{"as_of":"2026-08-10T10:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bb6d4ae2751aa35a9f39385870c16e69a0a66d89320d2ba09b1b8b460bd10f1c","coverage":[{"denominator":85,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":85,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T22:28:06.257168Z","state":"measured"},{"denominator":85,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":85,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2508.07066/citation-record","integrity":"/paper/2508.07066/integrity","json":"/paper/2508.07066/citation-record.json","paper":"/paper/2508.07066"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T22:28:05.861279Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.861279Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:63b952144ff0e7963a3586acc099b0d405c1e837376f646ea4d3b4739601b50e","observation_id":"1647fa2e-adf8-419b-8915-e66cf9d565e8","resolution":{"observed_at":"2026-08-05T22:28:05.861279Z","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":"2026-08-05T22:28:05.866455Z","title":"Estimat- ing example difficulty using variance of gradients","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.866455Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:f95df8853a0a8f6b24c907e4d7f157b1ae0dff19877147fb6c50fba894bd6c81","observation_id":"56b04d81-d41a-44ac-a2e5-549d52da0683","resolution":{"observed_at":"2026-08-05T22:28:05.866455Z","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":"2026-08-05T22:28:05.871241Z","title":"Memory aware synapses: Learning what (not) to forget","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.871241Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:7fc0f3a862620668a5693d48d3034928d48f2526ca30afd8b86390129c4484b7","observation_id":"8dcf3fec-84de-446e-a767-dd80b322cf92","resolution":{"observed_at":"2026-08-05T22:28:05.871241Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.07511","last_updated":"2022-12-07T05:08:01Z","snapshot_observed_at":"2026-07-06T11:29:34.579530Z","submitted_at":"2021-07-15T17:59:50Z","title":"A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.07511","snapshot_observed_at":"2026-08-05T22:28:05.875637Z","title":"A gentle in- troduction to conformal prediction and distribution-free un- certainty quantification","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.875637Z"},"links":{"cited_paper":"/paper/2107.07511","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:0d70e71575636312086f0d6a168a624f8cfdb72a0a5427e99d0fdfeacebd0358","observation_id":"676333bf-f1a3-4c78-85c8-96fe446506a6","resolution":{"observed_at":"2026-08-05T22:28:05.875637Z","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":"2026-08-05T22:28:05.880835Z","title":"Controlling the false discovery rate via knockoffs","venue":null,"work_id":null,"year":2055},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.880835Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:722d6bf140eacfaf0073b55e0d117d5430c6ca0b23b8bad42407987afadd7508","observation_id":"ba8f56ed-6a51-411e-adfe-5569d5bbc554","resolution":{"observed_at":"2026-08-05T22:28:05.880835Z","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":"2026-08-05T22:28:05.886254Z","title":"Practical ad- versarial multivalid conformal prediction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.886254Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:2818c4047bf77129dd5fbdf97acb30d49e93c1ecca7bf19969c8a9a5a7521d90","observation_id":"74b0c051-6dc1-4651-ac5d-6ea5a685a24a","resolution":{"observed_at":"2026-08-05T22:28:05.886254Z","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":"2026-08-05T22:28:07.485719Z","title":"Testing for outliers with conformal p-values","venue":null,"work_id":"45aff42b-c775-4080-adfd-b766373dfcd2","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.890760Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:bb3955ae1d324941153b433929a18aab49002dc55df1bc2ae055945420b6f2d8","observation_id":"27f6f63b-fae0-4ba7-b951-2a895fecd00e","resolution":{"observed_at":"2026-08-05T22:28:07.490129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.471305Z","title":"Discovering the false discovery rate","venue":null,"work_id":"1a27c8a2-3cf4-453f-9e87-04827a98c318","year":2010},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.895489Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:7577c94fae26122bd8c819d15e13ba59bba41eea81ae47dc22cc9ee0e12f98ea","observation_id":"eba287a7-45d9-4248-8683-3c5cdf2d802e","resolution":{"observed_at":"2026-08-05T22:28:07.476065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.456818Z","title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","venue":null,"work_id":"b0559a2b-6446-4780-9b71-e781613119bd","year":1995},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.900117Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:aa3917cc5b704db795088733989535ee23dac02044d8bf8c4f4802654fb8159e","observation_id":"997ad05e-7701-4514-b57b-75a128b59dd2","resolution":{"observed_at":"2026-08-05T22:28:07.461454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.442740Z","title":"Scalable member- ship inference attacks via quantile regression","venue":null,"work_id":"a0215cec-1796-4a48-bf38-d77eb08bd1e8","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.905154Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:3a59498d947af2f07c5fb6ac055c03ac246b1c045410e548469dc70083a05427","observation_id":"d7c838df-5dba-4bfe-9674-b94133d22854","resolution":{"observed_at":"2026-08-05T22:28:07.447179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.428876Z","title":"Machine unlearning","venue":null,"work_id":"c8eabccc-3060-456b-8589-d86e5824f151","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.910429Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:6eb376c478e33a41fac8209dfc738ad4ef7f6f2862de44a90f942ce091aa03a4","observation_id":"5b32443d-9156-452d-98d9-91de619ef780","resolution":{"observed_at":"2026-08-05T22:28:07.433317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.413937Z","title":"Membership