"2026-08-15T22:46:56.272775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.07902","last_updated":"2019-12-17T09:49:38Z","snapshot_observed_at":"2026-07-06T08:45:03.591439Z","submitted_at":"2019-12-17T09:49:38Z","title":"Asynchronous Federated Learning with Differential Privacy for Edge Intelligence","version":1},"cited_work":{"arxiv_id":"1912.07902","doi":null,"metadata_source":"pith","pith_arxiv_id":"1912.07902","snapshot_observed_at":"2026-08-15T22:46:55.821222Z","title":"Asynchronous Federated Learning with Differential Privacy for Edge Intelligence","venue":"cs.LG","work_id":"fa75498b-f413-43db-b755-940f445d57a7","year":2019},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.634826Z"},"links":{"cited_paper":"/paper/1912.07902","citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:c657fba26538b1df140f57b4c4433b1f5f2f44735fb86c938960f348a3eaa341","observation_id":"a2218972-7752-4fc7-a8f7-3ee6901d663b","resolution":{"observed_at":"2026-08-15T22:46:55.827781Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.255115Z","title":"SoteriaFL: A unified framework for private feder- ated learning with communication compression","venue":null,"work_id":"d1587dc4-39ed-4e86-9878-3411d7ce27b2","year":2022},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.639459Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:7a40b7432c110554b551c4b92761d2fd7f4a89793220fabcaa279696e3e184a0","observation_id":"f97c57a8-ab1a-4282-bcb1-841604dd516a","resolution":{"observed_at":"2026-08-15T22:46:56.259572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.241822Z","title":"Can decentral- ized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient de- scent","venue":null,"work_id":"fbad2596-e96a-4fc8-be20-64b6c94d0a91","year":2017},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.643749Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:3f700312848c007443445dda8dcdef3e583e41a328cd25f2a8e18ab258a1cb87","observation_id":"6952e0e7-c4e7-46f3-ae80-66fd2b24200b","resolution":{"observed_at":"2026-08-15T22:46:56.246283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.214820Z","title":"Loss-privacy tradeoff in federated edge learning","venue":null,"work_id":"e4c4aa9d-5a07-4cc1-a180-b6f5af94e9d5","year":2022},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.652199Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:a9ab24832b648e4305b5663061ff62013c6fdf05b64d3d4c282dde34c02594a0","observation_id":"65be5dbb-5523-4d58-910c-25865afaf606","resolution":{"observed_at":"2026-08-15T22:46:56.219295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06963","last_updated":"2018-02-24T00:40:30Z","snapshot_observed_at":"2026-08-14T20:22:22.512463Z","submitted_at":"2017-10-18T23:46:57Z","title":"Learning Differentially Private Recurrent Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06963","snapshot_observed_at":"2026-08-15T22:46:55.656469Z","title":"Learning differen- tially private recurrent language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.656469Z"},"links":{"cited_paper":"/paper/1710.06963","citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:1dc65d32b5d99356963b1d245d22e329fdb05cc94ea82035baa9878fe5a7b5e0","observation_id":"422093e0-9bf0-4f3f-b91b-51c1419bbc09","resolution":{"observed_at":"2026-08-15T22:46:55.656469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.199938Z","title":"R´enyi differential privacy","venue":null,"work_id":"0f8d2f0d-bf86-47c2-9f12-c62e026d4f7f","year":2017},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.661258Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:045715de51d1b51c2b2dda33c9129ffcbe1747b3b5e22f6d925968e5730a36d1","observation_id":"1b48ee46-73b4-4975-b036-47ed647870a0","resolution":{"observed_at":"2026-08-15T22:46:56.204611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.186505Z","title":"Pytorch: Tensors and dy- namic neural networks in python with strong gpu acceler- ation","venue":null,"work_id":"48b35eb1-bfcc-4670-b887-35798372f29a","year":2017},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.665647Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:db2b78d053740050af37bc041d1d243280fbd69afc6da281d9de9f22d8b44d0d","observation_id":"40db45dd-e95a-47ac-a4d9-7006f8db4eda","resolution":{"observed_at":"2026-08-15T22:46:56.190874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.173328Z","title":"Privacy enhanced matrix factor- ization for recommendation with local differential