{"as_of":"2026-08-17T03:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1d35873829d204b76dc6dbc123ca6af47a01fc232b8b33a8c0d9cb2e64f1f36e","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:26:41.082874Z","state":"measured"},{"denominator":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T20:00:20.012126Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-24T03:53:53.901980Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"cited_work":{"arxiv_id":"1908.03566","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1908.03566","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"That which we call private","venue":null,"work_id":"7c41d4d8-cf6d-444e-a4f3-3f3c5d791f5a","year":2020},"citing_paper":{"arxiv_id":"2403.10307","last_updated":"2026-05-20T08:59:43Z","snapshot_observed_at":"2026-08-17T03:54:26.529526Z","submitted_at":"2024-03-15T13:47:44Z","title":"Chernoff Information as a Privacy Constraint for Adversarial Classification and Membership Advantage","version":5},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-24T03:52:29.108705Z"},"links":{"cited_paper":"/paper/1908.03566","citing_paper":"/paper/2403.10307"},"observation_digest":"sha256:9c2c6e922a2d5eb0d04bfbbb682bdede098c97e88a454ee74360fdbda8835a3e","observation_id":"253e8ae2-52c5-4639-9858-c760156bf42c","resolution":{"observed_at":"2026-05-24T03:53:53.905502Z","resolver_source":"arxiv_id","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":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.03566","snapshot_observed_at":"2026-08-11T20:00:20.012126Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.06157","last_updated":"2024-12-09T02:39:58Z","snapshot_observed_at":"2026-08-15T22:22:00.400827Z","submitted_at":"2024-12-09T02:39:58Z","title":"Membership Inference Attacks and Defenses in Federated Learning: A Survey","version":1},"reference_index":141,"source":"pdf_text","source_observed_at":"2026-08-11T20:00:20.012126Z"},"links":{"cited_paper":"/paper/1908.03566","citing_paper":"/paper/2412.06157"},"observation_digest":"sha256:4a9a1275af492a230a3d234ee1bd6105d826fa8831cb968c2293f1c4bdd87c04","observation_id":"df82ad52-554d-4722-b2ef-798c7b46476c","resolution":{"observed_at":"2026-08-11T20:00:20.012126Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"cited_work":{"arxiv_id":"1908.03566","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1908.03566","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"That which we call private","venue":null,"work_id":"7c41d4d8-cf6d-444e-a4f3-3f3c5d791f5a","year":2020},"citing_paper":{"arxiv_id":"2605.06835","last_updated":"2026-05-07T18:42:35Z","snapshot_observed_at":"2026-08-15T17:58:25.752886Z","submitted_at":"2026-05-07T18:42:35Z","title":"On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-11T00:52:34.784185Z"},"links":{"cited_paper":"/paper/1908.03566","citing_paper":"/paper/2605.06835"},"observation_digest":"sha256:5992771078c528aa93cce39e362ca8843c0c81f92874e35235f783cc3e1d8858","observation_id":"f49f927c-bd22-4b89-8edc-2feeeb1ce5bb","resolution":{"observed_at":"2026-05-11T05:05:57.350034Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/1908.03566/citation-record","integrity":"/paper/1908.03566/integrity","json":"/paper/1908.03566/citation-record.json","paper":"/paper/1908.03566"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:26:41.296797Z","title":"Goodfellow, H","venue":null,"work_id":"be131492-1d95-4c30-b71a-ce3c373c4c2c","year":2016},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.018868Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:e9d71b3c28b693429a8c11f1ab953ddfca285da60b2f8ebe059bb793f25d8c30","observation_id":"5d95b956-a6e6-4107-991a-3c6594f234e7","resolution":{"observed_at":"2026-08-14T14:26:41.300310Z","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":"2026-08-14T14:26:41.286930Z","title":"Learning with pri- vacy at scale","venue":null,"work_id":"fad75d2d-e15a-447e-9c60-69c524452687","year":2017},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.022622Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:aed70f0770aa8e146294c00fa18eccb12001a05492d590e73b3707f56c511a8e","observation_id":"5d42e801-ffe0-4973-b6d5-c1cb28e4b5ac","resolution":{"observed_at":"2026-08-14T14:26:41.290118Z","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":"2026-08-14T14:26:41.277923Z","title":"Concentrated differ- ential privacy: Simplifications, extensions, and lower bounds","venue":null,"work_id":"8c77f4e6-d419-4b71-acaf-a488fc9b23b5","year":2016},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.025721Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:6ecee152f514b98ae7f896d215478a0cabe4b045e6d65fa67089d47931724702","observation_id":"ebecc266-8b39-4365-a694-af71da6f08db","resolution":{"observed_at":"2026-08-14T14:26:41.281216Z","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":"2026-08-14T14:26:41.268225Z","title":"The secret sharer: Measuring unintended neural network memorization & extracting