inference attacks from first principles","venue":null,"work_id":"0324c1e3-cbd3-4abb-8258-b1acbaaa6b4e","year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.916204Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:475622dd1910bdd9a91423d522fa770e949151e433a02353edbc23087500e040","observation_id":"68e3fafa-8fc9-435b-bb7a-6ad9b238acfe","resolution":{"observed_at":"2026-08-05T22:28:07.418541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.399091Z","title":"Quan- tifying memorization across neural language models","venue":null,"work_id":"068865d0-4e1a-433f-9015-a655cb1e80a0","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.921333Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:b143a2353c95790ec0158ee78b8cd5e1a2c5170d4abbddd65ab840ac485a6bad","observation_id":"1f5e0413-d7b5-4ee8-b955-e1385475b69d","resolution":{"observed_at":"2026-08-05T22:28:07.403801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.384911Z","title":"Modeling and understanding un- certainty in medical image classification","venue":null,"work_id":"6bf825da-bd8a-4056-a28d-a29011820855","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.925413Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:c93d6eda6d7c8baf644adde6b48d10bedfcb02b1f5e38bdc62e2e85fd0b73465","observation_id":"9847d438-f60f-45f0-98d1-1655c4f4ead3","resolution":{"observed_at":"2026-08-05T22:28:07.389384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.370800Z","title":"A survey of security and privacy issues of machine unlearning,","venue":null,"work_id":"7423cdf3-e242-4d0c-8b96-0d47f4fdf31c","year":null},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.929578Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:56a822e391b9608823babe9a799c5ede4ef87be97897638ab2580f004c52a2ac","observation_id":"aaecba27-29d3-4463-b2d1-e93a50bfd495","resolution":{"observed_at":"2026-08-05T22:28:07.375319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.356197Z","title":"When machine unlearn- ing jeopardizes privacy","venue":null,"work_id":"9e07428a-139d-407a-ad8a-4b95ee73a679","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.934529Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:17a32bbe06e2b2026850baf54baddd0c81b87e52fdc2c21a3bd105e8f969b562","observation_id":"9238d17c-7ff0-417e-9b62-b5d067d5f916","resolution":{"observed_at":"2026-08-05T22:28:07.361191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.341215Z","title":"Boundary unlearning: Rapid forgetting of deep net- works via shifting the decision boundary","venue":null,"work_id":"918b623d-bb97-4fdb-af50-7c0e287ce545","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.940038Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:728170ea6a081926bfa73c5e5844d70723eb82d311534aab88099e1bba28636e","observation_id":"3b55e0e7-c227-46e8-8cdf-9d6b8a3aea23","resolution":{"observed_at":"2026-08-05T22:28:07.346145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.326338Z","title":"Putting the object back into video object segmentation","venue":null,"work_id":"ae5a3747-80e9-4a3c-b16a-fe0676e42e4e","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.945181Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:feda6fe71036db7957b00935e535d75de992d2b61ca26b8f9d0ceeddd2df4488","observation_id":"eaf5cd41-609f-42f2-b6b3-ba293d854458","resolution":{"observed_at":"2026-08-05T22:28:07.330930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07018","last_updated":"2024-05-11T13:52:22Z","snapshot_observed_at":"2026-07-06T18:12:59.925736Z","submitted_at":"2024-05-11T13:52:22Z","title":"Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You Thought","version":1},"cited_work":{"arxiv_id":"2405.07018","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.07018","snapshot_observed_at":"2026-08-05T22:28:06.513662Z","title":"Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You Thought","venue":"cs.CR","work_id":"bee92a8b-ca6f-4903-a793-f51c7af0f293","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.950733Z"},"links":{"cited_paper":"/paper/2405.07018","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:e78c1b55c0ea0944f1d615e47f8601c726d392521d44f16c5c752c237841d04d","observation_id":"049eb5e0-528d-4f8a-8735-3d245d5a4f5a","resolution":{"observed_at":"2026-08-05T22:28:06.518707Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.311537Z","title":"Membership inference at- tack using self influence functions","venue":null,"work_id":"bb4f8228-f9dc-466a-a823-39a88298c3e2","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.955872Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:5aae0f84d92ccb51a2a5c60eab1f2a6ffb99bb5167fd99a463c034f0a6499be4","observation_id":"d9c42577-9936-4fa4-a153-f979c8331b30","resolution":{"observed_at":"2026-08-05T22:28:07.316121Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.297415Z","title":"Theory of probability: A critical introduc- tory treatment","venue":null,"work_id":"689f6be0-626b-4286-a661-0a5b76067037","year":2017},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.960615Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:e902fce316916895055e55832c053d2bddabd2ad3a694f57e2e40a9deaa64c60","observation_id":"85d606a4-c964-436d-8119-b0fbc4c4df80","resolution":{"observed_at":"2026-08-05T22:28:07.301944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.283343Z","title":"Objaverse: A universe of annotated 3d objects","venue":null,"work_id":"3c17adfa-a370-4544-87ee-6edd031c4824","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.965099Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:a3f2f014f3d1f0d3c66bcaa3b615ea89a7cbdf680406084ab4452b6234e66a2f","observation_id":"92896cb0-f9ec-4a6f-9e83-8615afa18c4c","resolution":{"observed_at":"2026-08-05T22:28:07.287942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.268017Z","title":"Leveraging