{"as_of":"2026-08-16T05:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bf98ffc8950a31add810584faad4d24594a2e3882a2aa254571b8df78da2cc71","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":"2026-08-14T14:36:35.797559Z","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":"2026-08-15T06:32:42.880941+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/1908.02997/citation-record","integrity":"/paper/1908.02997/integrity","json":"/paper/1908.02997/citation-record.json","paper":"/paper/1908.02997"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:36:35.541553Z","title":"Deep learning with differential privacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.541553Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:e0cc1509871dd4a8bbc813d720f9091a3e94b04fbaf099fa99c4b2e1da31e967","observation_id":"e2ee45af-36be-46a8-812e-ff0362d10639","resolution":{"observed_at":"2026-08-14T14:36:35.541553Z","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":"2026-08-14T14:36:36.774662Z","title":"Membership inference attacks against machine learning models,","venue":null,"work_id":"8d68e768-5026-441c-8fde-4d6246cbefab","year":2017},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.548144Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:df863358e8a1869bbaca88bd8f2e40f05f62c8b51e75136bd52c2ccbd9c42813","observation_id":"b0744473-4661-4041-b006-d961dcfa6ef6","resolution":{"observed_at":"2026-08-14T14:36:36.779642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:35.553392Z","title":"Tensorflow: a system for large- scale machine learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.553392Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:3df971766a765baf90e718e34842c65a4856a186757ec1bbff5f1166f962b3db","observation_id":"ad15fb4e-fdb7-4d2e-824d-93b6d1b19e83","resolution":{"observed_at":"2026-08-14T14:36:35.553392Z","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":"2026-08-14T14:36:35.559821Z","title":"Distributed graphlab: a framework for machine learning and data mining in the cloud,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.559821Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:516476d2ce2025f0616a4eb88fd73fc40ff84d2963eb2e5a9788920c271fffc6","observation_id":"662584df-7bde-4d6e-8042-25f0f93ef6b9","resolution":{"observed_at":"2026-08-14T14:36:35.559821Z","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":"2026-08-14T14:36:36.613109Z","title":"Machine learning models that remember too much,","venue":null,"work_id":"2b264866-2358-454e-8ef9-ffaeacdbcd91","year":2017},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.564731Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:fda328059da0d00e8bb5703961275a4bca50030afe5d3bf4a83fcb29ce2fd3cf","observation_id":"8472b1fe-daff-4b03-8f95-dae7eefd3b1b","resolution":{"observed_at":"2026-08-14T14:36:36.618144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.594103Z","title":"Model inversion attacks that exploit confidence information and basic countermeasures,","venue":null,"work_id":"1a254045-7bbd-4361-ae88-40a16e5bd944","year":2015},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.570019Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:1cd80330afb4b6441ab70881673f27bf0dfdf429a21ccd46b8c3665e887018c8","observation_id":"497b5006-aeb5-46d2-a75a-392d7dffcadc","resolution":{"observed_at":"2026-08-14T14:36:36.599034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.576791Z","title":"The algorithmic foundations of differential privacy,","venue":null,"work_id":"bbe6d8c2-2f2f-487b-a964-547c02509bca","year":2014},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.575818Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:bebd61177a5c1dff4b725d2312d69ce91c3c49f6886605306939b63932b58f98","observation_id":"70613b5e-630f-4efe-930d-ef6eb88a1a6b","resolution":{"observed_at":"2026-08-14T14:36:36.582696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.560088Z","title":"Privacy-preserving deep learning,","venue":null,"work_id":"0e5556c0-508e-4e0f-8aaf-40feee649cfb","year":2015},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.580718Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:2c73e8de50dafccd90a20e14c1b448391c66572255be9b3cfcb022d63c1f5b06","observation_id":"61f23fc8-266f-4b0b-99c6-fcb28345dfc2","resolution":{"observed_at":"2026-08-14T14:36:36.565969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.542993Z","title":"Output perturbation with query