{"as_of":"2026-08-08T01:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:350fb8578a5ba62f9056e1d11a8d2e677138c9e9918b947982815968cd5d0680","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:23:18.130072Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2506.00201/citation-record","integrity":"/paper/2506.00201/integrity","json":"/paper/2506.00201/citation-record.json","paper":"/paper/2506.00201"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:23:20.721197Z","title":"Goodfellow, H","venue":null,"work_id":"f650dede-67bc-486f-9326-15a146edc1d8","year":2016},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:15.760538Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:59635843b0e2a043d8aa858ad065cff96ee285aef79ed477e44bd07a1d5533e2","observation_id":"7fa93085-47b0-4bfc-a76f-0e95afe28821","resolution":{"observed_at":"2026-08-07T12:23:20.802375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:20.497171Z","title":"Reconstructing training data with informed adversaries","venue":null,"work_id":"8981c037-7e98-4e49-b2c3-62d4a371c1a1","year":2022},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:15.823362Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:ae30b8a9869707ae500415530838aa2c2c63622ad4e7e9d8cffacb2a31897008","observation_id":"f0992954-78bd-4f5b-a9be-79e480050004","resolution":{"observed_at":"2026-08-07T12:23:20.601940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:20.245784Z","title":"Protection against reconstruction and its applications in private federated learning, 2019","venue":null,"work_id":"8d400360-36c9-47ee-91d7-f99050b364ea","year":2019},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:15.900969Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:00443ced9bceb2de75cf4e05cfdfcca017c220f03e3ebaada99083d7e52ee45e","observation_id":"2d42f836-f76a-4141-9e96-ddcff9c109d0","resolution":{"observed_at":"2026-08-07T12:23:20.368097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:20.033533Z","title":"Private empirical risk minimization: Efficient algorithms and tight error bounds","venue":null,"work_id":"96e3bb64-6bee-4a98-8c4e-fad048682c47","year":2014},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:15.978543Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:93f39533276f3b290c4b51aef340839535a888d4db62c6f27bdbbb9d773596c7","observation_id":"2d2cd99f-658b-465d-9a2e-b36213f4fd8e","resolution":{"observed_at":"2026-08-07T12:23:20.144541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.00075","last_updated":"2019-04-30T19:43:53Z","snapshot_observed_at":"2026-07-06T07:49:38.806531Z","submitted_at":"2019-04-30T19:43:53Z","title":"On the Use of ArXiv as a Dataset","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.00075","snapshot_observed_at":"2026-08-07T12:23:16.040012Z","title":"Clement, Matthew Bierbaum, Kevin P","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:16.040012Z"},"links":{"cited_paper":"/paper/1905.00075","citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:7562ac9739cb70b98da72801b76b061a70b1525ca77f3ba8dca2a392a85bf5fd","observation_id":"615c6b4e-d676-4250-acaf-47a579807328","resolution":{"observed_at":"2026-08-07T12:23:16.040012Z","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":"2026-08-07T12:23:19.925502Z","title":null,"venue":null,"work_id":"c4743dc4-f44c-410f-bb95-8a1ad40b0713","year":2018},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:16.092379Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:266228bf6f7835bcbdaa1d916a65d85fd9f67c16e6be971975d48a5c360549bf","observation_id":"40b0203c-0be2-4e6a-b650-36b59a1841df","resolution":{"observed_at":"2026-08-07T12:23:19.951568Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:19.832722Z","title":"Mind the privacy unit! user-level differential privacy for language model fine-tuning","venue":null,"work_id":"9fc0200c-3517-4308-8610-709adc322855","year":2024},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:16.189040Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:b6175c922398f3fcf87fd2cc96d5e720a2804835e6c1e25c2709997f06866e06","observation_id":"cdfcacc3-38ed-49a4-8d82-079f7ca63ec2","resolution":{"observed_at":"2026-08-07T12:23:19.884934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:16.293586Z","title":"Brendan McMahan, Nicole Mitchell, Krishna Pillutla, and Keith