{"as_of":"2026-08-22T03:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b7d92d171b809e9687d8c2a92800cbf721d8ba93e320e6b8de28749e283b8b05","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:36:06.707062Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2505.07026/citation-record","integrity":"/paper/2505.07026/integrity","json":"/paper/2505.07026/citation-record.json","paper":"/paper/2505.07026"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:36:07.514048Z","title":"General data protection regulation,","venue":null,"work_id":"29ba2013-b64d-405e-8af3-b01b3e25c59d","year":2016},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.531603Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:b2e91b918989297f6b4ab2da712db7fe00b38da6e5da5581f95d63970b46e596","observation_id":"fe6058ef-67e0-4b3b-96c0-1f97b7160573","resolution":{"observed_at":"2026-08-15T22:36:07.517854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.501626Z","title":"California consumer privacy act of 2018,","venue":null,"work_id":"2171ed1c-476a-40e4-83b2-125e825d948d","year":2018},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.536853Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:8860ed439b5500d1cf4df592d18fb605518750419ad99e208a918a04e12339ae","observation_id":"293feb2b-6ae8-491e-a649-45a020c2fa84","resolution":{"observed_at":"2026-08-15T22:36:07.505663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.489760Z","title":"Machine unlearning,","venue":null,"work_id":"ded982a9-3f30-4f9a-a05a-c63ecd1faa1b","year":2021},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.541150Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:8b579cddc7d5f27088788710f0b29073434d75373a2defadf340fbab49256306","observation_id":"e8a33f1f-342f-4dd4-9727-b6474226e9ec","resolution":{"observed_at":"2026-08-15T22:36:07.493335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.477581Z","title":"Graph unlearning,","venue":null,"work_id":"873b6eb2-717a-4791-af87-dc6a60490626","year":2022},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.545661Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:3ec0e0b6166747454266b3327de1d1b4c1c8ac818eea810bf024ccef71f663eb","observation_id":"8f442f34-b9fa-4c01-a254-d6a6e81f8327","resolution":{"observed_at":"2026-08-15T22:36:07.481311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.465825Z","title":"Making AI forget you: Data deletion in machine learning,","venue":null,"work_id":"2f50392b-e6d8-4112-8d05-182d722d527c","year":2019},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.550149Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:42d8fd7555e65e5c56d32a9d42bd3b4b67074f9a2cb4cdccdd9360647d5ac7cb","observation_id":"a3000bfb-c7b9-4b71-9810-32ae49fd8835","resolution":{"observed_at":"2026-08-15T22:36:07.469498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.453707Z","title":"Towards making systems forget with machine unlearning,","venue":null,"work_id":"5f967ec0-0d65-4f51-8ab9-976aabb5c42e","year":2015},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.554242Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:29e16fe5d3a6e335fe48c48f7b515ba580d92939311439e7f282d09a99fa7819","observation_id":"ce66ec46-aa92-446b-a6f4-e60f6e6a3d26","resolution":{"observed_at":"2026-08-15T22:36:07.457686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.441992Z","title":"Certified data removal from machine learning models,","venue":null,"work_id":"87212491-4e69-41cf-9da6-6f6876258709","year":2020},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.560904Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:33792fc832301bb6019fd90d963e705531ea2d77faadab45b8eb4a6c4093924b","observation_id":"ca651079-ba52-4194-8ffe-ae736452bb70","resolution":{"observed_at":"2026-08-15T22:36:07.445677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.11577","last_updated":"2023-08-07T12:33:20Z","snapshot_observed_at":"2026-08-18T17:58:08.799481Z","submitted_at":"2021-08-26T04:42:24Z","title":"Machine Unlearning of Features and Labels","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.11577","snapshot_observed_at":"2026-08-15T22:36:06.567090Z","title":"Machine un- learning of features and labels,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.567090Z"},"links":{"cited_paper":"/paper/2108.11577","citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:50ebbae3bb83266b983f4215014767a2183101dd98413d80b153be76b0ca9df7","observation_id":"d4be1d5c-acc2-462f-89e5-8e1ac19c58da","resolution":{"observed_at":"2026-08-15T22:36:06.567090Z","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":"2026-08-15T22:36:07.429056Z","title":"Algorithms that approximate data removal: New results and limitations,","venue":null,"work_id":"3c6bd260-41a1-4580-b785-d27b9ffaf09a","year":2022},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.572127Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:2a96746fd2c7048b156d8354e5064507ea5edd0a50d3a084c34bcb7fae49c7aa","observation_id":"c19e9ba9-19e3-440a-a874-6279e2108169","resolution":{"observed_at":"2026-08-15T22:36:07.433211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.414867Z","title":"Deep unlearning via ran- domized conditionally independent