relaxation,","venue":null,"work_id":"728a7d18-0474-4659-b62e-24eba6e47dc5","year":2008},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.585862Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:24b8675a213813b39f5295f248a44671d886c609c57c4c48aafc01a52de440b0","observation_id":"a21e6670-d272-4e28-88b1-7352106fdd41","resolution":{"observed_at":"2026-08-14T14:36:36.548562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.524882Z","title":"Extremal mechanisms for local differential privacy,","venue":null,"work_id":"503f5bf0-3a62-473b-a57c-6e19330f1ca9","year":2014},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.590695Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:101fc3bd7373fa7d895d878e139d986170c0716a5b41f9f64f5f07429b7a8a4e","observation_id":"30c4759e-b62c-40cc-8911-7795e13153a9","resolution":{"observed_at":"2026-08-14T14:36:36.530407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.507662Z","title":null,"venue":null,"work_id":"e0e2ebaa-5aec-4d71-aa03-f292c611576f","year":2015},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.595613Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:ff7da555780775e5c9dadad1f4a3f8546dd061882d327d0d2ec740deea683563","observation_id":"22d83b17-ba35-4afa-bec8-82c3466b84d8","resolution":{"observed_at":"2026-08-14T14:36:36.512950Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.491879Z","title":"An efficient and scalable privacy preserving algorithm for big data and data streams,","venue":null,"work_id":"1328bcb5-a3e9-4992-8ac3-a97dfe7e269a","year":2019},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.601002Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:1f153e2d2bf167c5a297c204b3650deb3bbd29e14df031b983dc5b138cee1ec5","observation_id":"2e3e0e20-5489-4948-b719-8a7d4dbea548","resolution":{"observed_at":"2026-08-14T14:36:36.496924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.476409Z","title":"Differentially private continual monitoring of heavy hitters from distributed streams,","venue":null,"work_id":"c53b7353-12b4-4ecc-9a94-139ef7bcb4a1","year":2012},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.606074Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:055ddc6e1a947175c7a92ac3223a52d86ecb2b49a5db720dc1fb35617c1ffbd5","observation_id":"f96aada3-a78b-4a51-b1d8-6209c3be15c9","resolution":{"observed_at":"2026-08-14T14:36:36.481841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.460334Z","title":"Rappor: Randomized aggre- gatable privacy-preserving ordinal response,","venue":null,"work_id":"ad312930-fd56-47fd-8c72-857a41199ba4","year":2014},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.610717Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:492f5b6033fdf86216fb4b499c9073f1dd8af970197c07ac56acda43171c89e2","observation_id":"12b510c9-a6fe-4f31-9641-d5dc71c4a279","resolution":{"observed_at":"2026-08-14T14:36:36.465818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:35.615507Z","title":"Randomized response: A survey technique for eliminating evasive answer bias,","venue":null,"work_id":null,"year":1965},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.615507Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:b5eab0f77b3cf93ba856d3ce7c2e2590e1b96bd5d196892c95d28bd4f8f5679f","observation_id":"e363f7ad-7d3f-470d-bc7e-51ed06b26e7d","resolution":{"observed_at":"2026-08-14T14:36:35.615507Z","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":"2026-08-14T14:36:36.424289Z","title":"Using randomized response for differential privacy preserving data collection","venue":null,"work_id":"e3fae50b-09c1-40ca-8050-06d3e3f2830f","year":2016},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.620614Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:34687fcfe17be1bfba1378983bba7487ba72adce05d776dd8d97fdd18bb6481d","observation_id":"b74c0f5d-3bb0-491e-bd5c-32496990db5e","resolution":{"observed_at":"2026-08-14T14:36:36.429825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.407798Z","title":"Heavy hitter estimation over set-valued data with local differential privacy,","venue":null,"work_id":"fd790a66-09de-460b-ac59-3908157597e8","year":2016},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.625306Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:2037f567ccd31e53145694dc0c45d3bee6fc5005340d9ce3637fb48886276dc9","observation_id":"e931c4d9-36ec-4e2b-a851-ab309ba77667","resolution":{"observed_at":"2026-08-14T14:36:36.412869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.392364Z","title":"Concentrated differential privacy: Simplifi- cations, extensions, and lower