privacy","venue":null,"work_id":"6624c3c0-8a06-4377-aebf-2b1374fa6b4f","year":2018},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.669865Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:ec2a5ef7d20a077f2dc8adf66fbf8c435d3c45cbc9528c0f414b215cd2f722fd","observation_id":"3fddfc44-2382-4bd9-9b4a-4db9beb6d4dd","resolution":{"observed_at":"2026-08-15T22:46:56.177757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.159102Z","title":"D2: Decentralized training over de- centralized data","venue":null,"work_id":"784a65cd-ed7d-422f-a5d2-55e4da073db7","year":2018},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.674031Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:db0900a37f3035fbf526004b1631f73a209333210519ed4b4cbd43380c9d3dff","observation_id":"695f0dea-7154-4f37-acab-f5a9f4a02250","resolution":{"observed_at":"2026-08-15T22:46:56.163457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.146105Z","title":"Tailoring gradient methods for differentially private distributed optimization","venue":null,"work_id":"4dc9e963-8706-4bf4-9489-1d215640cf80","year":2024},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.678240Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:deed8f3054c082bc237e2a53447d628f4f6a27f5b09e89d769424b7b2cc264a4","observation_id":"a563ec68-06e3-41b3-8ed5-f2017104edbb","resolution":{"observed_at":"2026-08-15T22:46:56.150409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.120654Z","title":"Efficient privacy- preserving stochastic nonconvex optimization","venue":null,"work_id":"838dc790-16ae-4ea7-a993-420b14b70e73","year":1910},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.687222Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:85e9bf0ecf2c79913cb657f91966e42e7112c19d28ac216ff3a792249ac8c749","observation_id":"237a9d1b-1464-47cf-86d9-405853ce5549","resolution":{"observed_at":"2026-08-15T22:46:56.124808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.108094Z","title":"Beyond inferring class representatives: User-level privacy leakage from federated learning","venue":null,"work_id":"9fb0638e-7179-4b5b-af41-54132f558c67","year":2019},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.691416Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:50079fd867e3e03ef12c79bc0835fb5e822bcd74a30ef9c394289534bcda523c","observation_id":"da07162a-4ead-4b57-a0e2-fc440e611e01","resolution":{"observed_at":"2026-08-15T22:46:56.112267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.095032Z","title":"On differentially private stochas- tic convex optimization with heavy-tailed data","venue":null,"work_id":"c7499a33-78b7-412a-9759-154edc5eabab","year":2020},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.695844Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:f8ceffa485e6bc9ef5cee2076ff788fb97202da22d7ba4a380592ef2311c514d","observation_id":"1e405470-5c57-4972-a911-054b61bb11db","resolution":{"observed_at":"2026-08-15T22:46:56.099494Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.082309Z","title":"Gradient leakage attack resilient deep learning","venue":null,"work_id":"ebe17b1c-3043-4d5b-a9c8-569c9b5c6886","year":2021},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.699934Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:1df07f950bb23116b0698a3be92d3df54f55deb42ff21b2a9cc96e53ccef89ec","observation_id":"68bbf258-2cbe-402c-a44e-e25067033d98","resolution":{"observed_at":"2026-08-15T22:46:56.086576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.069261Z","title":"Federated learning with dif- ferential privacy: Algorithms and performance analysis","venue":null,"work_id":"5d6f01c1-9cf9-47cc-ab55-10039e7b7bf7","year":2020},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.703995Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:d94271e38133c4ba87e996c72ec075085abe3db5909da7effab19ee28f87c517","observation_id":"0fbea95c-27de-420b-a96e-952a4fb6284d","resolution":{"observed_at":"2026-08-15T22:46:56.073554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.056150Z","title":"Securing distributed sgd against gradient leakage threats","venue":null,"work_id":"7cfa839f-d627-4df2-a866-3d9305900558","year":2023},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.708109Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:8bd451ffa8080cd089a790782c6faba0b0433e05494ec4ea0ba8281eb533c38b","observation_id":"0fed96c7-7803-4a27-80ef-ab0fc52d6e39","resolution":{"observed_at":"2026-08-15T22:46:56.060225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-08-13T15:13:33.081929Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-15T22:46:55.716259Z","title":"Fashion-mnist: a novel image dataset for bench- marking machine learning algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.716259Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:64fdc76d110a409bab74338cf916b184a93510cec27c4fba09767d8c1bc22cbf","observation_id":"f91fb697-bf5c-4276-96f4-7455e33ee800","resolution":{"observed_at":"2026-08-15T22:46:55.716259Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.028347Z","title":"A(DP)ˆ2SGD: Asynchronous decentralized parallel stochastic gradient descent with differential privacy","venue":null,"work_id":"5dbe1247-2017-4c77-8a42-52b0960a6da8","year":2022},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.720349Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:81d6845a8add4b95e557c078eeb588b3c6ce5f0a35e981777f7c94c6af57bd3f","observation_id":"20b0ac10-6941-459a-b8f8-7a83fb691eb9","resolution":{"observed_at":"2026-08-15T22:46:56.032879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.014743Z","title":"Decentralized parallel sgd with privacy preserva- tion in vehicular networks","venue":null,"work_id":"d5b0314a-2e07-45b9-b582-0e8ba7598795","year":2021},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.724381Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:4db7df36e2f0aae55b4bd498a683e741a76f77c666e65993a58af45bdb929e63","observation_id":"1470db64-ae4a-4d06-9f69-1d6abcec37ea","resolution":{"observed_at":"2026-08-15T22:46:56.019019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.001576Z","title":"Differentially private federated tempo- ral difference learning","venue":null,"work_id":"d81392c8-b930-4bff-84df-50f4150345a2","year":2021},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.728756Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:47ebbdc9bb5a024f2c0290a7537c089775a4639f21020d9008dfb9d830c6dd5f","observation_id":"7842d44d-ef31-4b56-9652-7e7d646be487","resolution":{"observed_at":"2026-08-15T22:46:56.005808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:55.987885Z","title":"Efficient private erm for smooth objec- tives","venue":null,"work_id":"1c90f74a-338c-4ed7-823d-e7264c170e0a","year":2017},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.732862Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:3a76200637b90c5a9cfdf65260857637cbb5ee45715a54ea871f75868c9779d4","observation_id":"d2f4dabf-c4ab-428d-aaac-7e8cc540af93","resolution":{"observed_at":"2026-08-15T22:46:55.992487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:55.973309Z","title":"Optimizing the numbers of queries and replies in convex federated learn- ing with differential privacy","venue":null,"work_id":"c092e9b6-d88e-47d5-84c1-889d09e80d86","year":2023},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.736818Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:adf111acc80e37e0d1eee49f09ebe1103e36fd9eb03c41a2e05b2787fa8f6f94","observation_id":"d1d3c045-99e6-4ec1-9cec-f3f6eac8b485","resolution":{"observed_at":"2026-08-15T22:46:55.978293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:55.958459Z","title":"Deep leakage from gradients","venue":null,"work_id":"49b48d59-5ca8-4b12-8993-114362044960","year":2019},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.740982Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:c148f49278ad9246d0e62a52695e3908ddb35e72148b94a103df5476f42be7e7","observation_id":"c1311217-54f4-4eb3-a49b-9308e1e22fef","resolution":{"observed_at":"2026-08-15T22:46:55.962977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:55.944350Z","title":"R-FAST: Robust fully-asynchronous stochastic gradient tracking over general topology","venue":null,"work_id":"db175171-bb49-468b-ba20-650429e39c40","year":2024},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.745068Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:149a8e1d6908c2f08a5ad0a89f612007fcc239afd74cd82c0758b875a7445f78","observation_id":"aa691865-ac74-4ac0-989a-e90ba7d36ebb","resolution":{"observed_at":"2026-08-15T22:46:55.948948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:55.930554Z","title":"Parallelized stochastic gra- dient descent","venue":null,"work_id":"14ae5045-f568-4b02-82c4-ef0afd1c2ade","year":2010},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.749409Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:2967ff9257a882e53aab7f446c8eb6ba50364d984e81df5d4e515c4f07f7e219","observation_id":"8f287718-6e90-4157-b9c2-edd0d12803d9","resolution":{"observed_at":"2026-08-15T22:46:55.935032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:55.915934Z","title":"Then, we have kX l=0 λk−lvl !2 ⩽ 1 1−λ kX l=0 λk−l vl 