hessians,","venue":null,"work_id":"50d55736-08b8-4909-880a-59750f1b2971","year":2022},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.576984Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:75b240e2a72fb75748b683bd4ef11083df42144d4f64e45681dfe4bb9ea4f04b","observation_id":"39dae111-96ab-4649-92aa-4a52eeae1224","resolution":{"observed_at":"2026-08-15T22:36:07.419013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.401357Z","title":"Eternal sunshine of the spotless net: Selective forgetting in deep networks,","venue":null,"work_id":"287638a8-65e8-48b0-8b5a-328315c31e2e","year":2020},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.581673Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:0ef4ad2004a51eba0a97e2a4ad14f9595a721c93af0c74d783eee8ca56461449","observation_id":"bad1160e-eeeb-401b-a52d-9abf1f041298","resolution":{"observed_at":"2026-08-15T22:36:07.405777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.387692Z","title":"Deltagrad: Rapid retraining of machine learning models,","venue":null,"work_id":"078e5dfa-35e2-473c-9289-6e69b831e8e6","year":2020},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.588594Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:38deef85dc687f07ea548ec010efbb080b04f29811b29186cfd5ba2bb5f0ff5b","observation_id":"4e8ee7bb-be84-490e-b7ed-0be7e630bf18","resolution":{"observed_at":"2026-08-15T22:36:07.392394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.374990Z","title":"Fedrecover: Recovering from poisoning attacks in federated learning using historical information,","venue":null,"work_id":"ad232284-5355-42a8-aa99-cd07ecac357b","year":2023},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.593557Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:9e9ff193525e3e4535585586b3fa0d511582aa87cf211e3396bf2232106c0a2c","observation_id":"cd69ba49-979d-40e6-a000-8cffbc3ce38e","resolution":{"observed_at":"2026-08-15T22:36:07.378778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.02299","last_updated":"2024-09-17T11:55:58Z","snapshot_observed_at":"2026-08-18T20:41:01.318983Z","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":"2026-08-15T22:36:06.599433Z","title":"A survey of machine unlearning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.599433Z"},"links":{"cited_paper":"/paper/2209.02299","citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:15abe90cce36374666d966c3db5b55cc7748693ef0d3763aefc582f20d0891cf","observation_id":"569a61bb-f196-4e5a-9017-b074babe40d4","resolution":{"observed_at":"2026-08-15T22:36:06.599433Z","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":"2026-08-15T22:36:07.363003Z","title":"Machine unlearning: A survey,","venue":null,"work_id":"c4816e04-4ed6-470c-8dd2-58d6985416ac","year":2023},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.604731Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:922aec78c0d1cd4f37cba3d26594571610f58d9129429cd10ce0d859126efd36","observation_id":"94265aaf-44ec-4941-a38c-0127e7b9940b","resolution":{"observed_at":"2026-08-15T22:36:07.366737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07406","last_updated":"2026-04-20T05:27:15Z","snapshot_observed_at":"2026-07-06T18:13:16.171803Z","submitted_at":"2024-05-13T00:58:34Z","title":"Machine Unlearning: A Comprehensive Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07406","snapshot_observed_at":"2026-08-15T22:36:06.608934Z","title":"Machine unlearning: A comprehensive survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.608934Z"},"links":{"cited_paper":"/paper/2405.07406","citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:f4a5eb675a71809c45b69a5cb13b40685ebafd29c84ef18f7c5506e22491b6cb","observation_id":"ae0176be-8653-4aa9-8be6-7f818e200dae","resolution":{"observed_at":"2026-08-15T22:36:06.608934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:36:06.614383Z","title":"A survey on machine unlearning: Techniques and new emerged privacy risks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.614383Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:5000e6e040487597f00532b3536e6b2fec83650358ea95d188394ee431723be8","observation_id":"c00d22ac-a29d-4284-a020-c1a63166fb63","resolution":{"observed_at":"2026-08-15T22:36:06.614383Z","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":"2026-08-15T22:36:07.341698Z","title":"Threats, attacks, and defenses in machine unlearning: A survey,","venue":null,"work_id":"6624846c-6eb7-4914-b772-ec31bd3bbb96","year":2025},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.620214Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:868358e072bf485b700b7f0ba392d01cf37a2f3f29184bb358211d648076c5c3","observation_id":"a45b8fd0-a11e-453b-8bb9-414dd6e38465","resolution":{"observed_at":"2026-08-15T22:36:07.345562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.329672Z","title":"Machine un- learning of federated clusters,","venue":null,"work_id":"96893ea1-b1d2-4d52-878b-af6eacb1e78a","year":2023},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.624581Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:01207cd8108e41a3b8e14e7f5be80849ce3214cf86b8c247c3866981ed8f44e3","observation_id":"86e8a818-bfb0-4f41-a641-4c46021a1ac1","resolution":{"observed_at":"2026-08-15T22:36:07.333319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.317367Z","title":"An