bounds,","venue":null,"work_id":"d74122a5-92b6-4c54-b8bc-7e06c8d293dd","year":2016},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.630343Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:264bad01b018f9da2d45aeee414d18555f7cc3f9c551d1b8b1b47cde2729ab57","observation_id":"0f83a9f1-bc6e-488e-a628-a296b00c3ec3","resolution":{"observed_at":"2026-08-14T14:36:36.397279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.00823","last_updated":"2018-10-16T21:31:23Z","snapshot_observed_at":"2026-08-14T19:58:28.326944Z","submitted_at":"2018-01-02T20:24:24Z","title":"MVG Mechanism: Differential Privacy under Matrix-Valued Query","version":3},"cited_work":{"arxiv_id":"1801.00823","doi":null,"metadata_source":"pith","pith_arxiv_id":"1801.00823","snapshot_observed_at":"2026-08-14T14:36:35.911359Z","title":"MVG Mechanism: Differential Privacy under Matrix-Valued Query","venue":"cs.CR","work_id":"9514f0e2-8050-485c-b8e0-dfdab5e8c8fc","year":2018},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.634819Z"},"links":{"cited_paper":"/paper/1801.00823","citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:9615ec3855522c2301fbc10c27acd33305c3f9a2386ef26c6cd9ee88adafd2b7","observation_id":"da092dc1-46cf-478e-bcd3-b01be99909b2","resolution":{"observed_at":"2026-08-14T14:36:35.916718Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:35.640062Z","title":"Deep learning in neural networks: An overview,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.640062Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:8c8683fa120ea122c4e901d85d3cc88d2e73c0835129c6b3f75a85ed426950cc","observation_id":"0e011220-f31d-487b-b6f1-bdd95c33b8b2","resolution":{"observed_at":"2026-08-14T14:36:35.640062Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1408.5882","last_updated":"2014-09-03T03:09:02Z","snapshot_observed_at":"2026-08-14T23:21:58.977221Z","submitted_at":"2014-08-25T19:48:04Z","title":"Convolutional Neural Networks for Sentence Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1408.5882","snapshot_observed_at":"2026-08-14T14:36:35.645853Z","title":"Convolutional neural networks for sentence classification,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.645853Z"},"links":{"cited_paper":"/paper/1408.5882","citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:f31c1ac1c9b1896e8c5829fe8f13866c53f6e61ed2c736f945a05b185f8960b8","observation_id":"b2df6e99-1a37-460b-8e31-53cb2c2ab192","resolution":{"observed_at":"2026-08-14T14:36:35.645853Z","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":"2026-08-14T14:36:35.651152Z","title":"Imagenet classification with deep convolutional neural networks,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.651152Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:b98ec0ebce7f4fc0ac80a8b8299fc0037a8117b8936fe95dfdac9ba79c0de8c9","observation_id":"3078e9f0-b421-46a8-9f07-ce37796bf447","resolution":{"observed_at":"2026-08-14T14:36:35.651152Z","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":"2026-08-14T14:36:36.353375Z","title":"Finding your way in the fog: Towards a comprehensive definition of fog computing,","venue":null,"work_id":"61671dc8-e2ac-46d2-ad70-22d3a3d795a9","year":2014},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.656472Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:6dcadc8a8438aceec2f96d4d204aad871e24b8b6053d0ab047146881d5009825","observation_id":"c7a59605-5cc3-423f-bec1-e13eaa36e622","resolution":{"observed_at":"2026-08-14T14:36:36.358612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.09924","last_updated":"2019-03-24T04:54:41Z","snapshot_observed_at":"2026-08-14T16:57:44.114749Z","submitted_at":"2019-03-24T04:54:41Z","title":"An Energy-driven Network Function Virtualization for Multi-domain Software Defined Networks","version":1},"cited_work":{"arxiv_id":"1903.09924","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.09924","snapshot_observed_at":"2026-08-14T14:36:35.871709Z","title":"An Energy-driven Network Function Virtualization for Multi-domain Software Defined Networks","venue":"cs.NI","work_id":"f100d66e-9953-446d-9b9a-710ec8a89541","year":2019},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.661102Z"},"links":{"cited_paper":"/paper/1903.09924","citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:bd331cc0b335b7d6cce1196bbe696c6ae56a6dad00d862f2aeadf619ef4e3918","observation_id":"47fad5d2-925f-43d7-a860-fa48a68af92e","resolution":{"observed_at":"2026-08-14T14:36:35.878992Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.337526Z","title":"Keras: Deep learning library for theano and tensor- flow,","venue":null,"work_id":"c318972e-4ea8-448c-a5fe-33c326c377ef","year":2015},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.666513Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:510fabff6ca8de6fd9266fadb9946f3a2169b39f8d611deee152cdd955840636","observation_id":"9f03a973-6e80-45be-87c4-cc1d7ce57dba","resolution":{"observed_at":"2026-08-14T14:36:36.342452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.321279Z","title":"Locally