2","venue":null,"work_id":"28c1b119-db7f-4b5f-8ef9-3b9b1f96c3d5","year":2019},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.753705Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:53c7c90c447857225b8a90ee4236be329f6d1a79fdcda40571dabbc4daadbc63","observation_id":"91ddb3e0-2666-43ad-8488-d38f5c1da2b4","resolution":{"observed_at":"2026-08-15T22:46:55.920789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:55.901041Z","title":null,"venue":null,"work_id":"e4016443-0e7d-4ce8-b6d5-36720ae27fdc","year":2019},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.757872Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:2431c66da55c5dd907ca1f2fd2534c14b741bc17afb121c979b381efd3b15a6e","observation_id":"af01cc66-8ea5-42c1-8efa-e8395830de46","resolution":{"observed_at":"2026-08-15T22:46:55.905958Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.308582Z","title":"Decentralized deep learning with arbitrary communication compression","venue":null,"work_id":"f52d9dc8-f0c8-4d6e-b307-9338f5f6cad4","year":2019},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2003,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.612693Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:be7e6fc81e28bddbe6689c688e5fc62863da3e8e09810e0c6c7a618f811e8f87","observation_id":"c5cc06f1-128e-46f8-af13-d696ee72c312","resolution":{"observed_at":"2026-08-15T22:46:56.313145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.385192Z","title":"The algorithmic foundations of differential privacy","venue":null,"work_id":"fb5e3217-b77b-48e9-95ae-d59a20afd883","year":2014},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2006,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.586749Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:afb7a88ff1178fbb53ec3ae47574270317dc149e8be3162c672f9ef6fdec5ace","observation_id":"afdbf54d-a687-4f43-8f73-eee5a4d0cbf9","resolution":{"observed_at":"2026-08-15T22:46:56.389784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.281376Z","title":"Distributed training of deep learn- ing models: A taxonomic perspective","venue":null,"work_id":"07960343-dc99-46bd-950b-4d6886d29ed3","year":2020},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.621321Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:2ae99c1973052e49abee9a8256c0f448dfb29df56a5731361f4dc34038320294","observation_id":"90d55907-b258-4c9f-bd09-8a8cbd27ae44","resolution":{"observed_at":"2026-08-15T22:46:56.285571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.370702Z","title":"Adap DP- FL: Differentially private federated learning with adaptive noise","venue":null,"work_id":"187057df-d43f-4ae4-8972-23bfe726290d","year":2022},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.591557Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:304e998f17883bfe74375d545f7306a03f464547b1f0eda8aabe28f8b394bce5","observation_id":"5a6a2ad2-5414-4491-9a2e-4888de56ff9a","resolution":{"observed_at":"2026-08-15T22:46:56.375400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:55.600183Z","title":"Deep residual learning for image recog- nition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.600183Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:9979d087c91a715356531c14f21fd10b8a4004e6b4ca62ab099fa4ca5ada81d2","observation_id":"7c6e69a7-0ee2-4e3e-8b64-eeb5b5aeeac9","resolution":{"observed_at":"2026-08-15T22:46:55.600183Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.469399Z","title":"Differentially pri- vate learning with adaptive clipping","venue":null,"work_id":"cf2a3e81-a111-42ee-8a7f-5e0e367416d1","year":2021},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.544404Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:0a9efda893033e74f5148943e322d9592eac1851b30d3422ad695aa334c07915","observation_id":"aaba3338-3e5d-4766-ba06-af7d3c65944a","resolution":{"observed_at":"2026-08-15T22:46:56.473572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.228246Z","title":"Asynchronous decentralized parallel stochastic gra- dient descent","venue":null,"work_id":"d4f61574-80bc-46e9-87ba-b94555dbfa46","year":2018},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.648039Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:f8af06ff2f54a44aeb4bd4887d75018ee472d93c2111fa67314e5d85f87a51c7","observation_id":"1e5cc428-7680-42e6-a2db-f625b3e6be41","resolution":{"observed_at":"2026-08-15T22:46:56.232616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.426988Z","title":"Towards decentralized deep learning with differen- tial privacy","venue":null,"work_id":"38444d55-c664-4364-8738-23931d1cad1a","year":2019},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.568624Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:b24274714885599b5dd9851123046d3fafdd389f0b09f14726ea200ad4317fea","observation_id":"7fe1ca3f-397b-4d20-9828-082e99e88182","resolution":{"observed_at":"2026-08-15T22:46:56.432045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.11607","last_updated":"2020-07-22T16:09:13Z","snapshot_observed_at":"2026-08-11T01:49:45.976527Z","submitted_at":"2019-11-26T15:08:58Z","title":"Deep