{"as_of":"2026-08-18T00:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:27e96adf92e07a6e353810996f0e06421697c0bb2e5ab42094890f52dce68384","coverage":[{"denominator":63,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":63,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T18:12:21.068376Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2502.05755/citation-record","integrity":"/paper/2502.05755/integrity","json":"/paper/2502.05755/citation-record.json","paper":"/paper/2502.05755"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:12:21.938952Z","title":"Masktune: Mitigating spurious correlations by forcing to explore","venue":null,"work_id":"45c7b35b-9c7d-454a-aee0-e77098a74aa4","year":2022},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.364344Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:ec920aadda1696a38c4ca6c9e4649c2c81dcab3493f41e0d06c9d1c3328411b6","observation_id":"a2a32e22-414b-43e9-9449-bc4a38f944f2","resolution":{"observed_at":"2026-08-08T18:12:21.943058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.928441Z","title":"Rademacher and gaussian complexities: Risk bounds and structural results","venue":null,"work_id":"04d52241-e811-46be-8dde-8ea62febe9dc","year":null},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.369059Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:84c663015104bc0be8f0fc46accbaa735338ef8a79e385590b22660a076fc839","observation_id":"6fb2a055-f8b4-4117-92af-e4c1b6065045","resolution":{"observed_at":"2026-08-08T18:12:21.932439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.916594Z","title":"Mixmatch: A holistic approach to semi-supervised learning","venue":null,"work_id":"66340ef0-7a33-4290-8bf3-385eca142477","year":2019},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.834054Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:ee898d092804784831eeeabc72dfe8a303378d60e0cecc0b8711e814f933a80d","observation_id":"489f0ba7-bab9-4cbd-bf63-fc3d5b08379c","resolution":{"observed_at":"2026-08-08T18:12:21.921004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.905995Z","title":"Remix- match: Semi-supervised learning with distribution alignment and augmentation anchoring","venue":null,"work_id":"361cde57-b3a3-4974-9fe6-c05153b52bda","year":2020},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.838702Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:5647bda9c4f0911b89cfe81a82c54fe9f610bafced1443dce68ba1b7035db528","observation_id":"27cbc744-bec7-45df-b979-da1a0f46f356","resolution":{"observed_at":"2026-08-08T18:12:21.909685Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.896108Z","title":"Poisoning the unlabeled dataset of {Semi- Supervised} learning","venue":null,"work_id":"5ee8d56b-5312-4f89-ba5f-f0f5413d1ee6","year":2021},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.843410Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:eb2136c9d5703f136d216bcdf1a6d32f6caa982d436fd5b9423261edb5a68f1d","observation_id":"045313fa-bd5b-4039-8e5c-d4433d2c4367","resolution":{"observed_at":"2026-08-08T18:12:21.899715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.885385Z","title":"Semi-supervised learning","venue":null,"work_id":"2b7e579f-8617-440a-8847-08a022d3cae0","year":2006},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.848275Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:2dc6874cf8a445fbe87da9b1910d1ee77b5d6fd56c27972638bc10a689e3243b","observation_id":"cab99dba-d34d-4cbb-bbd6-a98af6521b07","resolution":{"observed_at":"2026-08-08T18:12:21.888986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.03728","last_updated":"2018-11-09T01:08:00Z","snapshot_observed_at":"2026-08-16T05:42:20.700873Z","submitted_at":"2018-11-09T01:08:00Z","title":"Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.03728","snapshot_observed_at":"2026-08-08T18:12:20.852645Z","title":"Detecting backdoor attacks on deep neural networks by activation clustering","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.852645Z"},"links":{"cited_paper":"/paper/1811.03728","citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:c8ca1a4daef7a0080b40d56da12c9f8048e4c68009f32d70e4bcf84f2d8c7f6d","observation_id":"b068910c-5f85-4f0e-89e8-ae43c8d73632","resolution":{"observed_at":"2026-08-08T18:12:20.852645Z","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":"2026-08-08T18:12:21.875834Z","title":"Softmatch: Addressing the quantity-quality trade-off in semi-supervised learning","venue":null,"work_id":"d76e1b60-4c75-4d3d-9838-a1fa74e7f7ce","year":2023},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.858093Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:67536012a176cdb0c91acbb32d3384e2c61d1b475f7ac24428e533343cb0379a","observation_id":"5309c973-98ce-408a-b3bf-17ab16a854fb","resolution":{"observed_at":"2026-08-08T18:12:21.878841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.866084Z","title":"A practical clean-label backdoor attack with limited information in vertical federated learning","venue":null,"work_id":"c258d0f7-6569-41ef-adb1-500c1c1e2718","year":2023},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.862212Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:4051cc2489ee2ff3149d2bf3eb5ed80350ec3945b8aab9f148ebb9997b3ad101","observation_id":"500ba90f-db4a-4654-ae2d-bb44c35185a0","resolution":{"observed_at":"2026-08-08T18:12:21.869956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.854208Z","title":"An analysis of single-layer networks in unsupervised feature learning","venue":null,"work_id":"ae660a53-0219-43cf-8d55-a9cbf8b3e544","year":2011},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.866204Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:2ba0328c3b45a47d9e19b717252358e3084003ddc3856b24937a41ab6177c0bd","observation_id":"6f848af6-8dea-408e-976c-f794bb2cff0c","resolution":{"observed_at":"2026-08-08T18:12:21.859120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.02582","last_updated":"2022-12-05T20:21:31Z","snapshot_observed_at":"2026-08-16T23:58:10.888968Z","submitted_at":"2022-12-05T20:21:31Z","title":"Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning","version":1},"cited_work":{"arxiv_id":"2212.02582","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.02582","snapshot_observed_at":"2026-08-08T18:12:21.112146Z","title":"Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning","venue":"cs.LG","work_id":"467996c1-7794-40ba-ac7c-489c35131492","year":2022},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.870241Z"},"links":{"cited_paper":"/paper/2212.02582","citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:6b5cdc33710ad0a4dea164ed7dab16c8b7ca8b35adb407887b46e1141c7c1cf5","observation_id":"e238fa46-0a7b-4b65-8e89-d5c1021974fe","resolution":{"observed_at":"2026-08-08T18:12:21.118184Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.843338Z","title":"Black-box detection of back- door attacks with limited information and data","venue":null,"work_id":"df02a5ab-ddce-4e47-9912-c6309227b129","year":2021},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.874728Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:e3dcd36d68aaf16ac21777b7734c4e33e43699522b6e9523b733c8fc376dd31b","observation_id":"aae6559a-be71-4d33-8bd2-286455ea2435","resolution":{"observed_at":"2026-08-08T18:12:21.847234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.831311Z","title":"Learning with multiple complementary labels","venue":null,"work_id":"d254ebb8-1ecc-45ae-a35b-dea7628f1559","year":2020},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.879171Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:218284adc07f154c3221184f7e73edb5b856bce179429889bc3266b5b7854449","observation_id":"87977a2b-c3ab-4b85-b92d-f661f1d3bc32","resolution":{"observed_at":"2026-08-08T18:12:21.835243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.819682Z","title":"Unbiased risk es- timator to multi-labeled complementary label learning","venue":null,"work_id":"04db6a78-86da-4408-93af-4e1c846cd6fe","year":2023},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.882789Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:ccb82f8b118746f7ffc8c201b9e5faff636b4cc6d983ae37e500a8e58ea62746","observation_id":"216b2807-7fc5-492c-9b61-de941a6a3906","resolution":{"observed_at":"2026-08-08T18:12:21.823751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.809586Z","title":"Complementary to multiple labels: A correlation-aware correction