adversarial examples to quantify membership information leakage","venue":null,"work_id":"0dd52d64-c78c-45fc-ae0f-397884d09f7a","year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.969242Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:9e5d6488691c34696fd5155da7dd8a662df5c6d1a8d601fefe8dba4e8743045d","observation_id":"df29e687-d576-4e2b-92c1-c493f9ff53d5","resolution":{"observed_at":"2026-08-05T22:28:07.273045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:05.973405Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.973405Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:446da528408b46e25c326fef5758ac9d24f633573cc8cddcd0e310a44766b2f6","observation_id":"e521eb02-72d0-4b0a-b84d-31541c6651a9","resolution":{"observed_at":"2026-08-05T22:28:05.973405Z","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":"2026-08-05T22:28:07.242337Z","title":"Eva: Exploring the limits of masked visual representa- tion learning at scale","venue":null,"work_id":"9ae10d45-5233-4be3-aca3-4cdda28ff4bf","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.977869Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:de7b672995aec47019786b5bbbe8e597ec12a19180a9aa500cb38727e60c631a","observation_id":"8c812bf1-e327-4578-ac16-fffeab4e262d","resolution":{"observed_at":"2026-08-05T22:28:07.248210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.225743Z","title":"What neural networks memorize and why: Discovering the long tail via influence estimation","venue":null,"work_id":"dfacd070-fccc-4a51-b05e-98d97add93d2","year":2020},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.982430Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:8b5f56df25d148a612b352a9fbf3f9e9a71a7d9ffd5874353e944c308e07aa48","observation_id":"1caf6c4f-2898-4f83-8cd3-196220382065","resolution":{"observed_at":"2026-08-05T22:28:07.231973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.210316Z","title":"Conditional calibration for false discovery rate control under dependence","venue":null,"work_id":"e6a39b27-2b6d-4f05-baca-9cc0c697c9f6","year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.988356Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:d44eb56a8fc8f698e0972c7eccf5d2c4de6be00cd020f1f1f75b0bae9ba5a211","observation_id":"88869dbd-faf1-4971-8d10-4c9c3641f271","resolution":{"observed_at":"2026-08-05T22:28:07.215124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.194485Z","title":"Adaptive conformal in- ference under distribution shift","venue":null,"work_id":"619b009e-6478-4753-ab54-6567a8a3a3bc","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.993652Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:4d3e3c04a4e5d8d1b28205c8cbde9833376a064de196c072005a69b37cb140f7","observation_id":"b251b007-825d-401d-a10b-9d32183322d0","resolution":{"observed_at":"2026-08-05T22:28:07.199795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.03030","last_updated":"2023-11-08T03:57:25Z","snapshot_observed_at":"2026-08-08T22:15:23.138654Z","submitted_at":"2019-11-08T03:57:41Z","title":"Certified Data Removal from Machine Learning Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.03030","snapshot_observed_at":"2026-08-05T22:28:05.998127Z","title":"Certified data removal from machine learning models","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:05.998127Z"},"links":{"cited_paper":"/paper/1911.03030","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:a8f4c12d5a9028b22d161975ac1e5fee197173e86bf02b0a5a18ad37a07fe798","observation_id":"00e73f4f-b707-4af4-b32f-bf722ddf3c94","resolution":{"observed_at":"2026-08-05T22:28:05.998127Z","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":"2026-08-05T22:28:07.179862Z","title":"Mem- bership inference attacks on deep regression models for neu- roimaging","venue":null,"work_id":"6ae74f7e-b9e4-4c5b-b374-ddbbfa8e1961","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.003358Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:240da2cccfad269e190591eb2d8335cbbbd8df0add15b7f9d85d83690e70c822","observation_id":"7f4390ae-8de1-4e50-9de3-581d90c3e9d1","resolution":{"observed_at":"2026-08-05T22:28:07.184662Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.165400Z","title":"Remind your neural net- work to prevent catastrophic forgetting","venue":null,"work_id":"4f0d7bf6-f633-4994-a132-a7dff3da60d0","year":2020},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.009220Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:368b87022da2a2ab424be587db6fa8fe93d8ca53aec2a593956037f78d3544f2","observation_id":"5ffc0774-4631-4100-a029-f5f1d9795dd8","resolution":{"observed_at":"2026-08-05T22:28:07.169881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.150568Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"41a8cc48-ed85-4e3f-9fca-e24e6613ed2f","year":2016},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.014033Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:fc260b653e0f2892194644ea4a8bd5d284ba462e0fc92a182eb022c241748da9","observation_id":"99420922-4f72-4f83-8ca9-7e9795fd8afd","resolution":{"observed_at":"2026-08-05T22:28:07.155108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.018606Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.018606Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:647ac08b5e4efae09cb78d02d2393e622b010315e6facfa3d4b220f24c86c9a4","observation_id":"fe5adf02-9938-4d28-bc7e-02244ada67b9","resolution":{"observed_at":"2026-08-05T22:28:06.018606Z","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":"2026-08-05T22:28:07.127065Z","title":"Semi-leak: Membership inference attacks against semi-supervised learning","venue":null,"work_id":"a53c9eb0-8f90-4916-8818-ff152e67c0d9","year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.023104Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:4c8857d885e964e8e17546fd51cf0b551dbfcb6b3e58f35ff51194414794e17b","observation_id":"55543104-ee43-4585-8554-ae10951e30eb","resolution":{"observed_at":"2026-08-05T22:28:07.131984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.113247Z","title":"Segmentations-leak: Membership inference attacks and de- fenses in semantic image segmentation","venue":null,"work_id":"52da9576-a704-4bf9-beec-7e78d7a12030","year":2020},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.028295Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:cbf28c04423eb65c078c71d5f0b5fb79015b870a0baaa5fffbfa3606ebd12198","observation_id":"a3468fc7-628a-40d1-b59b-e068dcf74989","resolution":{"observed_at":"2026-08-05T22:28:07.117916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.098764Z","title":"Resolving individuals contributing trace amounts of dna to highly complex mixtures using high-density snp genotyping microarrays","venue":null,"work_id":"53ff3d36-8991-468e-9c9b-083bb48a260c","year":2008},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.032952Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:c04f66cc6dfe7161916a7c73ab6fccdee1f2c71574bc13fbbc6a37a60fa4b9ca","observation_id":"c0f42f5d-fa5f-4582-819b-56fefd40e3bf","resolution":{"observed_at":"2026-08-05T22:28:07.103473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.084809Z","title":"Membership inference at- tacks on machine learning: A survey","venue":null,"work_id":"f6049b4d-897e-4728-aa2e-9bafe6a80036","year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.037792Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:c21a60a5f4c74414fed138f50cefe48f23c96a5f07a7e7d8e9e17ddf70522e91","observation_id":"b1aa4a6f-a443-446b-9f6e-b37b3559b929","resolution":{"observed_at":"2026-08-05T22:28:07.089289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.071362Z","title":"Subpopulation data poisoning attacks","venue":null,"work_id":"1de6c111-03a1-49d6-82d5-d81783a7ed25","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.042508Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:c00d353a8c242915880aaef2111f7b9a3a2a080474e7a11a0c5ef7ecaba5a057","observation_id":"dbee8c9c-6ad4-48c8-a15f-ab85c4c18cac","resolution":{"observed_at":"2026-08-05T22:28:07.075802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.056991Z","title":"False discovery rate con- trol via debiased lasso","venue":null,"work_id":"c5879981-e412-4e35-8677-b372a756ba23","year":2019},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.047177Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:174319086c357691d334fd0135b6ee37ac298c9354bac182ff6a63fe60ce406b","observation_id":"561824fc-2d07-4cf9-9033-25b3e408e3d8","resolution":{"observed_at":"2026-08-05T22:28:07.061856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.040796Z","title":"Segment any- thing","venue":null,"work_id":"069aa268-0a7d-4430-ba7a-51c7bb8c7d28","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.051608Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:227de6a3930aa226eea2f9859b0c0be5f946c45f39b93e48e91f0b6e89bcbdab","observation_id":"8bcc0db3-bc0d-4d31-a2d0-cbb506aca859","resolution":{"observed_at":"2026-08-05T22:28:07.045305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.025869Z","title":"Practical membership inference attacks against large- scale multi-modal models: A pilot study","venue":null,"work_id":"a973aeff-bc25-4988-ae4e-fbc5faa74c9d","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.056049Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:cdfd9bb85b4df5478dbfcba92bb7e39b5279f45212aac0e40f35f316f28d7216","observation_id":"019ab476-9e9e-4cde-b822-584c6b73f987","resolution":{"observed_at":"2026-08-05T22:28:07.031028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16064","last_updated":"2023-11-27T22:05:53Z","snapshot_observed_at":"2026-07-06T16:24:38.375055Z","submitted_at":"2023-09-27T23:11:35Z","title":"Masked Autoencoders are Scalable Learners of Cellular Morphology","version":2},"cited_work":{"arxiv_id":"2309.16064","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.16064","snapshot_observed_at":"2026-08-05T22:28:06.474525Z","title":"Masked Autoencoders are Scalable Learners of Cellular Morphology","venue":"cs.CV","work_id":"d0e62759-e180-4232-95d9-a162294c1b14","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.060334Z"},"links":{"cited_paper":"/paper/2309.16064","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:99e30ffa9d0904669d505381eb26677b1e4fe6678e097dc5626ecb5d273abd04","observation_id":"ca93c055-20fd-454b-b3f1-4dd1d4fbc146","resolution":{"observed_at":"2026-08-05T22:28:06.479727Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:07.010236Z","title":"Cifar-10 (canadian institute for advanced research)","venue":null,"work_id":"95cff5e5-0281-4ed6-b5ea-f72ae346516e","year":2009},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.065287Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:c26a310b7ffa4e23e97a86a6a38fdd18935228e7cdef54ce8cbb5d97fb4c24cf","observation_id":"233b886e-64c4-4128-92f5-0549b261e6fd","resolution":{"observed_at":"2026-08-05T22:28:07.015528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18404","last_updated":"2023-07-08T02:20:29Z","snapshot_observed_at":"2026-07-06T15:34:59.457879Z","submitted_at":"2023-05-28T15:26:10Z","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18404","snapshot_observed_at":"2026-08-05T22:28:06.069255Z","title":"Confor- mal prediction with large language models for multi-choice question answering","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.069255Z"},"links":{"cited_paper":"/paper/2305.18404","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:87f75faa1202317fbe2b390d3fb8b85f178428c26c6e508bcbd8d3ea1bc5b4cc","observation_id":"1abc9b59-ae0a-46da-b15a-39dfb676ee6a","resolution":{"observed_at":"2026-08-05T22:28:06.069255Z","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":"2026-08-05T22:28:06.994127Z","title":"Towards transferable targeted