{"as_of":"2026-08-19T06:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e0193893b00e8befb6a7307849b9474b0c7b91a63d9028c13b092316d376694b","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T17:47:14.660884Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2507.20573/citation-record","integrity":"/paper/2507.20573/integrity","json":"/paper/2507.20573/citation-record.json","paper":"/paper/2507.20573"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:47:15.161299Z","title":"https : / / www","venue":null,"work_id":"d7509584-627b-49c5-b145-43f62dc012f4","year":null},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.511404Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:60c7dfae5471e4093551ea70c16a1bbc340fe354c8512d913268373bf7095b87","observation_id":"93ffa154-8140-4af4-86a2-e007878ae329","resolution":{"observed_at":"2026-08-15T17:47:15.164800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.151848Z","title":"Nonparametric estimation and inference about the overlap of two distributions","venue":null,"work_id":"2a80a7e3-0e2d-425f-9e17-2dfaf405f9d1","year":2012},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.515283Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:fe161d63de87cf1c8af0ac5580e73a7a2d4b6bede04cf1d2bd97ec30769f549a","observation_id":"3f024f5f-b85d-4c37-93df-2aa6945151a3","resolution":{"observed_at":"2026-08-15T17:47:15.155266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.141873Z","title":"Membership inference at- tacks and defenses in federated learning: A survey","venue":null,"work_id":"a3b63f26-1a1f-4ed2-a6ea-72d0653b0931","year":2025},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.518827Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:ad7f49c9291d60bf5118ca71d78c9ae698d06ea8fcbc9455811ee1fdfdb500f8","observation_id":"08390ad7-67dd-493e-b920-88f6bb89dfdd","resolution":{"observed_at":"2026-08-15T17:47:15.145190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.132357Z","title":"Rmr: A relative membership risk measure for machine learning mod- els","venue":null,"work_id":"b4cd6ef2-9279-4032-b3bb-75f0fd6f92e7","year":2025},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.522451Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:0b27769ed197daf187e20ff8480860ce24f3bc221c6ebb674513072f73148a34","observation_id":"0118d6d0-cca7-4976-9cd4-545b9bde48d4","resolution":{"observed_at":"2026-08-15T17:47:15.135298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.123737Z","title":"Recon- struction attacks on machine unlearning: Simple mod- els are vulnerable","venue":null,"work_id":"831d1a64-27d4-4376-ab6e-5b356aa82d88","year":2025},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.526293Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:0d6553b3cd70f3664fba79f005ac253b9bb773c1e0bf93dfffefcaed01ce122c","observation_id":"a6ca1b5c-7104-4d96-87a8-6750f27101a4","resolution":{"observed_at":"2026-08-15T17:47:15.126626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.114935Z","title":"Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot","venue":null,"work_id":"193a6735-f63a-4409-be57-0d82cfedded1","year":2021},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.529766Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:8180ac3aa1f7c7e69e8e2b595cffad79c6e2cd4518657955800e330e022f68d9","observation_id":"3b9aec79-97bf-4e17-a0f3-3175a8c2aa7e","resolution":{"observed_at":"2026-08-15T17:47:15.117901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.105652Z","title":"Member- ship inference attacks from first principles","venue":null,"work_id":"7f44a626-0b1d-46e6-9fc3-592dda48027b","year":2022},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.533303Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:914fd5dd679d248ee5788c4f71da13bb6b3e3c9fb3084591579cd08072953af8","observation_id":"5e59ec03-191e-4879-b99d-89eaf056169e","resolution":{"observed_at":"2026-08-15T17:47:15.108922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.095126Z","title":"Boundary unlearning: Rapid forget- ting of deep networks via shifting the decision bound- ary","venue":null,"work_id":"07320075-2e12-446a-9d12-829d290d916c","year":2023},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.537034Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:0ec70143c1869dfde3b60958bf6d0f7fd61f11de05012679ea906bed43c7f1cd","observation_id":"13c0efb4-8e56-458e-a358-46e852f388c5","resolution":{"observed_at":"2026-08-15T17:47:15.098991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.085189Z","title":"When machine unlearning jeopardizes privacy","venue":null,"work_id":"a9cb63ec-4bcb-4752-a213-f3077e807e6b","year":2021},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.540490Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:fd570c9af5ab25f950dce20e76e64300b6d517201fb3168cc748d060de9db9e7","observation_id":"071c0adb-6e63-49ba-8552-fba30f14d9c4","resolution":{"observed_at":"2026-08-15T17:47:15.088594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.074954Z","title":"Chundawat, Ayush