approach","venue":null,"work_id":"673d2abd-4b60-4ec6-b77d-8d7ee1fab82e","year":2024},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.886414Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:5cb9c9b53ef6d77b078d89a9857e94d47d1a028b2daefee6eb186fe4636fd688","observation_id":"c59625cd-a46f-4bc0-b668-8e31d46e2b43","resolution":{"observed_at":"2026-08-08T18:12:21.812880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.799160Z","title":"Identifying vulner- abilities in the machine learning model supply chain","venue":null,"work_id":"2a54cc7d-c70e-4c57-891b-bd6d9b426846","year":2017},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.889601Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:7db999f16fae912319da497ae15c2bdd1e2c50a52ad811eae4c8c9dc543b8c05","observation_id":"e149081e-1710-439b-9a0c-b7b3900fcbe9","resolution":{"observed_at":"2026-08-08T18:12:21.803021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.787813Z","title":"Safe deep semi-supervised learning for unseen-class unlabeled data","venue":null,"work_id":"8bf2387a-c87c-48bc-90ef-b8ea148fb27b","year":2020},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.893083Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:15ecec194c16ec33a004374fbd317dbd8f9747cb52e2c2a2ae501897b5fd162f","observation_id":"b0e70138-9fcf-4e2c-b0f8-d2037701f7f3","resolution":{"observed_at":"2026-08-08T18:12:21.791847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.775529Z","title":"Robust semi-supervised learning when not all classes have labels","venue":null,"work_id":"4752a995-07c4-4621-8f31-c154dd566e39","year":2022},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.896280Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:8925b2a9c9dd9a891a22c5d0b8af44ac616dfd30370c8b022db558cc9db26b3e","observation_id":"caf4f58b-9aad-4bd8-913a-af94e79a4143","resolution":{"observed_at":"2026-08-08T18:12:21.780152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.759996Z","title":"Theoretical foundations of gaussian con- volution by extended box filtering","venue":null,"work_id":"0c88f140-7703-4d35-967a-b215952db8f1","year":2011},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.899735Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:7d021892e00de947d12a75c67eaede231f5a03ba0fcca6ceb1dadec1e4162d3f","observation_id":"19666faf-5a24-4eb8-a15d-9a10b576465b","resolution":{"observed_at":"2026-08-08T18:12:21.764974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.746188Z","title":"Learning from complementary labels","venue":null,"work_id":"9e7a2ecc-a1d7-4b93-8ac9-84340be10c8e","year":2017},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.903377Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:3178f657f6035adad6a4c61b1b6465e0f0adc80c6a0f926995f582c2d75d98d8","observation_id":"0a6d037f-be2e-407b-967b-29e16d338dd1","resolution":{"observed_at":"2026-08-08T18:12:21.751128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.733231Z","title":"Bidirectional adaptation for ro- bust semi-supervised learning with inconsistent data distri- butions","venue":null,"work_id":"9c9a9912-ee16-4dbc-91ab-ac64bdc891b6","year":2023},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.907140Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:59199cb0e83705f1c0ebb1ec2657b24086859d84681e7c0c0b2c00c6df86cf7c","observation_id":"0eef6c3c-d734-48d5-99d1-46007fa6b94e","resolution":{"observed_at":"2026-08-08T18:12:21.737653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.720559Z","title":"Learn- ing multiple layers of features from tiny images","venue":null,"work_id":"1c50ce28-70ee-4e7f-93cc-7dbb669565a7","year":2009},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.912015Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:76e8a2750ba044fa9c5a7a6fb10d9c35470bcf01903b36bac815e989e068476f","observation_id":"e0fb3a5b-eb5b-4347-a82b-2278ea0fcc98","resolution":{"observed_at":"2026-08-08T18:12:21.724858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.708834Z","title":"Pseudo-label: The simple and effi- cient semi-supervised learning method for deep neural net- works","venue":null,"work_id":"636426e4-8926-4c2a-a241-390aa826f7bd","year":2013},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.915774Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:9e11fa02493a204187b7e216387df2a94e66a335e405e3c58181e73a188977b7","observation_id":"c8e1d231-df8c-4f84-9983-18e15866fb7d","resolution":{"observed_at":"2026-08-08T18:12:21.713273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.697776Z","title":"Instant: Semi-supervised learning with instance-dependent thresholds","venue":null,"work_id":"8553a609-3ae4-4318-a993-3c44decb0948","year":2024},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.919709Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:e1391a8fc4ee0be3d96e67f2b0d02a5c9504ebcc82132a44647f42b22d0e610a","observation_id":"61d5c185-0ce1-4ecd-b35e-ee8686fc23c9","resolution":{"observed_at":"2026-08-08T18:12:21.701810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.686363Z","title":"Semireward: A general re- ward model for semi-supervised learning","venue":null,"work_id":"88594c38-8fcb-465a-90ce-0170eb563f54","year":2024},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.923357Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:1e55d8d7bbca83370fe93b7678979694ee741a2296f959be5a1f8f02a284370a","observation_id":"927704e5-f824-4a94-bab7-d66679778351","resolution":{"observed_at":"2026-08-08T18:12:21.690537Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.674464Z","title":"Anti-backdoor learning: Training clean models on poisoned data","venue":null,"work_id":"a55d2b8c-3e46-4e7c-bca1-041b5c292f06","year":2021},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.927026Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:d26f94dc8ca2105a914f9b873f1d7d808dd3c40f6c297b731272637f327e700c","observation_id":"14db541b-b9a3-431e-8618-7cdc1e9e5d09","resolution":{"observed_at":"2026-08-08T18:12:21.678285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.662974Z","title":"Neural attention distillation: Erasing back- door triggers from deep neural networks","venue":null,"work_id":"0552957d-122d-4c6a-8354-8894466d14c3","year":2022},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.930504Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:5f72a89ed1bd7d5856810605b2bc41852e8379e8b83bcea3ed476aa071ed19ab","observation_id":"d1cf3460-5fe3-4d2d-9e6a-403b44cc39cf","resolution":{"observed_at":"2026-08-08T18:12:21.667420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.652136Z","title":"Back- door learning: A survey","venue":null,"work_id":"4ca64f2d-d84f-472d-808a-82371f1f9600","year":2024},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.934291Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:4af16640840a49630c536174b70f5202e05556d1b18849f53f74eb83411310c6","observation_id":"f5a6fa26-aaa9-4d4b-a5f9-ac6ce5578c64","resolution":{"observed_at":"2026-08-08T18:12:21.656229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.640864Z","title":"Towards making unlabeled data never hurt","venue":null,"work_id":"a16df39d-f02d-47e9-8ca2-9af336aff90a","year":2015},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.939080Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:7ce4e1251f3de7c35cdb0bafc3c4fa02693d9ac3812a16cf192f9e685160b687","observation_id":"7b3a2c35-6284-4dfc-9a1e-22d92735d14b","resolution":{"observed_at":"2026-08-08T18:12:21.644800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.626293Z","title":"Towards safe weakly supervised learning","venue":null,"work_id":"52f33ce5-ed28-43b6-832a-4cb8f2cd4af4","year":2019},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.942947Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:515a1ff863d52803b8d2910b87f16939dff093ee090590e124fef7cfc05af337","observation_id":"1b2f84f2-95a2-424c-83e6-71d2d4bb8cc5","resolution":{"observed_at":"2026-08-08T18:12:21.632056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.609311Z","title":"Iomatch: Simplifying open-set semi-supervised learning with joint in- liers and outliers utilization","venue":null,"work_id":"be424d37-0840-42d3-8eb2-1437bbe069bb","year":null},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.946607Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:294c550bc98ec4b6f1b6ed45eb0158da4e9403b818c394dcd4c216cef5d68fe0","observation_id":"8b91564b-21a6-40cf-a5e9-73ef0d67ceac","resolution":{"observed_at":"2026-08-08T18:12:21.614011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.596157Z","title":"Fine- pruning: Defending against backdooring attacks on deep neural networks","venue":null,"work_id":"bf071bbe-470b-45e1-ae59-3289924d6dd8","year":null},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.950021Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:1aec32c41a053698c70bd14acec8deaddd28bc8781493db7ccfb77153583cba0","observation_id":"fbd74ea9-1e01-4fa4-9f3f-9923d5428a7f","resolution":{"observed_at":"2026-08-08T18:12:21.601038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.584473Z","title":"Beating