{"as_of":"2026-08-10T12:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:efc74d809a921b1abf0f55451bb6ae9a2f5b5a1378ea59a08922096154e018d9","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T16:22:55.084553Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"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/2508.18671/citation-record","integrity":"/paper/2508.18671/integrity","json":"/paper/2508.18671/citation-record.json","paper":"/paper/2508.18671"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:22:55.444351Z","title":"B., MIRONOV, I., T ALWAR, K., AND ZHANG , L","venue":null,"work_id":"727e2783-af90-46a3-9393-aeb01368b643","year":2016},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:54.960268Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:5405542afc4a627f53f7d13e294b7ed9fa1675efc337879feea1af7f88c34850","observation_id":"9f663c6a-eaac-4a1c-8d29-36176958e021","resolution":{"observed_at":"2026-08-05T16:22:55.447955Z","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":"2026-08-05T16:22:55.434315Z","title":"Evaluations of machine learning privacy defenses are misleading","venue":null,"work_id":"cfac7be5-b976-49a8-a7e5-1ec4cb74a671","year":2024},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:54.965923Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:d48b64c388ee016bf31c979e686cdb0356e6af29b9b33394b3152efb6db9ce40","observation_id":"d85d257f-c034-4d36-8eec-acaef26bb55e","resolution":{"observed_at":"2026-08-05T16:22:55.437918Z","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":"2026-08-05T16:22:55.423880Z","title":"Evaluations of machine learning privacy defenses are misleading","venue":null,"work_id":"6fb3488b-67a1-4e15-8ad5-8ca2db3ee4b0","year":2024},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:54.970701Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:e6533c007c101a12b12b8068713865327212b96ddfb7c89ce7a17ad9d795396e","observation_id":"0d217bcb-c3ba-4c3b-99dc-c4cb96aabc8b","resolution":{"observed_at":"2026-08-05T16:22:55.427423Z","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":"2026-08-05T16:22:55.413792Z","title":"A., JIA, H., T RAVERS , A., Z HANG , B., L IE, D., AND PAPERNOT , N","venue":null,"work_id":"ec6ef298-4896-411d-a9a4-34196a157158","year":2021},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:54.976232Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:5aa41160068ffc6c3cfd5142321c849cae8d335d812c4e247eff5968d2b7fb1b","observation_id":"c3a4f816-19d5-4bf5-8af0-28b4dcfd3d2c","resolution":{"observed_at":"2026-08-05T16:22:55.417182Z","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":"2026-08-05T16:22:55.403339Z","title":"California consumer privacy act of 2018, 2018","venue":null,"work_id":"144a0a47-c795-41fb-bab2-d8f5fd043430","year":2018},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:54.980898Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:3aeca8e05722a98d043393ebef2e42f5b4b7820df5734deec1f9b263dcea3619","observation_id":"d24e1ba0-89ad-4ee5-8b23-4294d1b8940c","resolution":{"observed_at":"2026-08-05T16:22:55.407021Z","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":"2026-08-05T16:22:55.392836Z","title":"Towards making systems forget with machine unlearning","venue":null,"work_id":"db594d7d-b71d-460c-ad0f-09048f33890f","year":2015},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:54.986311Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:6b31e8105f446ab722db7a26eb7b524967e3fc93e613082f0e1c786db5f8a9a5","observation_id":"09de7c6a-cbf2-45ed-9825-46bb64044b34","resolution":{"observed_at":"2026-08-05T16:22:55.396622Z","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":"2026-08-05T16:22:55.382760Z","title":"Membership inference attacks from first principles","venue":null,"work_id":"300bd016-4c18-4e1e-8797-76cbe4ae6992","year":2022},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:54.991270Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:d02f67b2c83710f0a32d36dcf357200b4c55ef6ba24ef9b5a49642039f142d62","observation_id":"b1ed5bc0-2441-4d6c-af48-4b961ae0383f","resolution":{"observed_at":"2026-08-05T16:22:55.386515Z","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":"2026-08-05T16:22:55.372803Z","title":"The privacy onion effect: Memorization is relative","venue":null,"work_id":"b143dc36-adcb-40e3-b12b-31150a419831","year":2022},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:54.996329Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:2cc3ba974790efc199e5754a18fc4f93004bbaf03c434c304b77b9e3bf163a11","observation_id":"491bc8cd-4c77-4d4b-8efb-7c9dea59077a","resolution":{"observed_at":"2026-08-05T16:22:55.376331Z","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":"2026-08-05T16:22:55.362531Z","title":"When machine unlearning jeopardizes