attack","venue":null,"work_id":"06554435-a4a7-400f-b2b6-ff92a8d0f02c","year":2020},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.074338Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:fb19650e0bd35394aa38c07d1ca637fc63f258484b2ee9146dae4986e6410702","observation_id":"37f01cc0-7575-49b4-82b1-3c688f0b8c5d","resolution":{"observed_at":"2026-08-05T22:28:06.999035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.979547Z","title":"Data poisoning attacks against con- formal prediction","venue":null,"work_id":"7b09a1fc-9bd9-49d8-9f30-34aec9f24021","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.078889Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:4059233dedca7020b4310dbc88fbce9628ba03308e9c88c5b138c8ecc963916c","observation_id":"43a894b4-6692-43ee-84e9-4319021eb240","resolution":{"observed_at":"2026-08-05T22:28:06.984008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.11111","last_updated":"2022-08-23T17:52:20Z","snapshot_observed_at":"2026-07-06T13:44:44.960340Z","submitted_at":"2022-08-23T17:52:20Z","title":"Integrative conformal p-values for powerful out-of-distribution testing with labeled outliers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.11111","snapshot_observed_at":"2026-08-05T22:28:06.083480Z","title":"Integra- tive conformal p-values for powerful out-of-distribution test- ing with labeled outliers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.083480Z"},"links":{"cited_paper":"/paper/2208.11111","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:8cb93ef9fb512a15b3b48a82c43cf4ccc627bfe0fe80a90393c823b99a2dd45f","observation_id":"6d2229de-0150-4034-a164-17e49070f698","resolution":{"observed_at":"2026-08-05T22:28:06.083480Z","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":"2026-08-05T22:28:06.965313Z","title":"A pragmatic approach to membership inferences on machine learning models","venue":null,"work_id":"553c33f6-c5d3-4781-8ed2-743003de74e9","year":2020},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.088632Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:7d1dcf3b6d121fbf28230599264136ee3ecacfb1e1f1312126f6593702018399","observation_id":"74b516d4-5d79-44f0-8d57-8bfe75679d48","resolution":{"observed_at":"2026-08-05T22:28:06.969705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.950247Z","title":"Global and simul- taneous hypothesis testing for high-dimensional logistic re- gression models","venue":null,"work_id":"8b939a69-faec-4279-a0e1-d1e821044f75","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.093223Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:0eb447d1ac61b4d750179764b50cdac0ffb25a3b6afebd174640a610ae1111ed","observation_id":"f995a6df-a778-4b65-9900-17e6addf3bae","resolution":{"observed_at":"2026-08-05T22:28:06.955349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.06685","last_updated":"2023-10-25T11:29:17Z","snapshot_observed_at":"2026-08-04T01:44:18.158078Z","submitted_at":"2022-08-13T17:14:55Z","title":"Adaptive novelty detection with false discovery rate guarantee","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.06685","snapshot_observed_at":"2026-08-05T22:28:06.097436Z","title":"Machine learning meets false discovery rate","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.097436Z"},"links":{"cited_paper":"/paper/2208.06685","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:945e9193c1b41fc981d18e7b2142275f7d1cb32f9a6d54cfb2c035a2f999327d","observation_id":"cf48af1b-1f04-45d3-8896-4e997308420c","resolution":{"observed_at":"2026-08-05T22:28:06.097436Z","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":"2026-08-05T22:28:06.934483Z","title":"Membership inference attacks against diffusion models","venue":null,"work_id":"b9116d0a-c80e-4305-932c-38e35dda6bbd","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.102296Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:2e85d1da2ad88bed316b9211addb121614f576cc8d8f3882fd32aac38c03045e","observation_id":"376648bd-669f-439c-80e5-52ddbffca6c5","resolution":{"observed_at":"2026-08-05T22:28:06.939427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.918564Z","title":"A survey on membership inference at- tacks and defenses in machine learning","venue":null,"work_id":"d5c75870-49ff-4de9-9800-6f057d6f279c","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.107459Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:d0e9e55644e2dfbe80db3211afe5e8db7df5de8d406fc5cda0acc1d1eb60fcf5","observation_id":"c089334a-bacf-4b21-a3e5-0417865b4aa2","resolution":{"observed_at":"2026-08-05T22:28:06.923496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.902337Z","title":"Towards understanding and enhancing robustness of deep learning models against malicious unlearning attacks","venue":null,"work_id":"c741ba04-2e89-4f5b-b4b6-8de62d6bdde8","year":1932},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.112525Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:6ff22b816c04a2007e325e05fa5a1663f37fa29336a78dfa9322148df75a2c2e","observation_id":"84ca7d0c-22aa-4103-a764-7300800352d6","resolution":{"observed_at":"2026-08-05T22:28:06.907603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.887841Z","title":"Towards modeling uncertainties of self-explaining neural networks via conformal prediction","venue":null,"work_id":"7e46614e-f945-45db-842e-54d0dbd2f6b1","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.116793Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:c8484548f228da5ce066d51e9768ce4a5fc9f0a238a30cc1873b932dceb405d9","observation_id":"edc85c43-7e5b-446c-bb68-ca6b210cf18d","resolution":{"observed_at":"2026-08-05T22:28:06.892506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.872724Z","title":"On the difficulty of member- ship inference