K","venue":null,"work_id":"2f99dff2-15f9-4b43-a9a4-881d4559f56b","year":2023},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.543808Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:cead6915d25766504ebbd73b9abbfd895f952445a1cf53a56fe1aed5cb84c2a4","observation_id":"58936e1e-c828-4146-af3a-400843b1f3f4","resolution":{"observed_at":"2026-08-15T17:47:15.078646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.064569Z","title":"Arcface: Additive angular margin loss for deep face recognition","venue":null,"work_id":"ae78cb8b-fdd5-43b1-9adf-733984cdc9d1","year":2019},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.546950Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:695ac58ce9b60e7780da6ba97643cc6d79b9a1fb0f0b4d753778b7a071e8cfd9","observation_id":"4cdc413d-58d6-48ba-b243-6da88d162400","resolution":{"observed_at":"2026-08-15T17:47:15.068334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.054663Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"ce6c7dfa-3948-4043-9f12-e6def383d3bf","year":2021},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.550378Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:5abc549df1fcf29ade15b4f5325c4bd34670e7e56df34318e156d3dda32460e9","observation_id":"8e6dd114-2222-4b0f-81fa-a5d759209180","resolution":{"observed_at":"2026-08-15T17:47:15.057713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.045044Z","title":"Salun: Empow- ering machine unlearning via gradient-based weight saliency in both image classification and generation","venue":null,"work_id":"749dd400-dfeb-41b2-a52c-5b8fef9dd66f","year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.553859Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:ab58a8975c4a09d363710f97648379f0f30314d0626eb2bfbc1b2a755a841a99","observation_id":"fb99f98a-0a81-4656-9990-8b8563a2d7bd","resolution":{"observed_at":"2026-08-15T17:47:15.048277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12777","last_updated":"2025-08-10T11:11:39Z","snapshot_observed_at":"2026-08-16T13:08:42.685067Z","submitted_at":"2024-10-16T17:51:25Z","title":"Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12777","snapshot_observed_at":"2026-08-15T17:47:14.557082Z","title":"Meta-unlearning on dif- fusion models: Preventing relearning unlearned con- cepts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.557082Z"},"links":{"cited_paper":"/paper/2410.12777","citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:5597183b9b15bceca3bdcc80492669951e29b15a694ff673a7914e41811f8708","observation_id":"6ee764f8-618a-4b98-a698-68a2050b6a50","resolution":{"observed_at":"2026-08-15T17:47:14.557082Z","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":"2026-08-15T17:47:15.035588Z","title":"Ethos: Rectifying language models in orthogonal parameter space","venue":null,"work_id":"fc0f6099-042d-4692-a313-cf68b5f19543","year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.560712Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:352aef610cb2960685b0370907cfb6615d53576b990f9bc1ddaf9831d9b120fe","observation_id":"905a8881-df7c-47cb-bfad-e61cd0098622","resolution":{"observed_at":"2026-08-15T17:47:15.038787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.025188Z","title":"Eternal sunshine of the spotless net: Selec- tive forgetting in deep networks","venue":null,"work_id":"74fa47e2-1555-4b1c-9f80-cf2508dcfae7","year":2020},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.563985Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:e90e75e2a158ecc6bcd9f3632ef488f5a88ac6cc229e65e19c1a36a7dc0349e9","observation_id":"1db0c169-3aaf-426c-9e8f-51b925fd3ff9","resolution":{"observed_at":"2026-08-15T17:47:15.028595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:15.013851Z","title":"Amnesiac machine learning","venue":null,"work_id":"1812ee4e-5f69-4323-85ad-3b81357e3891","year":2021},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.567205Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:6fd59531c0ab40880b73bca2f22abbaa81529a659a2bd18135c5e192eb244451","observation_id":"c934e7aa-8078-4a3d-af03-4250f6de5c95","resolution":{"observed_at":"2026-08-15T17:47:15.018064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.998515Z","title":"The elements of statistical learning: data mining, inference, and prediction, vol- ume 2","venue":null,"work_id":"c655ec9c-27e2-422f-948d-3c4912d06498","year":2009},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.570601Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:0a08be53692c57607f18538cd62d5bc2d799cac83257ad6bc547a6624de686ac","observation_id":"1c36d6cc-d748-492f-a4a8-82710948a596","resolution":{"observed_at":"2026-08-15T17:47:15.002957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.987907Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"4ee426d5-cf60-4cbf-b20e-cf5718e019df","year":2016},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.574014Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:efad20acfeb7e47e04a01ce266aa4c673181d9758a72fa36bf2469146d988ee7","observation_id":"822c355e-7a5b-4882-884a-2d6e8182029a","resolution":{"observed_at":"2026-08-15T17:47:14.991355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.976415Z","title":"Learn