privacy","venue":null,"work_id":"5e10a54d-0786-4de8-b4d8-572f9ffd644d","year":2021},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.000038Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:8929efa927f98d3d6fb51b0f600103108d89270af0a8df4b58154acf6b0c5377","observation_id":"4c923587-961c-4ff1-9594-53c0aada1352","resolution":{"observed_at":"2026-08-05T16:22:55.366090Z","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":"2026-08-05T16:22:55.352961Z","title":"Differential privacy: A survey of results","venue":null,"work_id":"68d2f51f-12dd-470e-b217-aa4d7035efdd","year":2008},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.004292Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:2df9346436cedb42d3669e3ef85b478bd766d5999dccc7f007742d6700124524","observation_id":"06aa997a-34f8-4b90-a622-64eb6cf0f4b3","resolution":{"observed_at":"2026-08-05T16:22:55.356498Z","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":"2026-08-05T16:22:55.343206Z","title":"The algorithmic foundations of differential privacy","venue":null,"work_id":"b4a2746d-9047-40bb-9731-4f285d2ef593","year":2014},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.008270Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:017825064958642101ecd89e3957c5a9abfd1f950da9e96c016f08c759693502","observation_id":"d33f53b0-cff6-45fa-adff-e5586aa727e8","resolution":{"observed_at":"2026-08-05T16:22:55.346637Z","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":"2026-08-05T16:22:55.333701Z","title":"Regulation (EU) 2016/679 of the European Parliament and of the Council, 2016","venue":null,"work_id":"eab74b3c-6eb3-43ae-b64a-188180a07b9c","year":2016},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.011869Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:7329efe22f27c4278a2d876686677829dd06a92fb2b82d48d04c56d127b2ab31","observation_id":"d9e885e9-9310-46fe-a959-fc5ae7f09cbd","resolution":{"observed_at":"2026-08-05T16:22:55.337008Z","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":"2026-08-05T16:22:55.323725Z","title":"Salun: Empowering machine unlearning via gradient-based weight saliency in both image classification and generation","venue":null,"work_id":"81078d91-f70b-46f8-a386-fe0ee9bbbf12","year":2024},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.014891Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:182d57efaddd2bd8b85e03958889bbcd7633304f259b42d5bc68c5866be96ad4","observation_id":"3142c421-ccd3-4197-b01c-2cc680173c30","resolution":{"observed_at":"2026-08-05T16:22:55.327607Z","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":"2026-08-05T16:22:55.314502Z","title":"Fisher information as a measure of privacy: Preserving privacy of households with smart meters using batteries","venue":null,"work_id":"424b2235-737e-4133-8381-09c454bd13ae","year":2017},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.018247Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:c19447bbad06992b633961ad693e9f23961213531b08d84a3a227cebfdaa35d2","observation_id":"e5bc753e-e2bf-4f05-963f-ba92cc13a757","resolution":{"observed_at":"2026-08-05T16:22:55.317824Z","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":"2026-08-05T16:22:55.304818Z","title":"Fast machine unlearning without retraining through selective synaptic dampening","venue":null,"work_id":"185dd482-0b27-4f52-8d21-faa2f120668e","year":2024},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.021188Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:0241e04591399ea8023cca77092639ffb7d41badbd6059ce8a41ec99cb3e12e4","observation_id":"5a838197-f10d-4fad-bead-255c6bb33dfb","resolution":{"observed_at":"2026-08-05T16:22:55.308122Z","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":"2026-08-05T16:22:55.294892Z","title":"Eternal sunshine of the spotless net: Selective forgetting in deep networks","venue":null,"work_id":"914443c5-235a-4e59-ab77-24c458d118cd","year":2020},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.024400Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:02c93c8b5b15f88fe17ffb41fcab17493f5c03af2f41cfefa843e402b20c093b","observation_id":"dbb6ce9f-1660-4fe5-8deb-8d61c7028f07","resolution":{"observed_at":"2026-08-05T16:22:55.298495Z","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":"2026-08-05T16:22:55.284580Z","title":"Demo: Ft-privacyscore: Personal- ized privacy scoring service for machine learning participation","venue":null,"work_id":"9075cf64-e81a-437a-b441-6a68b0061120","year":2024},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.028208Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:8b888e4db5c6257113b013787837c22d19e4d2ed63f231171012191dced212b5","observation_id":"cdbbb6d7-e18c-47f7-8123-c91ab4d4fc6d","resolution":{"observed_at":"2026-08-05T16:22:55.288423Z","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":"2507.18365","last_updated":"2025-09-06T19:57:14Z","snapshot_observed_at":"2026-08-06T14:30:45.750838Z","submitted_at":"2025-07-24T12:46:30Z","title":"RecPS: Privacy Risk Scoring for Recommender Systems","version":4},"cited_work":{"arxiv_id":"2507.18365","doi":null,"metadata_source":"pith","pith_arxiv_id":"2507.18365","snapshot_observed_at":"2026-08-05T16:22:55.134619Z","title":"RecPS: Privacy Risk Scoring for Recommender Systems","venue":"cs.IR","work_id":"dbcdfe9b-6d3d-47a1-8ec8-d87d7b5459d8","year":2025},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.031398Z"},"links":{"cited_paper":"/paper/2507.18365","citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:1486e18c15744cd4f1a7cc831fae099c6b7864a0b7a69cbe7ec81130ac23818e","observation_id":"e0dd6449-7f81-4ff5-97c3-2ca36cb2e696","resolution":{"observed_at":"2026-08-05T16:22:55.140664Z","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":"2026-08-05T16:22:55.274778Z","title":"Auditing differentially private machine learning: How private is private sgd? Advances in Neural Information Processing Systems 33 (2020), 22205–22216","venue":null,"work_id":"136d27f5-56c0-43bb-b6dc-263fc179877b","year":2020},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.034895Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:0ea08d8d305e6514305668477f24b5d08abc9fc7a4b4d0894f1b8e530dc3390b","observation_id":"fef43abc-0ddf-46ab-ba2c-73a3cd0f2c7c","resolution":{"observed_at":"2026-08-05T16:22:55.278410Z","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":"2026-08-05T16:22:55.265092Z","title":"The composition theorem for differential privacy","venue":null,"work_id":"acbebca1-9e99-429a-98ee-8f6dc744aa1a","year":2015},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.038962Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:8f9dae29b9ae069aa07440e7d81743f079e517dc70432241bccc8f11b219a8f2","observation_id":"f7e68696-5eeb-4a3c-9948-73685f6d11d3","resolution":{"observed_at":"2026-08-05T16:22:55.268516Z","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":"2026-08-05T16:22:55.255720Z","title":"C., A FROZ , S., M ILLER , B., SHANKAR , V., B ACHWANI , R., J OSEPH , A","venue":null,"work_id":"e6f6b9e1-aa6d-4fe4-a14e-ce09352b2dda","year":2015},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.042196Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:7b797ab275901df7df89724e8335bcf6e96b0c573182804bc2104382d3d976b4","observation_id":"8f262878-c02f-40bc-b05f-71ee373f1add","resolution":{"observed_at":"2026-08-05T16:22:55.259117Z","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":"2026-08-05T16:22:55.245659Z","title":"Z., AND MALOOF , M","venue":null,"work_id":"c607993f-a592-4388-b238-ded257a168df","year":2006},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.046179Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:cc21e41af0789a84187449beddb3a369953cf14708430aaa30a2ec8b9acfc4c8","observation_id":"5ebb6cd1-d519-42b7-aebd-df22470fb3dc","resolution":{"observed_at":"2026-08-05T16:22:55.249265Z","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":"2026-08-05T16:22:55.235507Z","title":"M., S ALMAN , H., AND M ˛ ADRY, A","venue":null,"work_id":"adbae16c-69c1-4b22-b979-02d33a8cae72","year":2023},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.049342Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:740bc4f87475a6b2bdf6a6fecc1ae08f371b81047dea9c25564c9a887a2a64fb","observation_id":"3a3924cc-49f6-466a-ae4b-ae32cfd92da1","resolution":{"observed_at":"2026-08-05T16:22:55.239183Z","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":"2026-08-05T16:22:55.225017Z","title":"Membership inference attacks against language models via neighbourhood comparison","venue":null,"work_id":"f5990000-b866-4873-802a-7559f23079be","year":2023},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.052820Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:a2ebf5ee104680d18ea3105b0d6fe30d700772c20f76c9650689540c37efaa31","observation_id":"d373d187-d33b-4c33-a395-c07c3bd05d7d","resolution":{"observed_at":"2026-08-05T16:22:55.228751Z","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":"2026-08-05T16:22:55.213890Z","title":"Tight auditing of differen- tially private machine learning","venue":null,"work_id":"c6442099-7110-4436-8c7b-3b20a1e745b7","year":2023},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.056255Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:73dd90f130890d9713e7c8b9449c0beb77b908f11aa4c34d831e8427d3c79eae","observation_id":"8b073716-1e9b-4689-9397-727364fbaf60","resolution":{"observed_at":"2026-08-05T16:22:55.217485Z","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":"2209.02299","last_updated":"2024-09-17T11:55:58Z","snapshot_observed_at":"2026-08-02T02:19:01.218373Z","submitted_at":"2022-09-06T08:51:53Z","title":"A Survey of Machine Unlearning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.02299","snapshot_observed_at":"2026-08-05T16:22:55.059845Z","title":"T., H