backdoor attack at its own game","venue":null,"work_id":"d1ec468e-f723-4a46-a301-655c0e3d6558","year":2023},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.953179Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:429ace967e11394c6f2b88cbb59c45cac7abeb75e821f9a18f41954d44d26a86","observation_id":"3dca801e-0cee-4c15-9c33-f2e7a6490939","resolution":{"observed_at":"2026-08-08T18:12:21.588449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.573860Z","title":"Iterative reclassification procedure for constructing an asymptotically optimal rule of allocation in discriminant analysis","venue":null,"work_id":"c3d77a91-f7ef-4760-875e-fadba02c1307","year":1975},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.956635Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:d17f314c916010dd42370755cd1995a6b30f2991eca277a5f08c7b8a7670c1cf","observation_id":"986acceb-976e-4f30-baa5-2aba97ab2732","resolution":{"observed_at":"2026-08-08T18:12:21.577226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.563311Z","title":"Foundations of machine learning","venue":null,"work_id":"ae05e8d4-ea44-4cee-a714-75ab53853f6d","year":2018},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.960094Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:d51f8b59488b33675efcffa2a890dcb2d070b84ee7a5afa18189f843aec19c60","observation_id":"badcaf2d-32be-4104-899e-b8b22bf4f051","resolution":{"observed_at":"2026-08-08T18:12:21.567094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.551215Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"7aa36d2a-3dde-40ff-ba32-14f07689ba92","year":2011},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.963736Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:8a9cacc7fe60bdaea0c581eb7453267cedac12f7132adab1f5e927841436efe9","observation_id":"9c232269-c4bd-4c27-b3dc-7f9b46d4b05e","resolution":{"observed_at":"2026-08-08T18:12:21.556026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.540110Z","title":"Hidden trigger backdoor attacks","venue":null,"work_id":"52712c1b-35d6-4095-b8f9-a756e42511e3","year":2020},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.967343Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:2cb21e4b72504ac3e6f72f0137a60bc9d18aa403341b9610ee01f80162afa389","observation_id":"9de0b0cc-fdca-4d9d-b62f-32b2f8d69628","resolution":{"observed_at":"2026-08-08T18:12:21.543869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.529127Z","title":"Probability of error of some adaptive pattern-recognition machines","venue":null,"work_id":"c367f0fc-b9bd-48cf-a541-09ac623014a3","year":1965},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.971145Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:7f2668144dbc119882a379941992eb134dc1c2194df23cb7b79d9a49e2e2b82d","observation_id":"39df8120-673f-435f-9741-2be47ad58584","resolution":{"observed_at":"2026-08-08T18:12:21.532901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.517967Z","title":"The perils of learning from unlabeled data: Backdoor attacks on semi-supervised learning","venue":null,"work_id":"20a60788-0349-4140-aefc-49f3877c1190","year":null},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.975268Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:478b022647da081982b112ccc77ae57fe2c893c315174025e4d91cbe57605e2b","observation_id":"d3901200-af71-4081-9d88-087e6d0df028","resolution":{"observed_at":"2026-08-08T18:12:21.522375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.495822Z","title":"Bypassing backdoor detection algorithms in deep learning","venue":null,"work_id":"edb9509c-f67b-4b56-96fe-901e23c84a3f","year":2020},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.984813Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:c2fce08b27bc7df7e5eb93189787bcc10cbc92dcfbd756fe020fbd4a8704f429","observation_id":"50c6e1e4-15d4-41da-908a-e9e2eac6ad2a","resolution":{"observed_at":"2026-08-08T18:12:21.499164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.485170Z","title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","venue":null,"work_id":"ded4e1c3-a857-48c3-b7cd-892b55387161","year":2020},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.989384Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:61bdd4177261a4d47ee504967f0d9842732b108da3eb189c83f82e3db69f0ac9","observation_id":"38525825-23cb-42e0-8610-bf7c7bbd899a","resolution":{"observed_at":"2026-08-08T18:12:21.488899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.473993Z","title":"Concentration