Rush","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:16.293586Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:b18a87c9a01f973bf6290a3c8fec1950a6efc98d4b795b1686db697e7b1e790a","observation_id":"07881899-0319-4b96-b202-fdea4fcbec79","resolution":{"observed_at":"2026-08-07T12:23:16.293586Z","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":"2026-08-07T12:23:16.465263Z","title":"Quantifying memorization across neural language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:16.465263Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:e5f49653c33b03dcf6410c2edd0e43c1da4ea5b662892279f2458187112e5ae0","observation_id":"1ad3582e-b915-4030-934f-0fc5329bb4e3","resolution":{"observed_at":"2026-08-07T12:23:16.465263Z","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":"2026-08-07T12:23:16.578239Z","title":"Extracting training data from large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:16.578239Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:1e22dfe79c468ba860c61fe485096358f96ebbfa15cfa02ae92a9a1c32c2ff7e","observation_id":"9219d0c6-e244-4a4b-9aba-5e418cd860fc","resolution":{"observed_at":"2026-08-07T12:23:16.578239Z","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":"2026-08-07T12:23:19.693673Z","title":"BERT : Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":"a43b61ec-843f-4076-b7df-79ab3ddc46ca","year":2019},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:16.687066Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:a0f2052a535df463732ebe6593285e61087eb4384baf73cbbd2668bffc7fd67f","observation_id":"5b781f38-b837-4c70-902b-bd6ff34af79a","resolution":{"observed_at":"2026-08-07T12:23:19.752346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:19.581600Z","title":"R2t: Instance-optimal truncation for differentially private query evaluation with foreign keys","venue":null,"work_id":"5eb86d32-1d81-48a4-83f5-3e5ece9b8c6d","year":2022},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:16.808432Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:e6da6130cd3923386da86e93181f435328d257daba1c32ba8438b847212bf646","observation_id":"d4e2de4b-ccb3-461e-a40c-5a1df9c037f2","resolution":{"observed_at":"2026-08-07T12:23:19.631319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:19.439604Z","title":"Calibrating noise to sensitivity in private data analysis","venue":null,"work_id":"c3ecbcc1-7f91-44c2-9b87-32f02a495d70","year":2006},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:16.949808Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:c93461bc98e8cbe835de411401b81bee9d4bc47ea0fb155f17e2b9ce9da2eada","observation_id":"da5bfb44-152c-4ee4-a3c7-a35db99a56b7","resolution":{"observed_at":"2026-08-07T12:23:19.509064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:19.346792Z","title":"Google's differential privacy libraries., 2022","venue":null,"work_id":"324bf0b6-790d-4833-8b93-81a46d7d7b77","year":2022},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:17.087052Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:a3414bdc6023da57ce771c911af3e3a10fb951206ca5c541eac33928934d9094","observation_id":"03849e87-b2b9-4159-95e9-9bdb8f390c6b","resolution":{"observed_at":"2026-08-07T12:23:19.411217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:17.189622Z","title":"It's my data too: Private ml for datasets with multi-user training examples, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:17.189622Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:1239191637a6bb221b6b8a16f52f0b51006cc3f8dd065ad0ba6d479f4c74ecc9","observation_id":"3dc3d496-3ac2-49a4-85b4-913c27d08585","resolution":{"observed_at":"2026-08-07T12:23:17.189622Z","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":"2026-08-07T12:23:19.055311Z","title":"Bounding training data reconstruction in DP - SGD","venue":null,"work_id":"a5bbdaf3-028e-41c0-ad82-8fd620454d6f","year":2023},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:17.316563Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:564c6bdc52288d310f3c8ef73327c2eac7373d00fa8a2b945174a402d3f575aa","observation_id":"7f13ddfd-d10d-442c-bf9e-5c7f7546fafe","resolution":{"observed_at":"2026-08-07T12:23:19.279865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17546","last_updated":"2023-09-11T16:58:48Z","snapshot_observed_at":"2026-08-04T04:34:05.607113Z","submitted_at":"2022-10-31T17:57:55Z","title":"Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.17546","snapshot_observed_at":"2026-08-07T12:23:17.454703Z","title":"Preventing verbatim memorization in language models gives a false sense of