differentially private pro- tocols for frequency estimation,","venue":null,"work_id":"6079f0bd-6cb2-46b1-9441-4380d95f36be","year":2017},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.671181Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:ddda50f4686d03598df5ba150167935cc9345248dda0dd347dbbb4bd4efae602","observation_id":"83c07524-0310-438c-a7e4-29f54fa1eb34","resolution":{"observed_at":"2026-08-14T14:36:36.327134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:35.676439Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.676439Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:2d617e2ce3928747ecb941bb76d7b9fb34c2b5333b73d2537436e8238f4fcba0","observation_id":"3d6944e0-fcff-4595-ba96-3417814a7e6d","resolution":{"observed_at":"2026-08-14T14:36:35.676439Z","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":"2026-08-14T14:36:36.291986Z","title":"An efficient and fine-grained big data access control scheme with privacy-preserving policy,","venue":null,"work_id":"3cb4bbc3-dd41-47ad-92b2-11b939053876","year":2017},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.681591Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:b3e01501c6c0e8783bccf758e80674e577002ba07b778149f9d19f3e26737f93","observation_id":"bba29ccd-1afe-40e1-8d51-50bf8ee03ae2","resolution":{"observed_at":"2026-08-14T14:36:36.298591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:35.686670Z","title":"Privacy-preserving record linkage for big data: Current approaches and research challenges,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.686670Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:6d2758930e3dfcc8774a107a3e2dbaa3b2dd9ac7e6dbdb79036c952488591bd4","observation_id":"d06940a0-7678-49c0-bdd9-9cea4c04cd7f","resolution":{"observed_at":"2026-08-14T14:36:35.686670Z","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":"2026-08-14T14:36:36.260591Z","title":"A random rotation perturbation approach to privacy preserving data classification,","venue":null,"work_id":"ff80afb7-64f2-4090-a9c7-16caad144ee5","year":2005},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.691782Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:35779b6e9d8c57f9206a48612b2efd9735ada16923c531b18f5e6108dc173da8","observation_id":"ad364c58-345d-4cef-9df0-ff0c0c6654b0","resolution":{"observed_at":"2026-08-14T14:36:36.266975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.238053Z","title":"Geometric data perturbation for privacy preserving outsourced data mining,","venue":null,"work_id":"e4f1c8e0-ee2d-4049-92da-e7f87c214c81","year":2011},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.696679Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:c87b06cbf033467cac9e145e731ff48e15998dd6ab7f8a2bf8495b28bd001a01","observation_id":"209d478c-0af1-4b8f-a1f1-3b3732491338","resolution":{"observed_at":"2026-08-14T14:36:36.248221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.219225Z","title":"Searchable encryption to reduce encryption degradation in adjustably encrypted databases,","venue":null,"work_id":"308ec7f4-0509-42c2-9d7d-14a794214b62","year":2017},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.701379Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:ef579abe54d2fcd16392c49c38da7d3045e964e61fa82504bb01dfe9b5e10981","observation_id":"2adef31c-62f1-48b0-a1cb-6c8e530f58d9","resolution":{"observed_at":"2026-08-14T14:36:36.224154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.203489Z","title":"Privacy-aware adaptive data encryption strategy of big data in cloud computing,","venue":null,"work_id":"a14bfa9a-a284-4013-93a0-8d3528b91b7f","year":2016},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.707238Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:065f4cb32c2db10948650dd2226db12875834eb65fc2260cda5f21202a9ed98e","observation_id":"3b19d1d4-8051-4ef0-aa23-baa3b369f61b","resolution":{"observed_at":"2026-08-14T14:36:36.208557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.182922Z","title":"Building confidential and efficient query services in the cloud with rasp data perturbation,","venue":null,"work_id":"07c181e2-1fa8-476f-b393-b8dca9ec76d0","year":2014},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.712124Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:bb426f3b342ce064d121458083ca06bc8200e1d92749c20c478ac8c87c4c18a2","observation_id":"8426b19c-8d99-4b15-8fc8-9a8b1be1ebb9","resolution":{"observed_at":"2026-08-14T14:36:36.188321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.167499Z","title":"Efficient data perturbation