information theoretic approach to machine unlearning,","venue":null,"work_id":"9df61920-0919-4fad-81c3-1e9e42bda2e5","year":2025},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.628687Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:45412caded11ef769a25f333360ca673d9ae1b7903265779431485e7dd8d4068","observation_id":"eb3e6abc-9e97-4759-81f4-860a87af05dd","resolution":{"observed_at":"2026-08-15T22:36:07.321104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:36:06.632585Z","title":"Model sparsity can simplify machine unlearning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.632585Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:2fe5d1e1bb924c6246fee1ddf38fd76e12d9bf72ed5581c8ab21c987e0785e76","observation_id":"0a0521c6-c3f0-44f4-9346-7b4d714c1190","resolution":{"observed_at":"2026-08-15T22:36:06.632585Z","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":"2026-08-15T22:36:07.295739Z","title":"Fast yet effective machine unlearning,","venue":null,"work_id":"74f14a72-9f80-4f3c-b2c2-aecfc9cc4468","year":2024},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.637042Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:73ad4b4f1ae41918d255349fc064a0160ccb2f40b724187b5000cd7b387c8fa1","observation_id":"1b1fef2d-5e49-4714-8025-c9f5351ca02a","resolution":{"observed_at":"2026-08-15T22:36:07.299916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.03030","last_updated":"2023-11-08T03:57:25Z","snapshot_observed_at":"2026-08-15T07:57:47.753668Z","submitted_at":"2019-11-08T03:57:41Z","title":"Certified Data Removal from Machine Learning Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.03030","snapshot_observed_at":"2026-08-15T22:36:06.641159Z","title":"Cer- tified data removal from machine learning models,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.641159Z"},"links":{"cited_paper":"/paper/1911.03030","citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:e07afd3723b863cf799eeabac1294831a3a525e317d0ce872929690970ccc7a0","observation_id":"0a26ec0d-ad36-4962-89a3-e93c3d270f26","resolution":{"observed_at":"2026-08-15T22:36:06.641159Z","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":"2026-08-15T22:36:07.282015Z","title":"Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models,","venue":null,"work_id":"34ef5770-bdff-462f-8f35-43344ba43768","year":2019},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.645960Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:004f354f63edacb0f266a9066048e973b1961316642b5e0fb064fbc282bb5e35","observation_id":"2f4957c7-1618-4ee5-b4e4-47e5e5bdc3af","resolution":{"observed_at":"2026-08-15T22:36:07.285891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.269671Z","title":"En- hanced membership inference attacks against machine learning models,","venue":null,"work_id":"dde1c704-ef8e-4148-bf3f-817b0810359a","year":2022},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.652051Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:2cfc341fee499a5608ab069859046f2afe84ec274465ad0e2e10bc3f00ed68d3","observation_id":"f2b82a6f-5db6-4f9a-9d32-a88b858dc20a","resolution":{"observed_at":"2026-08-15T22:36:07.273563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.255919Z","title":"A survey on membership inference attacks and defenses in machine learning,","venue":null,"work_id":"4a56474a-27f0-4a73-a0a8-cc63fd244e31","year":2024},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.656834Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:121dd28e898197cc1dd17592dd00538ac3a23441ba83e87247f3c92e8c2c1f5c","observation_id":"b20baa2b-a214-492c-be68-aeb7e057f1c4","resolution":{"observed_at":"2026-08-15T22:36:07.260507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.04247","last_updated":"2020-12-01T16:01:10Z","snapshot_observed_at":"2026-08-06T06:26:57.210854Z","submitted_at":"2020-03-09T16:39:46Z","title":"Towards Probabilistic Verification of Machine Unlearning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.04247","snapshot_observed_at":"2026-08-15T22:36:06.662312Z","title":"Towards probabilistic verification of machine unlearning,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.662312Z"},"links":{"cited_paper":"/paper/2003.04247","citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:4c1afeb36f70b063a138191e285e62c26b1f2f1cc469a3e24a5bd3f18e8c0203","observation_id":"894f9757-f4d9-432d-a05e-d1c49ef85b9c","resolution":{"observed_at":"2026-08-15T22:36:06.662312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:36:06.667496Z","title":"An informa- tion theoretic evaluation metric for strong unlearning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.667496Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:346392f8a612d612507e77f78b0ac9ef10bc2f87f40a769492ee47861daa477a","observation_id":"fcf7c987-c9b4-4a05-bb0d-459fbda7934b","resolution":{"observed_at":"2026-08-15T22:36:06.667496Z","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":"2026-08-15T22:36:07.241888Z","title":"Verification of machine unlearning is