attacks","venue":null,"work_id":"2d19e9ea-61ce-4bc3-ada3-39f105198451","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.121158Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:4b2800fad181a616839c0f6e74fb9930e44849ddc202d8c11c7c6d197e0724b7","observation_id":"3a64d5da-9db6-4427-af45-0683f76dacaa","resolution":{"observed_at":"2026-08-05T22:28:06.877863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.01246","last_updated":"2018-12-14T19:39:43Z","snapshot_observed_at":"2026-08-08T03:39:28.408433Z","submitted_at":"2018-06-04T17:38:42Z","title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.01246","snapshot_observed_at":"2026-08-05T22:28:06.125364Z","title":"Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.125364Z"},"links":{"cited_paper":"/paper/1806.01246","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:bb9d6b6ee0991d1ff6397dfc05ff6c7696ac327ae9924a2b717842ebf45ea784","observation_id":"c8532ef4-0d7b-41a7-8fe6-1b630250263c","resolution":{"observed_at":"2026-08-05T22:28:06.125364Z","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":"2026-08-05T22:28:06.857453Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":"0cff2a7f-53a7-44cb-8f60-3aca5a10f102","year":2018},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.129887Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:4ce33dd5521657298390501a343a03280682cf79931f05ad7aa8a34f27ac7fb8","observation_id":"efb35d8b-812b-4bae-b3a6-d2bcb8793017","resolution":{"observed_at":"2026-08-05T22:28:06.862281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.842826Z","title":"Just how toxic is data poison- ing? a unified benchmark for backdoor and data poisoning attacks","venue":null,"work_id":"d7c5e1df-2039-40e6-8d26-0c6acf8d8fca","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.134359Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:0e2093f3e1a92437dff72ec5f192be6b9d6b7f2aa004e1dc915965289dd43945","observation_id":"e6ff639c-b7b7-4878-b45f-6e37ef03129f","resolution":{"observed_at":"2026-08-05T22:28:06.847581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.826792Z","title":"Member- ship inference attacks are easier on difficult problems","venue":null,"work_id":"cc926f7e-4474-41d2-80a3-57e64c974150","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.138847Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:c5488b46f5f0f99e14e46068471d05461e471abb9247643b4df7f7e7a3196ce6","observation_id":"400999e0-a362-4400-a82c-429877153c7d","resolution":{"observed_at":"2026-08-05T22:28:06.831871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.809496Z","title":"Membership pri- vacy for machine learning models through knowledge trans- fer","venue":null,"work_id":"c760e744-85cf-4255-846f-e3b528064000","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.143622Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:935f2e23abb0f998eef124026a8165df7f96cab0cf43f29feff6ddcfe5ca7e5d","observation_id":"f826a51c-cad2-45bc-8368-0497138433c2","resolution":{"observed_at":"2026-08-05T22:28:06.816100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.793706Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":"6a351879-70de-48b8-9052-a4abc8460ab8","year":2017},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.147941Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:697869a56d8a52a33f08d46d4ce6f13b6c971109d7e8382cb1678418f96f2455","observation_id":"b8edd97d-7b4a-4ea0-8e25-457818ddc1b4","resolution":{"observed_at":"2026-08-05T22:28:06.798682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-07-06T03:53:32.549552Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-05T22:28:06.152577Z","title":"Very deep convo- lutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.152577Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:ee90b3bf23104fa22c6aa9976995ade71eeaacf696ecbab012f71e7ad26aa9ae","observation_id":"837bdce3-1d05-4473-ad88-d84958f5fc3f","resolution":{"observed_at":"2026-08-05T22:28:06.152577Z","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":"2026-08-05T22:28:06.157168Z","title":"Systematic evaluation of pri- vacy risks of machine learning models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.157168Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:067e31ae48cb49c644c4abfc3075c944314f2aad1104b23834d5282e719ba93b","observation_id":"cb904e27-94ba-4a60-b7d0-284f5eea276b","resolution":{"observed_at":"2026-08-05T22:28:06.157168Z","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":"2026-08-05T22:28:06.768165Z","title":"A taxonomy and terminology of adversarial machine learning","venue":null,"work_id":"a7f428d8-a352-47ee-9a8e-5f9d1a1016eb","year":2019},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.161908Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:32538e405fc825f4d2a68c0b1a4ffcebb1f2b2b60495a417cf44a2dc4f56f424","observation_id":"ceb65a8a-995e-41c6-bc31-41a50910bcd2","resolution":{"observed_at":"2026-08-05T22:28:06.773414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.753373Z","title":"Unrolling sgd: Understanding factors in- fluencing machine unlearning","venue":null,"work_id":"d9007862-7abb-4d48-9d7f-0404e3b2cb43","year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.166429Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:8c35e321f1fd0d744aaa78941b2fa1c8ca5100deb93f1ab020ea1dc2f89779d4","observation_id":"c645b008-aedd-435d-a7db-1fb1db300ad6","resolution":{"observed_at":"2026-08-05T22:28:06.758497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.738296Z","title":"Conformal prediction under covariate shift","venue":null,"work_id":"19bdec81-8dc2-4dc2-ad18-430a27d25e86","year":2019},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.170764Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:f6a21484b56626f7450763e13a668c222b21a96c4bcc4e82f991effac9c21e83","observation_id":"86ee7c69-4952-413d-bdb7-5440510dc9e6","resolution":{"observed_at":"2026-08-05T22:28:06.743913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.721846Z","title":"Algorithmic learning in a random