secrets","venue":null,"work_id":"7f94c17d-d3f2-4e7e-a362-bd93c85553e9","year":2019},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.028832Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:7a7f3d90d0dc09e391ceb8f1ef54fee373383ea9f9c4a8ef4713a94af273eeab","observation_id":"eb9b4007-84e0-4ae1-aed1-a98383fc090f","resolution":{"observed_at":"2026-08-14T14:26:41.271535Z","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":"2026-08-14T14:26:41.258528Z","title":"Collecting telemetry data privately","venue":null,"work_id":"e54843a6-e14b-4d13-94db-b45256a508b9","year":2017},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.031886Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:a290490032ad721ad251bfefaf33cf39d6f34e474bcf394ceb7c88c129a52ce9","observation_id":"96a64511-f61b-4222-ab4b-f3b417d91b74","resolution":{"observed_at":"2026-08-14T14:26:41.261897Z","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":"2026-08-14T14:26:41.248919Z","title":"Our data, ourselves: Privacy via distributed noise generation","venue":null,"work_id":"80cf17a7-0546-4932-a9c9-2e1666af904e","year":2006},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.035246Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:c8b685716b8c3f83a6fa216f38be6bd732aec459b1a6a64688cb6d99e0393a24","observation_id":"9a878e15-8db2-46a8-b1b9-cdd23ab47985","resolution":{"observed_at":"2026-08-14T14:26:41.252732Z","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":"2026-08-14T14:26:41.238795Z","title":"Calibrating noise to sensitivity in private data analysis","venue":null,"work_id":"754d2f29-0ef6-4656-b6bf-4fc67c374ddb","year":2006},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.038532Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:5a323ced24be58b7d929dbf20d31eabe20402a9f8249a8ea7b2b8e8d1087a058","observation_id":"24014c0f-cb5a-4fb5-ad7e-7aabecf377a5","resolution":{"observed_at":"2026-08-14T14:26:41.242629Z","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":"2026-08-14T14:26:41.227983Z","title":"Rothblum, and Salil Vadhan","venue":null,"work_id":"631f48b3-1b53-4d61-a6d9-15e7d525d617","year":2010},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.041539Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:1de598027cba3eaaea5a66b925cb832a87a099d7a2673591e6cd8e50634b88ce","observation_id":"f85c300d-3118-4144-a910-4974e77e02bf","resolution":{"observed_at":"2026-08-14T14:26:41.231858Z","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":"2026-08-14T14:26:41.218636Z","title":"RAPPOR: Randomized aggregatable privacy- preserving ordinal response","venue":null,"work_id":"446a3403-56a2-4546-9e6d-8c075d182bca","year":2014},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.044611Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:347b482aabca1974bb02579c5901a55423c74dfd34e1afae86faa7109de3767b","observation_id":"f97093f7-970d-4d37-b5f8-e4457803f282","resolution":{"observed_at":"2026-08-14T14:26:41.221993Z","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":"2026-08-14T14:26:41.208792Z","title":"Differential privacy for functions and functional data","venue":null,"work_id":"3e3dde9b-b4f2-4d95-8e34-444e015d7c20","year":2013},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.048288Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:bf451c080a54b23c830e18bec435eaf1f96abea0adf32d1ff32e3b4dd16a8dac","observation_id":"ba23fc05-5f5f-4817-a77f-7a28e1cda1cf","resolution":{"observed_at":"2026-08-14T14:26:41.212860Z","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":"1902.08874","last_updated":"2019-08-12T23:18:20Z","snapshot_observed_at":"2026-08-14T17:12:15.326285Z","submitted_at":"2019-02-24T01:48:53Z","title":"Evaluating Differentially Private Machine Learning in Practice","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08874","snapshot_observed_at":"2026-08-14T14:26:41.052038Z","title":"Evaluat- ing differentially private machine learning in practice","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.052038Z"},"links":{"cited_paper":"/paper/1902.08874","citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:e28702521950d91158655f22371089c31da3a0d9d8741077c4e4a22a0931683b","observation_id":"71f91be3-2727-4b0a-a858-2f5042a58499","resolution":{"observed_at":"2026-08-14T14:26:41.052038Z","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":"2026-08-14T14:26:41.198083Z","title":"R ´enyi differential privacy","venue":null,"work_id":"c14d78c0-18f7-421a-849f-3e4f4412635c","year":2017},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.055696Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:1750894f9243b90f4eb5bca43e11f27160f3355283e019bf4a8640d2dcb468b3","observation_id":"2f825373-f4df-48fd-9c7f-a57e5bdbfacb","resolution":{"observed_at":"2026-08-14T14:26:41.201995Z","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":"2026-08-14T14:26:41.186552Z","title":"Secureml: A sys- tem for scalable privacy-preserving machine learning","venue":null,"work_id":"d2e49375-4ef7-40c8-bdc8-02026e8b2cab","year":2017},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.058611Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:b36c57772376e7fccbb9f50f57de4cc97f5a96b4cc6b102b72b6a0ee4df1cbdc","observation_id":"50bd5490-303f-42fb-8cd1-01f2a88fefd0","resolution":{"observed_at":"2026-08-14T14:26:41.191203Z","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":"2026-08-14T14:26:41.175170Z","title":"Semi-supervised