{"as_of":"2026-08-04T10:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:620b00f8ffbfc23b214d9f1fc7bcc996a1dab309758063862e0eabe40bfc09d0","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T10:22:28.671574Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+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/2606.22700/citation-record","integrity":"/paper/2606.22700/integrity","json":"/paper/2606.22700/citation-record.json","paper":"/paper/2606.22700"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T10:22:28.671574Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:97a6cb8bdc864e1fca62ecfcb7c3a3aa6831e2ba376d8b91a33c7d102da09652","observation_id":"da415bec-ff70-4f8a-b648-b01d2ba9e35d","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"A survey of security threats in federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:aa5f414296e92fdb4dffaf97abbbcce6053b41f386bd14d10f17284edc3b398f","observation_id":"6cc24856-0f79-427a-879a-e57cb4d25fb7","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"MITRE ATLAS: Adversarial Threat Landscape for Artificial-Intelligence Systems,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:0d989213a45826e93479d56ce4855128f8421a133ea8b76496165b3376e296d3","observation_id":"0c1f3eda-ab38-4ec5-b4f2-19e1119c4781","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.13995","last_updated":"2022-04-12T01:56:47Z","snapshot_observed_at":"2026-07-06T10:28:06.533127Z","submitted_at":"2020-12-27T18:43:39Z","title":"FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping","version":3},"cited_work":{"arxiv_id":"2012.13995","doi":"10.48550/arxiv.2012.13995","metadata_source":"arxiv_reference","pith_arxiv_id":"2012.13995","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"arXiv preprint arXiv:2012.13995 , year=","venue":null,"work_id":"0364103d-9db6-4c1c-a200-06789828f79f","year":2012},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"cited_paper":"/paper/2012.13995","citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:bd05e9ac393aad18b41a1b3b2a02b3708a00ab027f772a99b2621ef01cf7b69e","observation_id":"bbd2db44-cb9c-4fad-ac93-e019ec3452d8","resolution":{"observed_at":"2026-07-04T09:09:43.726674Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-26T10:22:28.671574Z","title":"{FLAME}: Taming backdoors in federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:fba0949f5f4e1495185fcce8de357416a03ef6a8abe76e28a9c2f1ad15d1bfaa","observation_id":"05fa4399-9047-482f-82d5-642fde1c4bd7","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Resisting poisoning attacks in federated learning via dual-domain distance and trust assessment,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:ddb8e06c3fc6f569b2989ff43c28477902fe57c4efa7e718cd527816b99e5203","observation_id":"a54b5498-fe64-45ae-b1da-967d68ca52e8","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Robust knowl- edge distillation in federated learning: Counteracting backdoor attacks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:62f21017b2ce6975dd806b8bb59d341dde6bf59aed451972a1cb24e53dae0135","observation_id":"b4a8dcc4-d7e5-4983-8418-4e0f375ea8bc","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Defending against backdoor attacks in federated learning by using differential privacy and ood data attributes,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:ae2eb4d03c6ac445a17ac139da82c3f5fb8003d542d7b2166e49b10d62fc744a","observation_id":"1ddbb54e-c81c-41cc-82ff-37c203ef7ddf","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2505.10297","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T09:09:43.722320Z","title":"Defending the edge: Representative-attention defense against backdoor attacks in federated learning,","venue":null,"work_id":"ac0e5914-45b3-4481-85dd-b8b7ea21376a","year":2025},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:3a3d81f0202ebe5346e7e8ab953f79c165e44e8fbfcea9989ed36c494f9a3a94","observation_id":"0bbac3a6-f31e-4baa-b3a1-9c90f26ff259","resolution":{"observed_at":"2026-07-04T09:09:43.723893Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-26T10:22:28.671574Z","title":"Securing federated learning against backdoor threats with foundation model integration,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:57b045a169b4c75d4acfbf164af89b5fa85bd8c324ff2424d0c75630a445bfb8","observation_id":"52dc044b-a331-415a-bfdc-c72839f75e04","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Flpu- rifier: Backdoor defense in federated learning via decoupled contrastive training,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:1cf9e1252cc0542b01207c73f4e8a60a23cb284703ece90656d4d8c3533b9be4","observation_id":"75ed20ce-1984-4227-8683-47a82f3b99f6","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Unlearning backdoor attacks in federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:cfa5fa1d302b981a3026238edeff894157a44e329c23694137faaaf2f5f29887","observation_id":"a7c790bc-3e35-40b5-a1b0-f6c850e8c96b","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Fedcleanse: Cleanse the backdoor attacks in federated learning system,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:ef90d11efe3095b83ffc597276842f2de93eda722f4ad578e701c32e0bf05f8d","observation_id":"85b62ec1-e1bc-4d6e-9165-d6f48e74c388","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Shift: Enhancing federated learning robustness through client-side backdoor detection,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:c8f239048926f64104c7330840cf2bf3bebd5d3b4f42ad91079017daba38d49f","observation_id":"10fc4bad-6aae-48d6-b67e-2657a94bf14e","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Adfl: Defending backdoor attacks in federated learning via adversarial distillation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:b6289a667b09bc534458ac45171d33214c1982b9426553e17532b79cd0e85261","observation_id":"8de4f82b-e741-407f-95be-05c239178520","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Mitigating distributed backdoor attack in federated learning through mode connec- tivity,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:dd333892d263e92b061ca2c748b82ca5332f5dbc987db10992793e85a766e489","observation_id":"586f559c-4443-455f-b4d6-42624b7c7121","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Generative adversarial nets,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:cc5aaabb2a5ebfaf4391bf2f880f7355f32e7a5b4472519248940a4d4e8046b4","observation_id":"fcf23ea2-f25f-4b95-87d4-9c690b8995e2","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Improved training of wasserstein gans,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:0a99b67737507601a0ea31e95d04222ea3211ccba3013368a9aaa54d8d748502","observation_id":"61f83c78-6abe-4a30-b10e-1d8e42e5c212","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.03728","last_updated":"2018-11-09T01:08:00Z","snapshot_observed_at":"2026-07-06T07:13:39.005894Z","submitted_at":"2018-11-09T01:08:00Z","title":"Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering","version":1},"cited_work":{"arxiv_id":"1811.03728","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.03728","snapshot_observed_at":"2026-07-04T21:00:09.063525Z","title":"Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering","venue":"cs.LG","work_id":"2e1136ed-bfba-455c-979e-f617263c8b5e","year":2018},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"cited_paper":"/paper/1811.03728","citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:06ceeb9c674186a5b704b87293b396879b5d873a8b25013ba6cf9a63c94b3c39","observation_id":"c6c8ac62-9087-4209-9fab-c6925122788b","resolution":{"observed_at":"2026-07-04T09:09:43.729228Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-26T10:22:28.671574Z","title":"Mudguard: Taming malicious majorities in federated learning using privacy-preserving byzantine-robust clustering,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:e2978b3b776317d90357becd6cada202366592fe03d6f501c1616df672c7706d","observation_id":"3c355777-bf69-4724-a506-cee1b1fbd4ac","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:4aae38f512618cd002f7a5ca020e4dd53c7dc2269abcd8e1b30ab7c0e4e6395d","observation_id":"ddb14572-63d3-4b49-8735-67167163937d","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"The german traffic sign recognition benchmark: a multi-class classification competition,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:4af13bd650bdca8ca199069c5e4880988b57a95226f0ac406a39f5ba08f06fee","observation_id":"1aa0dbc0-3735-4f5d-85dd-6cfbdd8fac39","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Fine-pruning: Defending against backdooring attacks on deep neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:04eba480a7a545adcaa28defbf1924ef3f05de1d3cf283c6cbbef776de5a5aed","observation_id":"4b0ebd39-11dc-4b84-8a9c-5e5287841981","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","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":"2026-06-26T10:22:28.671574Z","title":"Neural cleanse: Identifying and mitigating backdoor attacks in neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-26T10:22:28.671574Z"},"links":{"citing_paper":"/paper/2606.22700"},"observation_digest":"sha256:fcbe3a24a3a91b5caec47fca90acda7954109af4713c7be875244e70cb75c883","observation_id":"514e9ee2-e3ef-4572-b3cb-66138a74b9e8","resolution":{"observed_at":"2026-06-26T10:22:28.671574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.22700","last_updated":"2026-06-21T22:34:34Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-03T15:50:10.985369Z","submitted_at":"2026-06-21T22:34:34Z","title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":21,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":24},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2606.22700."}