{"as_of":"2026-08-16T08:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:506ebae4e47e22c17f525780dae222c25b42cb9f1ccb0d57abc57086f6a939c2","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T19:29:47.951014Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"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/2608.09328/citation-record","integrity":"/paper/2608.09328/integrity","json":"/paper/2608.09328/citation-record.json","paper":"/paper/2608.09328"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:29:48.219932Z","title":"Advances and open problems in federated learning,","venue":null,"work_id":"eccf31e0-7387-4bc8-9792-06a9022eca8b","year":2021},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.886553Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:b7e4ae6548033eb44562701c076bf69d9ed8294550b9fdb982ff6c57ecc358ed","observation_id":"1d1329e3-621a-49a1-9c9a-101de6cb8438","resolution":{"observed_at":"2026-08-11T19:29:48.223569Z","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":"2026-08-11T19:29:48.210104Z","title":"Pri vacy- preserving aggregation in federated learning: A survey,","venue":null,"work_id":"07f8e6cd-915b-466b-b06e-98a380389485","year":2022},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.890696Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:cfc9556c0d4606c36e7571ed4f1807072be5b6a8ef81d15a1bacb318c06169da","observation_id":"b8388b5a-735b-4c54-81bd-8663100b9abf","resolution":{"observed_at":"2026-08-11T19:29:48.213210Z","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":"2026-08-11T19:29:48.200588Z","title":"Practical secure aggregation for privacy-preserving machine learning,","venue":null,"work_id":"70335d16-4143-4f4a-879e-f9c343f103aa","year":2017},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.893664Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:afa9a85eacea18b3ce650427862460e872ad909df6d70a54ade496d9952afa4e","observation_id":"d944b24f-0e8a-44bd-b722-956b3aaaf54e","resolution":{"observed_at":"2026-08-11T19:29:48.203835Z","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":"2009.11248","last_updated":"2020-09-23T16:49:02Z","snapshot_observed_at":"2026-08-16T06:39:41.604269Z","submitted_at":"2020-09-23T16:49:02Z","title":"FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.11248","snapshot_observed_at":"2026-08-11T19:29:47.896570Z","title":"Fast- secagg: Scalable secure aggregation for privacy-preservi ng federated learning,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.896570Z"},"links":{"cited_paper":"/paper/2009.11248","citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:9a6fcfa4e25cafe6d122aff8cb86139558bc8231ec039ade025f6550d4310965","observation_id":"a57b46e5-380e-4b43-a69b-f03471af9108","resolution":{"observed_at":"2026-08-11T19:29:47.896570Z","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":"2026-08-11T19:29:47.900050Z","title":"Deep learning with differential pr ivacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.900050Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:c9b83661dd19dddb66fd247b7aa15a9235d513f5129122c05d2a5a3f01556bc6","observation_id":"13c7b41c-b6cb-423f-8ddb-8e050a78373c","resolution":{"observed_at":"2026-08-11T19:29:47.900050Z","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":"2026-08-11T19:29:48.182654Z","title":"Ap prox- imating functions with approximate privacy for applicatio ns in signal estimation and learning,","venue":null,"work_id":"1d3e5d7f-695d-4036-b88d-6725b55181ba","year":2023},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.902946Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:538e151d328c94e83bb25ed1b718b21f6a79be8a0cadda98cab6bf7a1c0f67f0","observation_id":"b1f8bd65-b2c2-43b1-b0d1-20363a793148","resolution":{"observed_at":"2026-08-11T19:29:48.185987Z","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":"2026-08-11T19:29:48.172148Z","title":"Privfl: Practical privacy-preser ving federated regressions on high-dimensional data over mobile networks ,","venue":null,"work_id":"430bea9d-fedb-4a75-b21f-756e533aff46","year":2019},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.906064Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:149b9bfc0ac21cdb97d86f11dff2dba8bfc2302b47c0c59864ceb6d2a978c092","observation_id":"16a8ad8d-9cc5-4b98-a951-eb3ba2be3e58","resolution":{"observed_at":"2026-08-11T19:29:48.175484Z","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":"2002.09843","last_updated":"2021-08-15T16:48:08Z","snapshot_observed_at":"2026-08-13T19:42:13.601026Z","submitted_at":"2020-02-23T06:50:20Z","title":"An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning","version":5},"cited_work":{"arxiv_id":"2002.09843","doi":null,"metadata_source":"pith","pith_arxiv_id":"2002.09843","snapshot_observed_at":"2026-08-11T19:29:48.003109Z","title":"An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning","venue":"cs.LG","work_id":"2f5d3176-ea73-43a7-9a92-1a040d1570f2","year":2020},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.908705Z"},"links":{"cited_paper":"/paper/2002.09843","citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:02398c504af343fc7985da8a4cabbe72d96477878b98e57617eeefdf166879cb","observation_id":"993c310c-8e35-4fff-a1ee-9bad4e782b3e","resolution":{"observed_at":"2026-08-11T19:29:48.007793Z","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":"2504.02114","last_updated":"2025-04-02T20:20:13Z","snapshot_observed_at":"2026-08-07T16:13:32.119696Z","submitted_at":"2025-04-02T20:20:13Z","title":"On Model Protection in Federated Learning against Eavesdropping Attacks","version":1},"cited_work":{"arxiv_id":"2504.02114","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.02114","snapshot_observed_at":"2026-08-11T19:29:47.982076Z","title":"On Model Protection in Federated Learning against Eavesdropping Attacks","venue":"cs.CR","work_id":"99b11a51-9723-4b1b-8285-0bc456ff4e41","year":2025},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.911886Z"},"links":{"cited_paper":"/paper/2504.02114","citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:4d3ab785ee7067ed1b8fef0cfe6004e9e65e21ef9bd1e36bc78cd1575fa9527c","observation_id":"456829d1-b446-4b04-bbc1-57aa3785848a","resolution":{"observed_at":"2026-08-11T19:29:47.988201Z","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":"2026-08-11T19:29:48.162558Z","title":"Channel state information-free loc ation-privacy enhancement: Fake path injection,","venue":null,"work_id":"ee008d55-1c8b-4745-8a88-5f591515bbac","year":2024},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.915181Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:741630f5c8f11687a9c54accad17b304962f25fef416718afb1da6c8dd956aba","observation_id":"b915efcf-1dd1-4d77-aa2e-5cb13e1e19e6","resolution":{"observed_at":"2026-08-11T19:29:48.165770Z","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":"2026-08-11T19:29:48.150829Z","title":"Channel state information-free location-privac y enhancement: Delay-angle information spoofing,","venue":null,"work_id":"defc3550-7ba1-4cd8-9831-1a0df09eb5b3","year":2024},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.917753Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:47e98b19bf7f56ffa7890d92379ce860642dc20df977c5da2ad774f4f8776d90","observation_id":"111e4847-a908-4dfc-844c-0b9e0b6ce6c2","resolution":{"observed_at":"2026-08-11T19:29:48.155053Z","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":"2026-08-11T19:29:48.138656Z","title":"Optimized parameter design for channel state info rmation-free location spoofing,","venue":null,"work_id":"bf33157c-c5da-41a4-84f2-3eb72104af04","year":2024},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.920267Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:a4fb070e6b2b2fd0ea9ffb90c60a2a967b39b94bac5abc9c184b943023f173e6","observation_id":"76383f90-8225-46b9-af27-4d659e5872d9","resolution":{"observed_at":"2026-08-11T19:29:48.142914Z","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":"2026-08-11T19:29:48.125171Z","title":"Modshift: Model privacy via designed shifts,","venue":null,"work_id":"89dc124d-d6ee-4a38-9cc4-7eb147c5ab2a","year":2025},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.922903Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:60cce2b691562846404e36866585462bc706351394029d255dc78daec1e02134","observation_id":"d7b69a9a-1caf-4882-a776-71b80e7bbde4","resolution":{"observed_at":"2026-08-11T19:29:48.129239Z","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":"2026-08-11T19:29:48.112070Z","title":"Scaffold: Stochastic controlled averaging for fe derated learn- ing,","venue":null,"work_id":"2fef2161-1af5-43fa-bad7-366a80ded62f","year":2020},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.925321Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:71f41352aa9e8194f98b9b6e022e1792094f47812f38ebafeefc0c71ac4c6d8b","observation_id":"560cd13a-4131-45d2-b5df-81245bab0482","resolution":{"observed_at":"2026-08-11T19:29:48.116303Z","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":"2026-08-11T19:29:48.099004Z","title":"Feddc: F ederated learning with non-iid data via local drift decoupling and co rrection,","venue":null,"work_id":"5fe3d785-aa6b-46a7-b3c7-099c92218f1a","year":2022},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.927755Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:982817820b48bcee449edcc352e856d01f2a9aeab3e3f69d661e9834a4c2e2ac","observation_id":"d0c47881-dc44-4705-a4c5-3b5703bd2791","resolution":{"observed_at":"2026-08-11T19:29:48.103124Z","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":"2026-08-11T19:29:48.085247Z","title":"Block mo dshift: Model privacy via dynamic designed shifts,","venue":null,"work_id":"d81b85b9-40b4-4634-b57b-6f0d2a18bee6","year":2026},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.930232Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:4b823d11dcea29384d3b71014e26d325a13e3a517427c874c352481bacbb1de7","observation_id":"d1cdd4b7-0fe7-474c-a439-b0daaf1474b7","resolution":{"observed_at":"2026-08-11T19:29:48.089179Z","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":"2026-08-11T19:29:47.932714Z","title":"Communication-efficient learning of deep networks from de centralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.932714Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:beb39c625590e99dcc1fc3c9d6867667f7dd1291f783ac9b72b1914333182b5f","observation_id":"0042fe49-ed14-4d44-a914-052c2cdf82e0","resolution":{"observed_at":"2026-08-11T19:29:47.932714Z","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":"2026-08-11T19:29:48.069823Z","title":"Maximal dissent: a state-dependent way to agree in distributed convex optimi zation,","venue":null,"work_id":"db734923-d626-48e0-81d3-bc72418488c0","year":2023},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.935883Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:bf9fb3eb387ea0a6c2a57962ebcb413ceeef030bfd14dbdcebfc2030a677b7b8","observation_id":"ad6ac38a-1980-4780-a5ad-4918265240f0","resolution":{"observed_at":"2026-08-11T19:29:48.072767Z","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":"2026-08-11T19:29:47.939141Z","title":"Goldsmith, Wireless communications","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.939141Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:6be9f98495eb0f5540fe1886e9c636a9003ec7a1ebdbf6a68da3dea9f5e96786","observation_id":"c3a8085a-038e-495d-9746-806e08b9ce34","resolution":{"observed_at":"2026-08-11T19:29:47.939141Z","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":"2026-08-11T19:29:48.053925Z","title":"Guaranteed private c ommunication with secret block structure,","venue":null,"work_id":"81e7acc9-170f-4685-9c23-f1e8e27dd668","year":2024},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.943029Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:30c26eb2c3d054f2f8568d42806b58f91884f68d5c5e028cd503894303b5562e","observation_id":"ffc608ad-154a-4e72-b10a-452d41acab55","resolution":{"observed_at":"2026-08-11T19:29:48.057030Z","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":"2026-08-11T19:29:48.042753Z","title":"Block modshift: Model priva cy via dynamic designed shifts,","venue":null,"work_id":"e725f3ca-748f-4835-80c8-c29c19715177","year":2025},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.947281Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:f912cf7c7b1ac3f116b8a39f40b5f33ed6c5c217b17f5946023d9a6fb36a06b7","observation_id":"be737e01-be24-449d-8dfd-b082258a1d7a","resolution":{"observed_at":"2026-08-11T19:29:48.046382Z","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":"2026-08-11T19:29:48.030945Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":"965b854b-ca9e-464e-b584-f55d5dec0e14","year":2002},"citing_paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T19:29:47.951014Z"},"links":{"citing_paper":"/paper/2608.09328"},"observation_digest":"sha256:5ccb73dc6334ffd31e70663af9f2059c75a2fdf8aa2db469c3661c478fa9e900","observation_id":"7d8e4347-b830-4185-b03a-f20eec44bd59","resolution":{"observed_at":"2026-08-11T19:29:48.034602Z","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"}}],"paper":{"arxiv_id":"2608.09328","last_updated":"2026-08-10T09:08:48Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T03:36:22.377573Z","submitted_at":"2026-08-10T09:08:48Z","title":"MaxModShift: Model Privacy via Designed Shifts"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":2,"verified_fuzzy":16},"total_outbound_references":22},"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 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2608.09328."}