world","venue":null,"work_id":"546156e6-e1f2-4cbc-af65-3fa0b8cdeafc","year":2005},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.175552Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:bc02979ba8c690215793a481567bf53b00002b43d13a7561a2522ee831a05690","observation_id":"191ff526-5f5c-41c8-9ab6-0ba7ef902b84","resolution":{"observed_at":"2026-08-05T22:28:06.727276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.705513Z","title":"Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","venue":null,"work_id":"c06fba44-2341-4b03-b9ea-67f804c71388","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.179777Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:849c87d82505b3c6a12210236ba9c8abb830a8f01a14642895a1b6bed022468e","observation_id":"1cb10836-96ad-453a-8b5c-41083876e2f4","resolution":{"observed_at":"2026-08-05T22:28:06.710595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.03247","last_updated":"2024-07-03T16:23:41Z","snapshot_observed_at":"2026-08-10T06:50:57.559919Z","submitted_at":"2024-07-03T16:23:41Z","title":"Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning","version":1},"cited_work":{"arxiv_id":"2407.03247","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.03247","snapshot_observed_at":"2026-08-05T22:28:06.379291Z","title":"Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning","venue":"cs.DC","work_id":"56445de7-5374-420f-8b96-0a0407a47ab5","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.184448Z"},"links":{"cited_paper":"/paper/2407.03247","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:86ba96902b70f60dc32d5a66bd1cfe574dae8a1e058dcd95718a3cdca1697a27","observation_id":"42f069a1-d5f8-43ee-8251-c34724f61abf","resolution":{"observed_at":"2026-08-05T22:28:06.384367Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.690065Z","title":"Transferable normalization: Towards im- proving transferability of deep neural networks","venue":null,"work_id":"f69324fb-f9f7-43c3-b359-41ec042bdc61","year":2019},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.189025Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:76e0a81a06b488da8fa352dbdcf2b483103bee4e86e8ff78ac49e6eace347b29","observation_id":"1fc230cd-1464-4e5e-930f-0b0e2fd28d4a","resolution":{"observed_at":"2026-08-05T22:28:06.695409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.673557Z","title":"Continual learning with lifelong vision trans- former","venue":null,"work_id":"2021ba15-b119-49e5-ba6a-32d7503244ef","year":null},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.193345Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:9869ebaf528c3a38b668e1a995177b1f20223458e5572619de245d01a6e5f8b8","observation_id":"383a5728-9806-43a8-8b5b-64a8037df65f","resolution":{"observed_at":"2026-08-05T22:28:06.678590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.11577","last_updated":"2023-08-07T12:33:20Z","snapshot_observed_at":"2026-08-10T06:56:08.280195Z","submitted_at":"2021-08-26T04:42:24Z","title":"Machine Unlearning of Features and Labels","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.11577","snapshot_observed_at":"2026-08-05T22:28:06.197869Z","title":"Machine unlearning of features and la- bels","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.197869Z"},"links":{"cited_paper":"/paper/2108.11577","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:ab8854c3793695176378e80d27d6688855b468c1a729155818509781fd62d289","observation_id":"46cb6d27-b84a-4589-889c-99bfe735ecdb","resolution":{"observed_at":"2026-08-05T22:28:06.197869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.08440","last_updated":"2022-04-11T09:23:43Z","snapshot_observed_at":"2026-07-06T12:09:00.789234Z","submitted_at":"2021-11-15T12:32:20Z","title":"On the Importance of Difficulty Calibration in Membership Inference Attacks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.08440","snapshot_observed_at":"2026-08-05T22:28:06.202502Z","title":"On the importance of difficulty calibra- tion in membership inference attacks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.202502Z"},"links":{"cited_paper":"/paper/2111.08440","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:860c8736b3b63b7c8ac9097b186aac24a6386e025ed2fa287c12aaeea9410117","observation_id":"fd6dfb77-44ef-4e9a-8f0e-106c066968d4","resolution":{"observed_at":"2026-08-05T22:28:06.202502Z","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":"2026-08-05T22:28:06.657991Z","title":"Membership inference attacks against medical databases","venue":null,"work_id":"8a412d6c-bdb6-487f-b65a-3ea84c2516fb","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.206874Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:12faeaef8ad8d8dc4c5844704020c7769ae1def6c0a4fbea0aad6fdab7dbaf33","observation_id":"41d124ec-0a47-46fa-ac47-7a8a0117f14b","resolution":{"observed_at":"2026-08-05T22:28:06.663217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.642247Z","title":"Enhanced membership inference attacks against machine learning models","venue":null,"work_id":"ea94c37e-557a-4832-b0f1-9e810f89b6e6","year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.212024Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:9b9dc6ef6a8ad87518f0684d9c688fefb8064cfad7e679e4e50a73c701588aee","observation_id":"0a0a4222-c951-4d0c-95dd-de7f1f1345e6","resolution":{"observed_at":"2026-08-05T22:28:06.647994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.216361Z","title":"Privacy risk in machine learning: Analyzing the connection to overfitting","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.216361Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:77e35728a6f48742d56824484e4807dab1c45d963d83e1e2dc0248c287c406bf","observation_id":"32840a9d-9a37-482e-9abc-671568e43904","resolution":{"observed_at":"2026-08-05T22:28:06.216361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.09165","last_updated":"2024-07-12T10:59:44Z","snapshot_observed_at":"2026-08-09T20:28:19.751479Z","submitted_at":"2024-07-12T10:59:44Z","title":"Robust