privacy","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:17.454703Z"},"links":{"cited_paper":"/paper/2210.17546","citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:7c97ac729ea16af54e5241cad11ef287a9bbf386c3838bfcb9154e7b5e01bfef","observation_id":"e4ca734f-88c7-40df-b168-f01b88a536a3","resolution":{"observed_at":"2026-08-07T12:23:17.454703Z","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":"2026-08-07T12:23:18.953484Z","title":"Conservative or liberal? personalized differential privacy","venue":null,"work_id":"738c14ae-92fc-46be-a981-7a4d68af55ce","year":2015},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:17.539693Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:9ddf7b012e863d2b4667f4c4eb72e9ce026dbd70588ab937b376133e65e57575","observation_id":"610f935d-7d9f-4507-a6f2-beeb73c72f1d","resolution":{"observed_at":"2026-08-07T12:23:18.980338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.17035","last_updated":"2023-11-28T18:47:03Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-11-28T18:47:03Z","title":"Scalable Extraction of Training Data from (Production) Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.17035","snapshot_observed_at":"2026-08-07T12:23:17.626720Z","title":"Scalable extraction of training data from (production) language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:17.626720Z"},"links":{"cited_paper":"/paper/2311.17035","citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:e0410feb149cb68caff3ec070bb0e223abaf41405e93ed979e702ff1882ab228","observation_id":"be6e8bbe-a6c6-4d80-9612-562ed5597033","resolution":{"observed_at":"2026-08-07T12:23:17.626720Z","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":"2026-08-07T12:23:17.726823Z","title":"The fineweb datasets: Decanting the web for the finest text data at scale, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:17.726823Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:90662a81a702a44e64f529c87762d2fd03ec65de8dee2a1222a41a1432e1dba8","observation_id":"c45ab347-b745-4216-b0c2-07c14c17028c","resolution":{"observed_at":"2026-08-07T12:23:17.726823Z","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":"2026-08-07T12:23:18.816122Z","title":"Stochastic gradient descent with differentially private updates","venue":null,"work_id":"7ae26b7d-c4de-4e74-bb53-76ced764486a","year":2013},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:17.837310Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:de2078053b7b4792ce7e859039dbe70133748deadd401d1c370fa179b3087f19","observation_id":"4584597b-c276-4054-ac51-baf9879ff149","resolution":{"observed_at":"2026-08-07T12:23:18.887926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:18.657298Z","title":null,"venue":null,"work_id":"6949ea29-88cd-482b-bb2a-ee1c48202ecf","year":2024},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:17.949185Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:55538137cd5de7e264a8edd71ad2a7abec8b9522c1932e2f616fd2d8760d0cd4","observation_id":"ce7b3e87-1c38-492f-9174-4f2e1a1b92b6","resolution":{"observed_at":"2026-08-07T12:23:18.718309Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:18.488054Z","title":"Individual privacy accounting for differentially private stochastic gradient descent","venue":null,"work_id":"b01c9166-917f-4bf3-a75b-e7a092087d92","year":2023},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:18.039269Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:764189f039d9c7fdf05c4ee698fd82d3caeab3d8478973f4e07238c67275804d","observation_id":"2e14ec89-9ec6-4945-bd22-af228c20be35","resolution":{"observed_at":"2026-08-07T12:23:18.576318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T12:23:18.319622Z","title":"Optimal accounting of differential privacy via characteristic function","venue":null,"work_id":"0c5e6844-d8a5-451e-bdc7-932863f3d4f5","year":2022},"citing_paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T12:23:18.130072Z"},"links":{"citing_paper":"/paper/2506.00201"},"observation_digest":"sha256:9188235ce507be91e39b8a18a8e3fb931ca666fffcfc3f5e2a5c70392bfedbd9","observation_id":"bd539190-f018-4a46-9dcf-6f1733163094","resolution":{"observed_at":"2026-08-07T12:23:18.404720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.00201","last_updated":"2025-05-30T20:14:02Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-07T12:08:05.778764Z","submitted_at":"2025-05-30T20:14:02Z","title":"Hush! Protecting Secrets During Model Training: An Indistinguishability Approach"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":0,"verified_fuzzy":14},"total_outbound_references":24},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2506.00201."}