for privacy preserving and accurate data stream mining,","venue":null,"work_id":"386713c9-97d4-4a4b-9aa6-1305b8343d8b","year":2018},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.717056Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:6da375f671ac409cae9b6d16be19ba6fa8866057a3887bb98e2347f7563ce415","observation_id":"53ed0775-2e4f-481c-8b01-3f2d15f6865e","resolution":{"observed_at":"2026-08-14T14:36:36.172632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.149911Z","title":"Designing statistical privacy for your data,","venue":null,"work_id":"bd19b4a5-4d38-470d-94b9-a1e19f8c3764","year":2015},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.722773Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:2f0b56ff3b1a5a113b4074b0ca0139718dd6b707d7a22261a4c4f21853456a24","observation_id":"381f09c6-feca-482c-8aea-b65f68d755d4","resolution":{"observed_at":"2026-08-14T14:36:36.155789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.132369Z","title":"Efficient privacy preservation of big data for accurate data mining,","venue":null,"work_id":"449a7315-fc34-4fdc-86da-4563a3fe19d7","year":2019},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.727877Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:aaa66ec07ef4fafc0a61dc61bfb4a29cf5d675ce6302edc06c425b5e43b95d86","observation_id":"a5706a7d-5f28-477e-9927-5ae7d72cf782","resolution":{"observed_at":"2026-08-14T14:36:36.137460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.116983Z","title":"t-closeness: Privacy beyond k-anonymity and l-diversity,","venue":null,"work_id":"b96b3b92-13b9-4198-8f45-7bb50a477723","year":2007},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.733629Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:59aa066f2a67f048541c56fe69fbece0814a62c27a6c39e6b898d03d3642ff2a","observation_id":"178f837a-3895-43db-b086-ee4b9e2b90e4","resolution":{"observed_at":"2026-08-14T14:36:36.122283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.102148Z","title":"Information disclosure under realistic assumptions: Privacy versus optimality,","venue":null,"work_id":"556feab3-d005-469d-82fd-8821b97b56a1","year":2007},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.738443Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:ff35513a803d11429ffb5c5de07825c7e860cc2c948e674add0adc14caf1ff46","observation_id":"e2f20a89-bef2-47be-a5ba-e1211849ea48","resolution":{"observed_at":"2026-08-14T14:36:36.106891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.086439Z","title":"Composition attacks and auxiliary information in data privacy,","venue":null,"work_id":"2047054e-1ea5-4dc6-9c69-768ac5c93cb7","year":2008},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.744428Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:10c06a32cc36761b39c19ce1b3ff13a2a47c2060852c810a7ecc3d1ae5e5182a","observation_id":"b84744ef-f66d-4388-89a2-2fbbc6aad989","resolution":{"observed_at":"2026-08-14T14:36:36.091614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.069666Z","title":"Can the utility of anonymized data be used for privacy breaches?","venue":null,"work_id":"944684db-bbfd-4a62-b28d-03689fb7f07d","year":2011},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.749490Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:1f09870d958dc691949d9b175880cb0f9d1de0f3ce74cb29b041a63c5a37a95a","observation_id":"ff115aa7-b504-4db7-95db-8bd2406a26e9","resolution":{"observed_at":"2026-08-14T14:36:36.074657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.050939Z","title":"The differential privacy frontier,","venue":null,"work_id":"f0eea86b-4f50-485e-85b4-df3b69bca6bb","year":2009},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.755075Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:7c57a6424c1659831e4964d0fd8e530d3438048269803df78e4c82fbdc262718","observation_id":"00860a87-98b3-4d1e-adf7-bfd20d936ab1","resolution":{"observed_at":"2026-08-14T14:36:36.058938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.023482Z","title":"Differentially private data release for data mining,","venue":null,"work_id":"c089fa38-d69e-4a24-a37c-bfe60205c99f","year":2011},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.759694Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:dff780752c3d1a546f8e0e959a46d571c0955222860a22281e8f8710f7b035d9","observation_id":"7060cf78-d278-467e-8dbb-93932a6df031","resolution":{"observed_at":"2026-08-14T14:36:36.029376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:36.004859Z","title":"Towards practical differential privacy for sql