knowl- edge transfer for deep learning from private training data","venue":null,"work_id":"9d18dac4-e7c7-4004-a307-d9a7502b6927","year":2017},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.061692Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:79329a8f2f102328e6cc3573924bc9bef97960c986bf48456a56781ca88f4ac0","observation_id":"f0986356-b2aa-4e1b-83cb-ad592495d17d","resolution":{"observed_at":"2026-08-14T14:26:41.180147Z","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":"2026-08-14T14:26:41.165049Z","title":"In- troducing tensorflow privacy: Learning with differential privacy for training data","venue":null,"work_id":"419c5db2-3215-4e17-be00-69074535ab21","year":2019},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.064464Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:9b70abfc9cc2242d7f65b9462d2b05c30fd313e15f123a6332c0c644e4037610","observation_id":"81cdd153-3ade-48a1-bda4-1226548fa245","resolution":{"observed_at":"2026-08-14T14:26:41.168464Z","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":"1806.00451","last_updated":"2018-06-01T17:16:56Z","snapshot_observed_at":"2026-08-16T06:32:06.888652Z","submitted_at":"2018-06-01T17:16:56Z","title":"Do CIFAR-10 Classifiers Generalize to CIFAR-10?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00451","snapshot_observed_at":"2026-08-14T14:26:41.067815Z","title":"Do cifar-10 classifiers generalize to cifar-10? arXiv preprint arXiv:1806.00451, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.067815Z"},"links":{"cited_paper":"/paper/1806.00451","citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:32232ebf1e1cca33f409209445d7b524775a25cb8f7ddfc4b3d8a9e49899bc6a","observation_id":"8eaff7cd-2aa0-4f88-a383-ae73fce0d19f","resolution":{"observed_at":"2026-08-14T14:26:41.067815Z","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":"2026-08-14T14:26:41.155598Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":"8695dcb4-45b3-4fd5-9dcd-33c27f44a562","year":2017},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.071493Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:30af3f248bf0df724acdaaed9031fc25a09b544941ba2849e00a823a5cb05619","observation_id":"2d58a502-a456-4671-af9b-cdd7eee36ac9","resolution":{"observed_at":"2026-08-14T14:26:41.159112Z","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":"2026-08-14T14:26:41.145753Z","title":"Machine learning models that remember too much","venue":null,"work_id":"317f3f12-3404-4d3f-90ae-d3fc23c35cb2","year":2017},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.075393Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:4ccfe0da8fdaa2a8f418b32b35d728bdf43c26b91b20178cc532025dfe567518","observation_id":"de0039c9-316d-4b95-a1d6-93d26de6af06","resolution":{"observed_at":"2026-08-14T14:26:41.148934Z","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":"1905.10498","last_updated":"2019-11-04T21:05:26Z","snapshot_observed_at":"2026-08-14T16:26:48.764751Z","submitted_at":"2019-05-25T01:50:51Z","title":"Cold Case: The Lost MNIST Digits","version":2},"cited_work":{"arxiv_id":"1905.10498","doi":null,"metadata_source":"pith","pith_arxiv_id":"1905.10498","snapshot_observed_at":"2026-08-14T14:26:41.108035Z","title":"Cold Case: The Lost MNIST Digits","venue":"cs.LG","work_id":"3748d85c-022d-48b0-a2ca-5b6142f9c1a3","year":2019},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.078881Z"},"links":{"cited_paper":"/paper/1905.10498","citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:98c1256c0490daf39d4c54bf3ada942d2fc8a5c8238459b13fe29421ba801eab","observation_id":"b4de073b-799e-4c21-bc69-95c7c3122cc3","resolution":{"observed_at":"2026-08-14T14:26:41.113426Z","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":"2026-08-14T14:26:41.136433Z","title":"Privacy risk in machine learning: An- alyzing the connection to overfitting","venue":null,"work_id":"e1873831-a0a4-4979-af3d-e3448d7f5caa","year":2018},"citing_paper":{"arxiv_id":"1908.03566","last_updated":"2020-04-20T18:39:55Z","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:26:41.082874Z"},"links":{"citing_paper":"/paper/1908.03566"},"observation_digest":"sha256:1513ee38c0f3a34375c02872af1596e68bbd9ca6e779a5498eb69e5324a2a239","observation_id":"b031efc0-110f-45b8-90b7-b48c0fe11782","resolution":{"observed_at":"2026-08-14T14:26:41.139776Z","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":"1908.03566","last_updated":"2020-04-20T18:39:55Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T22:20:53.600206Z","submitted_at":"2019-08-08T22:09:52Z","title":"That which we call private"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":2,"verified_exact":1,"verified_fuzzy":17},"total_outbound_references":20},"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 17 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 3 inbound Pith citation observations for arXiv:1908.03566."}