Learning with Gaussian Differential Privacy","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.11607","snapshot_observed_at":"2026-08-15T22:46:55.554181Z","title":"Deep learning with gaussian differential privacy","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.554181Z"},"links":{"cited_paper":"/paper/1911.11607","citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:27f98c5ecd540f09f0e2ee486b08bd7fdad2d7383c90b292670f4ae2ca8b7f0d","observation_id":"b173630c-3a7e-414f-8fc2-c0eab08ae30c","resolution":{"observed_at":"2026-08-15T22:46:55.554181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.441947Z","title":"Understanding gradient clipping in private sgd: A geometric perspective","venue":null,"work_id":"87c3f247-bd08-41ee-8551-f8df4cd1174a","year":2020},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.558905Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:4babadf308584da5a33b4804ff313e95b97d4da759cd8f63554bb2d12886ffd8","observation_id":"211d1d9b-edeb-4a69-83d2-98346724125c","resolution":{"observed_at":"2026-08-15T22:46:56.446403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.455800Z","title":"Stochastic gradient push for distributed deep learning","venue":null,"work_id":"2826482f-0d5e-4026-b6f1-e5b101733ba9","year":2019},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.548827Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:7c48c565a05e8b69f560aa07ff000175e56f8aa143dd09c644b1da22b2901011","observation_id":"6f7a4800-51ec-4e53-bfe0-d2e3e5f15dfe","resolution":{"observed_at":"2026-08-15T22:46:56.460264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.357086Z","title":"Escaping from saddle points—online stochastic gra- dient for tensor decomposition","venue":null,"work_id":"44a2103c-b4ec-4e42-b3f6-e4804c90d7ec","year":2015},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.595824Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:816087adc1aaed2bf535510746686a824fce1d8df5c8307527af0a375d879e98","observation_id":"dd035b4e-af3b-4c0c-b540-1931cdbbc83d","resolution":{"observed_at":"2026-08-15T22:46:56.361642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.042466Z","title":"The value of collaboration in convex machine learning with differential privacy","venue":null,"work_id":"698d2aca-5ab8-4edb-8eb0-bc9c4dc34876","year":2020},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.712153Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:9ef3d4c0e504e41501e4249e3a4853aa3655ba6f5cf59a4e39f4fc7e643c6542","observation_id":"2208ca7c-6f21-4f94-8777-bc19c69fe3b7","resolution":{"observed_at":"2026-08-15T22:46:56.047058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:46:56.133591Z","title":"Differentially private empirical risk minimization revis- ited: Faster and more general","venue":null,"work_id":"65cefeac-e21c-4b95-8ce4-94c0d09fd08c","year":2017},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.683007Z"},"links":{"citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:8e2f110198d639c73a6ae47bf3158f52ea33ed34a2467c8bada023564c93597b","observation_id":"cbebcc14-d4ba-4555-a5dd-65bac401e516","resolution":{"observed_at":"2026-08-15T22:46:56.137676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.05830","last_updated":"2020-02-21T17:08:10Z","snapshot_observed_at":"2026-07-06T08:21:19.915142Z","submitted_at":"2019-09-12T17:37:08Z","title":"Differentially Private Meta-Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.05830","snapshot_observed_at":"2026-08-15T22:46:55.629970Z","title":"Differentially private meta- learning","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T22:46:55.629970Z"},"links":{"cited_paper":"/paper/1909.05830","citing_paper":"/paper/2505.06651"},"observation_digest":"sha256:0966a1be940a5f134f8940f97a2422a81c98c2402d37a98b81bb3c6649ef6990","observation_id":"7f02f943-1e0b-4e99-a836-f5401a0dfdd4","resolution":{"observed_at":"2026-08-15T22:46:55.629970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.06651","last_updated":"2025-05-10T13:57:57Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T22:34:39.041126Z","submitted_at":"2025-05-10T13:57:57Z","title":"Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":2,"verified_fuzzy":42},"total_outbound_references":51},"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 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2505.06651."}