UYNH , T","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.059845Z"},"links":{"cited_paper":"/paper/2209.02299","citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:8fc9526769d953f861f3959e3014f6201a7849dc0f263d4450a7f70d6ae776af","observation_id":"d655cced-50ce-4684-916d-9bd71fc31f0f","resolution":{"observed_at":"2026-08-05T16:22:55.059845Z","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":"2026-08-05T16:22:55.203607Z","title":"Personal Information Protection and Elec- tronic Documents Act, 2000","venue":null,"work_id":"1bedccd2-6c8e-4e05-be3b-7982ecb3e780","year":2000},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.063518Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:26ce581d51d64963a2cf1184ec3bc9731bdfe464b949002f9c90d71705bb33da","observation_id":"49f78488-6821-4757-8013-2ac401056277","resolution":{"observed_at":"2026-08-05T16:22:55.207143Z","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":"2026-08-05T16:22:55.192461Z","title":"Privacy auditing with one (1) training run","venue":null,"work_id":"6d8ec0b9-c77e-4d92-b530-d30426bb4ace","year":2023},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.067036Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:a976a0aedddb0269a335d9879d39d532c03648707f905c789cfe6589558a3d22","observation_id":"a23d3d47-04cb-4b7a-a876-c25100585e1a","resolution":{"observed_at":"2026-08-05T16:22:55.196427Z","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":"2026-08-05T16:22:55.181454Z","title":"Privacy auditing with one (1) training run","venue":null,"work_id":"537ff167-649c-4671-b43d-8a3eb1a7d799","year":2024},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.070298Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:1ac0f7071e1d95b5aaefa69757c4a2ffa2ffa52faf1455fafc8a861b286ee1a7","observation_id":"7af0df3b-49c3-4254-9fed-89016fc945b0","resolution":{"observed_at":"2026-08-05T16:22:55.185071Z","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":"2202.12219","last_updated":"2022-03-28T17:10:52Z","snapshot_observed_at":"2026-07-06T12:41:22.635071Z","submitted_at":"2022-02-24T17:31:08Z","title":"Debugging Differential Privacy: A Case Study for Privacy Auditing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.12219","snapshot_observed_at":"2026-08-05T16:22:55.073521Z","title":"Debugging differential privacy: A case study for privacy auditing","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.073521Z"},"links":{"cited_paper":"/paper/2202.12219","citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:9354ad53a13db8088bed614d91ba765e7baf1ce3ff5c81df0da5a4cdf57967f8","observation_id":"dca5b1f3-ef37-47be-b276-e7d16e92a553","resolution":{"observed_at":"2026-08-05T16:22:55.073521Z","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":"2026-08-05T16:22:55.170606Z","title":null,"venue":null,"work_id":"f2ce4f77-06a2-44d0-9c98-997418e72b40","year":2023},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.077650Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:024d185f6735f7b5c207584444f59f8decd256ea34148cd207b291e014653422","observation_id":"5f3f64d1-a1f1-4d61-a7e3-cc6c00362d93","resolution":{"observed_at":"2026-08-05T16:22:55.174140Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-05T16:22:55.159547Z","title":"Machine unlearning: Solutions and challenges","venue":null,"work_id":"27b1f0c2-73e0-479a-9bfa-69c907f6ab1e","year":2024},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.081438Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:7a609cdb749815df52fdebb17f2bb553fd4e94bcc5787b9718e4a968abc4c675","observation_id":"792d93bc-84ca-4558-90b3-5651399db3bd","resolution":{"observed_at":"2026-08-05T16:22:55.163422Z","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":"2026-08-05T16:22:55.148678Z","title":"privacy onion effect","venue":null,"work_id":"eeee8df4-c5a3-45de-9920-7fbf5d2f41a7","year":2024},"citing_paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T16:22:55.084553Z"},"links":{"citing_paper":"/paper/2508.18671"},"observation_digest":"sha256:18acac0604dd4a1386a4f4f8cd2106340cef2b316e476c67fca84bef0f0354a3","observation_id":"c48833a5-adc5-402c-aaeb-151d2f22a822","resolution":{"observed_at":"2026-08-05T16:22:55.152239Z","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"}}],"paper":{"arxiv_id":"2508.18671","last_updated":"2025-08-26T04:29:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T16:22:54.356910Z","submitted_at":"2025-08-26T04:29:33Z","title":"Auditing Approximate Machine Unlearning for Differentially Private Models"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":1,"verified_fuzzy":29},"total_outbound_references":33},"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 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2508.18671."}