to unlearn for deep neural networks: Minimizing unlearning interference with gradient pro- jection","venue":null,"work_id":"35deb28c-bdb9-4ec9-baa9-2e3393c401be","year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.577779Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:ef93509a77b6a7327aa84d10cc017213bbdcc17fac966e9f2cdbe6368ba8e228","observation_id":"8b754d4b-5d49-455f-87af-775b1bc25222","resolution":{"observed_at":"2026-08-15T17:47:14.980014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.966928Z","title":"Learn what you want to unlearn: Unlearning in- version attacks against machine unlearning","venue":null,"work_id":"d0e776da-50e1-4924-b848-bd04a93e0b50","year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.581146Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:277fb5f982462cc4062acb4f00f9046856bdc5fe18242eb88dc45f7fb9f909ba","observation_id":"0bf8a385-4810-41e0-9849-4f81cd42b7c2","resolution":{"observed_at":"2026-08-15T17:47:14.970091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13356","last_updated":"2025-03-17T07:46:49Z","snapshot_observed_at":"2026-08-16T13:41:32.655911Z","submitted_at":"2024-06-19T09:03:21Z","title":"Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.13356","snapshot_observed_at":"2026-08-15T17:47:14.583928Z","title":"Jogging the memory of unlearned llms through targeted relearning attacks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.583928Z"},"links":{"cited_paper":"/paper/2406.13356","citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:d14f2a3019b56e376137ade7dadd766a8f5b98c68b838c9ded68e18fd0aabd68","observation_id":"bf02db72-d3c4-4723-b18d-1b286a5390c2","resolution":{"observed_at":"2026-08-15T17:47:14.583928Z","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":"2026-08-15T17:47:14.957955Z","title":"Unified gradient-based machine unlearning with re- main geometry enhancement","venue":null,"work_id":"1be3397a-7d18-48af-9c12-df00f87414eb","year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.586913Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:a90e748dc237aaaba74298b9f1432f939a30318f902247a71c4165014dc8d7fb","observation_id":"130c2098-9140-492d-beab-128363e893c0","resolution":{"observed_at":"2026-08-15T17:47:14.960801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.948479Z","title":"Model sparsity can simplify machine unlearning","venue":null,"work_id":"6037826e-33e0-4f1d-b80c-ea9bfdbfc6c0","year":2023},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.589862Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:5db8894e160238166cd187d57b1dcbc5e2e3360b8ea7ec391e8a955d417cc4ad","observation_id":"327b0244-1835-45a2-b83f-583f168f68da","resolution":{"observed_at":"2026-08-15T17:47:14.951564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.938876Z","title":"F? d: On under- standing the role of deep feature spaces on face gen- eration evaluation","venue":null,"work_id":"ea5b4d22-c6be-4b4b-8f9f-8e4ead6b20e3","year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.592609Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:207634fa3092d55d77a0d0da230de0ab36da471d05c8e5a59b22a702c2002c85","observation_id":"4c68611e-d8ef-4fa7-9982-8644b8bc8e2b","resolution":{"observed_at":"2026-08-15T17:47:14.942161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.929217Z","title":"Progressive growing of gans for improved quality, stability, and variation","venue":null,"work_id":"d7204ed8-1bac-4b89-ac30-b4ff2370498c","year":2018},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.595383Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:87c456e1526c8b493e029a9764abe4e5c25c4b3113904f9c4232407f616dbd0a","observation_id":"cbd71aa4-30e7-4b6c-b2ff-e1b533c92923","resolution":{"observed_at":"2026-08-15T17:47:14.932577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.919438Z","title":"Towards unbounded machine unlearning","venue":null,"work_id":"ca9b1966-0396-469c-9e80-5572268d3899","year":1957},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.598269Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:cdccc4e89b54128709883a8cc82becb769a9e63930fb4de07bf48fac21f39b18","observation_id":"48c24ca4-362c-4a41-ab80-158b07a7f577","resolution":{"observed_at":"2026-08-15T17:47:14.922833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.907665Z","title":"A sample-level evaluation and generative framework for model inver- sion attacks","venue":null,"work_id":"f20b0dc7-2afc-49ab-b33d-386f67c7d222","year":2025},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.601145Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:2b60d63f65e1f63ecd1ed1c2cbfa372f5d30a51273035d1058271fb39d7f2ca1","observation_id":"b9d00b76-45dc-4e9a-be8b-2bbac974d583","resolution":{"observed_at":"2026-08-15T17:47:14.911919Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.896589Z","title":"FUNU: boosting machine unlearning efficiency by filtering unnecessary unlearning","venue":null,"work_id":"566647e0-2c8f-4f8e-9eda-10153b8daec6","year":2025},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.604343Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:de5a76d0c3ed61b226f527eaeea0b677e3584f6e063f34dbb1c374b13cb6b88b","observation_id":"c20a3b60-fff2-4673-8b1a-c9f9ea7f8bd6","resolution":{"observed_at":"2026-08-15T17:47:14.900434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.885930Z","title":"A data- free backdoor injection approach in neural networks","venue":null,"work_id":"be648b6c-c873-49c2-b620-ce63acbe86b4","year":2023},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.607142Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:33f5151674f86101c6e86d928bcdbef7bd130ef68ce49acd0e63e0ad1e117894","observation_id":"11a80319-9feb-48d1-87df-da3c3841a30c","resolution":{"observed_at":"2026-08-15T17:47:14.889661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-15T17:47:14.609909Z","title":"To- wards deep learning models resistant to adversarial at- tacks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.609909Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:e1302e6e3c2cb6f44cb01cdefd4489df8fcf102d20a54a5b3a8e8bc29e7cca37","observation_id":"ee1c4257-edef-44fe-b97f-6f234ce766ae","resolution":{"observed_at":"2026-08-15T17:47:14.609909Z","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":"2026-08-15T17:47:14.875726Z","title":"The eu proposal for a general data protection regulation and the roots of the ‘right to be forgotten’","venue":null,"work_id":"eb17acb4-861d-47de-8c0d-41d48996f042","year":2013},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.613137Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:e789af77a65ee3e804e0234166b419ff427482c5cb41bf96fd31cd220e2dbf9a","observation_id":"580efdb3-34fe-4193-9d65-227c8f1f6ce3","resolution":{"observed_at":"2026-08-15T17:47:14.879358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.865881Z","title":"No-reference image quality assessment in the spatial domain","venue":null,"work_id":"6a92702b-72d2-45cd-a5be-f203659c0d2c","year":2012},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.615927Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:d0ab017d60bd14f88a0f52148f3e9f6ed0635fb2847fada1a6db00fe1201b47a","observation_id":"31f59c8b-fda1-44c1-ac05-d5b359603dad","resolution":{"observed_at":"2026-08-15T17:47:14.868788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.856093Z","title":null,"venue":null,"work_id":"93999edd-4a71-439a-80c8-ea7019b68b1d","year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.618876Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:8bc3b962f20559a72e55584b30b1e3fab56dcc8af8fceec178214b6c1cfcca83","observation_id":"29541dd5-1c11-4167-b0f7-639af9e34032","resolution":{"observed_at":"2026-08-15T17:47:14.859592Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.845902Z","title":"High- resolution image synthesis with latent diffusion mod- els","venue":null,"work_id":"30586340-24de-4182-915b-003f43f77a01","year":2022},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.621886Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:ca54a90080de5e484602365e8d07c80fac7b350f2654ddcf298703be20dbe4da","observation_id":"ce2f2f6a-2a10-47ee-aa60-5b5013e53018","resolution":{"observed_at":"2026-08-15T17:47:14.849788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.835810Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":"e286a39d-a838-4e1f-8249-261491646799","year":2023},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.624637Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:36b71875d71d37d20c9d7e912be0c7377fadfbecda3e0cdf7b21ad618bd2e2da","observation_id":"bc7bd329-da6d-42fb-a36e-77e79f1ba31b","resolution":{"observed_at":"2026-08-15T17:47:14.839660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.825306Z","title":"Cluster quality analysis using silhouette score","venue":null,"work_id":"b33cc4a3-6bba-4266-a489-47cc510a7584","year":2020},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.627773Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:09853e989ada4d8c1e4edefe0655299e7a4939152e956889328cc2e3ad9e527f","observation_id":"d909291f-748e-4677-9d13-72fec883e5d9","resolution":{"observed_at":"2026-08-15T17:47:14.829025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.814519Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":"86d59b4a-1910-4371-8be4-8a5a89e2f206","year":2017},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.630563Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:ba576e1b7c749c279c0d18ac615d4a6b4c7c7869c94186efd1ea78d23ae10ce5","observation_id":"7f0114e5-7091-4a4a-93eb-4dd7bf640838","resolution":{"observed_at":"2026-08-15T17:47:14.818254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.803516Z","title":"Unrolling