Yet Efficient Conformal Prediction Sets","version":1},"cited_work":{"arxiv_id":"2407.09165","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.09165","snapshot_observed_at":"2026-08-05T22:28:06.326227Z","title":"Robust Yet Efficient Conformal Prediction Sets","venue":"cs.LG","work_id":"183b4add-2e89-4bf1-87a7-78a4521fbcbf","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.220767Z"},"links":{"cited_paper":"/paper/2407.09165","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:2583da4189c02422d5e9115c0a860659fa680f234d7b57cadc727cc2a31d8fac","observation_id":"24f2f2cc-d2a7-4729-913b-232c0b18b4d3","resolution":{"observed_at":"2026-08-05T22:28:06.333531Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03262","last_updated":"2024-06-12T09:02:47Z","snapshot_observed_at":"2026-08-09T01:42:01.147623Z","submitted_at":"2023-12-06T03:18:49Z","title":"Low-Cost High-Power Membership Inference Attacks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.03262","snapshot_observed_at":"2026-08-05T22:28:06.225473Z","title":"Low-cost high-power membership inference by boosting relativity","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.225473Z"},"links":{"cited_paper":"/paper/2312.03262","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:7bc789f1276a76e51e23e56dcff696ee6b67b146046e0bc42020c0d48c2700a3","observation_id":"673f4f04-707b-4b77-9841-bd393f9a8fc4","resolution":{"observed_at":"2026-08-05T22:28:06.225473Z","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":"2026-08-05T22:28:06.617179Z","title":"Label-only membership inference attacks and defenses in semantic segmentation models","venue":null,"work_id":"08f7c80d-d0f1-4a12-b9d5-9c77c462cff8","year":2022},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.230132Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:c35d8def2da11fb089aa9eb7c564210c9c04b18332b8daacf1d6c80e771291b7","observation_id":"e5eb248f-2d97-41e2-bc6f-f34fd2fc17f5","resolution":{"observed_at":"2026-08-05T22:28:06.622129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.602670Z","title":"Membership inference attacks against recommender systems","venue":null,"work_id":"0d929f75-29ac-4687-b512-c322a3205e50","year":2021},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.234470Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:449400b4c0a8a86e1c823ad58c2521ae26110b87cabf219daedbe33df597f0a0","observation_id":"ffd8b2dd-801b-4174-96ef-77f242e9fd6b","resolution":{"observed_at":"2026-08-05T22:28:06.607406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.586941Z","title":"Generated distributions are all you need for membership inference attacks against generative models","venue":null,"work_id":"16271bc6-8bc7-4876-b186-a100a7944131","year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.238830Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:37f7d263c007910ddb4f94b5205fc5e93c6d492fa4d80e5c53d7bc0127a02c00","observation_id":"4bb8f430-3827-48f4-a535-a69bc52f5ae8","resolution":{"observed_at":"2026-08-05T22:28:06.591885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.14513","last_updated":"2024-09-24T17:48:58Z","snapshot_observed_at":"2026-08-10T00:30:27.118730Z","submitted_at":"2024-09-22T16:18:14Z","title":"Order of Magnitude Speedups for LLM Membership Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.14513","snapshot_observed_at":"2026-08-05T22:28:06.243263Z","title":"Order of magnitude speedups for llm membership inference","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.243263Z"},"links":{"cited_paper":"/paper/2409.14513","citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:1ba0e613e728aa12a3ea7629045e1202ce4ef178b603baeef79c4efaf6d1aa3a","observation_id":"c85f70f4-a362-4bab-9c91-77d6a0a5edc0","resolution":{"observed_at":"2026-08-05T22:28:06.243263Z","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":"2026-08-05T22:28:06.571634Z","title":"Static and sequential malicious attacks in the context of selective forgetting","venue":null,"work_id":"3773a65e-1153-45b2-8507-806d06e8377b","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.248308Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:96d8756fc99b32e96ceaf55b64efbb9877ae2b452043f66e37ef0a4f180f0e79","observation_id":"dc4c816c-ec68-4c24-af64-34174c5d173f","resolution":{"observed_at":"2026-08-05T22:28:06.576684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.555484Z","title":"Blur interpolation transformer for real-world motion from blur","venue":null,"work_id":"d8f7a38e-8251-4a9b-9028-1867ea1ec900","year":2023},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.252953Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:af3ce8bc89bd37034590fd5697b11b3086e833470eb9bc0bbb437503d4122dcd","observation_id":"b364eb63-eb8b-49da-8bb4-62956acb4cc7","resolution":{"observed_at":"2026-08-05T22:28:06.560969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T22:28:06.257168Z","title":"Conditional prompt learning for vision-language mod- els","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-05T22:28:06.257168Z"},"links":{"citing_paper":"/paper/2508.07066"},"observation_digest":"sha256:fc6cc5988f3910b33b9ee4ef48dfa0c6c1485b5fef2a9c0d582d8b0946cf1052","observation_id":"11e9111f-5d08-4b67-93a4-afcf4b7b6b07","resolution":{"observed_at":"2026-08-05T22:28:06.257168Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.07066","last_updated":"2025-08-09T18:14:50Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-10T01:40:38.456537Z","submitted_at":"2025-08-09T18:14:50Z","title":"Membership Inference Attacks with False Discovery Rate Control"},"reference_resolution":{"displayed":85,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":4,"verified_fuzzy":60},"total_outbound_references":85},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 85 of 85 outbound references and 0 inbound Pith citation observations for arXiv:2508.07066."}