fragile,","venue":null,"work_id":"1dd26307-5165-4628-994d-177ceb2d7e3c","year":2024},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.671612Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:ed55e6077921f11e42d3bbf30269930b26114adc2643298a6dfec1c9ae59a3f1","observation_id":"7b354605-2f96-42ae-9709-07d1cff30e09","resolution":{"observed_at":"2026-08-15T22:36:07.246628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19798","last_updated":"2025-03-07T14:20:23Z","snapshot_observed_at":"2026-08-16T13:14:20.695452Z","submitted_at":"2024-09-29T21:49:32Z","title":"Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.19798","snapshot_observed_at":"2026-08-15T22:36:06.676088Z","title":"Membership inference attacks cannot prove that a model was trained on your data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.676088Z"},"links":{"cited_paper":"/paper/2409.19798","citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:7068f44c5f7ea3f595eb024de2dc00b54a9f252d82da02985a405be98b2eb47f","observation_id":"5f7037d6-eea1-4f06-b42c-6a84212bd4da","resolution":{"observed_at":"2026-08-15T22:36:06.676088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06808","last_updated":"2025-03-09T23:32:15Z","snapshot_observed_at":"2026-08-16T12:51:43.040020Z","submitted_at":"2025-03-09T23:32:15Z","title":"Privacy Auditing of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.06808","snapshot_observed_at":"2026-08-15T22:36:06.680767Z","title":"Privacy auditing of large language models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.680767Z"},"links":{"cited_paper":"/paper/2503.06808","citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:55862c96ba2c15bd3c7b88cd08106b57cded8c717a694a6fc5a7fb4079eb3163","observation_id":"a687f264-09a3-4a0d-af68-332bcea30cf2","resolution":{"observed_at":"2026-08-15T22:36:06.680767Z","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":"2026-08-15T22:36:07.227778Z","title":"Membership inference attacks and defenses in classification models,","venue":null,"work_id":"3dd47851-331b-4ff5-840f-4e35e1718739","year":2021},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.685953Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:3ae89d5afb8b4849929c5e13e96779503d86255f2d70d51d454cce86a283a5c5","observation_id":"e93a94b7-19c3-4554-931d-dc53a64edc10","resolution":{"observed_at":"2026-08-15T22:36:07.232470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:36:06.689459Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.689459Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:2b7e53024a5c74bd9d03cad5eadfec70ec5de87bb122817cee7ea1e98981d6e4","observation_id":"3ae8f258-0137-4618-9182-6a0fbc7a9cfb","resolution":{"observed_at":"2026-08-15T22:36:06.689459Z","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":"2026-08-15T22:36:07.135762Z","title":"Regularization mixup adversarial training: A defense strategy for membership privacy with model availability assurance,","venue":null,"work_id":"7c0686d3-03b1-409b-915c-4dc17d88dc58","year":2024},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.693576Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:8d79eb56ab3e934606382943ced30a37e7d7c88b42e26f7da601940771210819","observation_id":"e72cd1f7-4260-4d18-af3c-97a789ebb382","resolution":{"observed_at":"2026-08-15T22:36:07.209483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.040463Z","title":"Membership inference attacks against adversarially robust deep learning models,","venue":null,"work_id":"c359070e-e2fd-45bf-b8bc-d873a4076b69","year":2019},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.698390Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:18988274f575f7258693ac458f0f3aa9eb4cfb6d469b832aa69a2b023c9302c0","observation_id":"917a6421-0257-4fae-a1af-3ea3e692379e","resolution":{"observed_at":"2026-08-15T22:36:07.067678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:07.027354Z","title":"Unrolling sgd: Understanding factors influencing machine unlearning,","venue":null,"work_id":"3fdcb156-eedb-4291-a78b-03d1b2ffb04f","year":2022},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.702767Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:1af067160feaa2189336ce89ff46dd877da62c250ce07ab3158aa7597232aeaf","observation_id":"79e5c38d-999f-4a3d-b56d-f20cd3bbb987","resolution":{"observed_at":"2026-08-15T22:36:07.031315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T22:36:06.996004Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":"106a933e-c2bc-4ccf-974e-9ed386fbbf35","year":1998},"citing_paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T22:36:06.707062Z"},"links":{"citing_paper":"/paper/2505.07026"},"observation_digest":"sha256:10955b867c6c4b183e9af9de5e1992592b231fb23a415707488598dee89c239b","observation_id":"3198eb3d-4599-4a0e-a223-7d6aa85dcee8","resolution":{"observed_at":"2026-08-15T22:36:07.017566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.07026","last_updated":"2025-05-11T15:42:11Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T04:42:49.130511Z","submitted_at":"2025-05-11T15:42:11Z","title":"Efficient Machine Unlearning by Model Splitting and Core Sample Selection"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":26},"total_outbound_references":37},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2505.07026."}