sgd: Understand- ing factors influencing machine unlearning","venue":null,"work_id":"33ca7f49-bd38-482b-8629-7cfe269e1096","year":2022},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.633174Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:af42f5b51b34af101daa309311afc5b70d0d4a02210e6b83455ee1123025a360","observation_id":"b4b314c9-bd3f-4a71-9cb2-f436f0007830","resolution":{"observed_at":"2026-08-15T17:47:14.807224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.794208Z","title":"Data-free model extraction","venue":null,"work_id":"cd4bf2ff-9ad4-46bc-948d-e91220b967a7","year":2021},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.637109Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:a92fbe7d1c2b3461d0ff4f29e03c5c5e4b0d39032acaa0d60c3ac4dbfa5db053","observation_id":"69d1740d-14bc-4aa7-832e-50c97cf46836","resolution":{"observed_at":"2026-08-15T17:47:14.797114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.784466Z","title":"Visu- alizing data using t-sne","venue":null,"work_id":"285360c6-7e34-4ad3-88ff-76db930b142b","year":2008},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.640220Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:8ab34329ed1986047477083c7b2a70dc5ce86b82079375fa0ec3b7176e6f5c3f","observation_id":"0627be5a-5c21-4e97-b17a-94f03a69e080","resolution":{"observed_at":"2026-08-15T17:47:14.787785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.774208Z","title":"Anti- dreambooth: Protecting users from personalized text- to-image synthesis","venue":null,"work_id":"6954444f-c477-4b03-a557-0b93daa4d0d1","year":2023},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.643481Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:24587bbd0714aadeea1118c17abfd5759311c8923fdbfdf4615f51e1677b74db","observation_id":"99b8278b-ec69-4832-91d3-72dc19b30f65","resolution":{"observed_at":"2026-08-15T17:47:14.777915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.762409Z","title":"Precise, fast, and low-cost concept erasure in value space: Or- thogonal complement matters","venue":null,"work_id":"933132a9-ab6d-481a-89c5-a6442a1219dc","year":2025},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.646801Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:553b913071e79bd7cdefe5a9629856a6d6cc8bfe9511d22fde6eaf09c301e86f","observation_id":"fc36a255-86af-4210-936e-1012cd20cf4e","resolution":{"observed_at":"2026-08-15T17:47:14.766425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.752013Z","title":"Machine unlearning of features and labels","venue":null,"work_id":"4ca9888e-a7ab-477e-a8d1-b960269cdc68","year":2023},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.650290Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:20b8b51a8275890c0fa5772f24a800791e8e6e279c9f56d3ee521d78a70c240c","observation_id":"79230b04-cc7a-4c0c-92c7-e07ee3ec77d2","resolution":{"observed_at":"2026-08-15T17:47:14.755496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.741058Z","title":"Mexmi: Pool-based active model extraction crossover membership infer- ence","venue":null,"work_id":"82a93789-e78c-4c1f-9ca6-c8f6ac7a6e19","year":2022},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.654003Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:6f285ffc9a599c7f05aedb1b036c917ef2a4cf71d85720774e1a5180add6d49b","observation_id":"05d01d86-dd30-46c2-9874-d05074f18553","resolution":{"observed_at":"2026-08-15T17:47:14.744681Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.729902Z","title":"To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe im- ages","venue":null,"work_id":"af6d525c-6d0b-4566-ade0-c1f3ea4104ac","year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.657399Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:7260eca62d2b6e8a7762586a1e25283bdf348a8e684fba5e5845614d7bc9004c","observation_id":"854485a1-0142-49f8-8509-30141c7961c6","resolution":{"observed_at":"2026-08-15T17:47:14.733724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T17:47:14.718871Z","title":"unlearning-by-disobedience","venue":null,"work_id":"a902b86e-d128-4704-9cda-0706345d072f","year":2024},"citing_paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T17:47:14.660884Z"},"links":{"citing_paper":"/paper/2507.20573"},"observation_digest":"sha256:cc7776438f5d524f38831b85ac6a4d46efba8adb127f28a91c59edf4a9f925bf","observation_id":"43fcb0bb-5f00-45a3-be81-9093509d4c15","resolution":{"observed_at":"2026-08-15T17:47:14.722947Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.20573","last_updated":"2025-07-28T07:12:12Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T01:59:20.542555Z","submitted_at":"2025-07-28T07:12:12Z","title":"Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":42},"total_outbound_references":47},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2507.20573."}