queries,","venue":null,"work_id":"f57196f5-254d-42d7-af04-9316fb5d0df8","year":2018},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.764827Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:27af498ff66c75a8228d019085f9484716ac0eaef651b6fef3cbfc6a91253fa5","observation_id":"9cd0f1d9-89c7-4720-81d5-12d368548368","resolution":{"observed_at":"2026-08-14T14:36:36.010115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:35.986670Z","title":"Privacy integrated queries: an extensible platform for privacy-preserving data analysis,","venue":null,"work_id":"b56ab7f8-598c-458d-ac0f-8587a106d8bc","year":2009},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.769615Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:aeaa21034c78f556af9b4e9f27d3499dc1d803d9952f142f1d78f79fb3cc022f","observation_id":"edc87a47-16ad-44a3-b003-24ee15e9cbe2","resolution":{"observed_at":"2026-08-14T14:36:35.991888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:35.969018Z","title":"Local, private, efficient protocols for succinct histograms,","venue":null,"work_id":"21877c43-8d6f-42f3-bb1e-ebcf0a1ca1d6","year":2015},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.774292Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:a32e31d4c8cf8942447d70453e082cfa0fd712b652d68d33b8a88465b4d3012c","observation_id":"729e7db0-5371-4174-b7a5-167188aba77e","resolution":{"observed_at":"2026-08-14T14:36:35.975171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T14:36:35.952911Z","title":"Multi- key privacy-preserving deep learning in cloud computing,","venue":null,"work_id":"9af3974e-9e55-4614-adf3-f2c1177bf113","year":2017},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.778707Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:5dfa2da531e82978de26eb73af59f0112d0f2efffaaa9cfd58066f63f0b2abf6","observation_id":"58d36571-b3eb-4379-adc9-2f8b15e43d0d","resolution":{"observed_at":"2026-08-14T14:36:35.957814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1610.05755","last_updated":"2017-03-03T18:56:43Z","snapshot_observed_at":"2026-08-14T21:34:38.608528Z","submitted_at":"2016-10-18T19:37:37Z","title":"Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.05755","snapshot_observed_at":"2026-08-14T14:36:35.783262Z","title":"Semi-supervised knowledge transfer for deep learning from private training data,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.783262Z"},"links":{"cited_paper":"/paper/1610.05755","citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:3168b2b559fa3c00b6e904ec75519d5979a285ab57e38fb6946d1d70738c7412","observation_id":"9ab40071-f8bf-4cbf-a762-c1c454236245","resolution":{"observed_at":"2026-08-14T14:36:35.783262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.02952","last_updated":"2019-12-27T00:15:48Z","snapshot_observed_at":"2026-08-14T21:12:50.101596Z","submitted_at":"2017-03-08T18:21:03Z","title":"A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.02952","snapshot_observed_at":"2026-08-14T14:36:35.788126Z","title":"A hybrid deep learning architecture for privacy-preserving mobile analytics,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.788126Z"},"links":{"cited_paper":"/paper/1703.02952","citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:096f3095f50372f94fe694011738827594f21cfecf3bf42f930bb53fbaf689e6","observation_id":"69cffede-4b3f-42bd-93d7-ac55a60f6bda","resolution":{"observed_at":"2026-08-14T14:36:35.788126Z","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":"2026-08-14T14:36:35.793002Z","title":"Scikit-learn: Machine learning in python,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.793002Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:331553ee19df36ed7f6325c2e959dc626af6865cb65dc5c742f86f4933c61ed0","observation_id":"36460c3b-e8fb-423e-9595-034972b069fe","resolution":{"observed_at":"2026-08-14T14:36:35.793002Z","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":"2026-08-14T14:36:35.797559Z","title":"Xgboost: A scalable tree boosting system,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T14:36:35.797559Z"},"links":{"citing_paper":"/paper/1908.02997"},"observation_digest":"sha256:92043f1b423f59a83c32e0d3d30be516d3dc1a972773429a7da8a9f8735bf387","observation_id":"07314aa1-8189-4d3a-809c-a6f8e6af016b","resolution":{"observed_at":"2026-08-14T14:36:35.797559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.02997","last_updated":"2019-11-09T07:21:59Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T02:22:12.471822Z","submitted_at":"2019-08-08T10:13:56Z","title":"Local Differential Privacy for Deep Learning"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":2,"verified_fuzzy":35},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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:1908.02997."}