of measure and isoperi- metric inequalities in product spaces","venue":null,"work_id":"4ebf5d49-5c14-4183-bcbd-415d6b1077d0","year":1995},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.993543Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:bee06aab00a862561b2681112ecf62711c7428ffcfc86da9e0335c850255741b","observation_id":"c57635da-3c4a-43ea-82fa-278124bda9c3","resolution":{"observed_at":"2026-08-08T18:12:21.478273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.462828Z","title":"Defending against patch-based backdoor attacks on self- supervised learning","venue":null,"work_id":"6a2d025d-f091-496c-a102-cd663acb5992","year":2023},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.997562Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:048f6dad49c8b173976ac936b241343534eb975bdc4140d2320ecc749bdf9d42","observation_id":"314d3776-cd6e-4e1c-8125-97d0bba222c3","resolution":{"observed_at":"2026-08-08T18:12:21.466729Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.02771","last_updated":"2019-12-06T23:16:45Z","snapshot_observed_at":"2026-08-10T18:11:31.253134Z","submitted_at":"2019-12-05T18:05:59Z","title":"Label-Consistent Backdoor Attacks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.02771","snapshot_observed_at":"2026-08-08T18:12:21.001980Z","title":"Label-consistent backdoor attacks","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.001980Z"},"links":{"cited_paper":"/paper/1912.02771","citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:3fd132ed7767f33e3bf518dd7cb663f95c6f7ae6f9c774fb7610c558615a4b1c","observation_id":"9ce0f2ef-2a96-4744-8f37-d615e8f1270c","resolution":{"observed_at":"2026-08-08T18:12:21.001980Z","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":"2026-08-08T18:12:21.450230Z","title":"Unlocking the power of open set: A new perspective for open-set noisy label learn- ing","venue":null,"work_id":"0dfb366b-cb13-40e0-ae1f-45d9695d9e3e","year":2024},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.006361Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:d588d32c02ce5ab2fe8f602c00d47abbfb4e1d329466d91c12ee329824d3b69b","observation_id":"68d5ca4e-98a7-4348-8b13-55edaec11439","resolution":{"observed_at":"2026-08-08T18:12:21.454971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.437652Z","title":"Learning from complementary labels via partial-output consistency regularization","venue":null,"work_id":"4edc338d-4dd7-41da-8ecc-279f9bac7928","year":2021},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.010127Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:4124c40cdb9fe7a0fd954764c9a5d347a58919d49910275c91f9d4f50469ff51","observation_id":"f7f2be35-9bbb-4b11-91d1-0baa7d3cff80","resolution":{"observed_at":"2026-08-08T18:12:21.442332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.426529Z","title":"Mm-bd: Post-training detection of backdoor attacks with arbitrary backdoor pattern types using a maximum mar- gin statistic","venue":null,"work_id":"7fa97302-d55c-4606-9aae-dfa9e4debb51","year":null},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.013518Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:4d68159c960191adcbda9fb999d3515089fccfc0680cf9d265e60948da843503","observation_id":"60abd80d-a965-43f8-8b4f-2ffaffb88113","resolution":{"observed_at":"2026-08-08T18:12:21.430517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.414408Z","title":"Mm-bd: Post-training detection of backdoor attacks with arbitrary backdoor pattern types using a maximum mar- gin statistic","venue":null,"work_id":"e084300a-f59d-4af2-a6bd-9dce2d98cc41","year":2024},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.017491Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:df770a89fbfc1a0f4172a135b4f1e0758398cdf43202adf523f7d68b4d1b5caa","observation_id":"22b2ccc8-fcf0-4dbf-b8cb-aaa293d0e956","resolution":{"observed_at":"2026-08-08T18:12:21.418907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.401995Z","title":"An invisible black-box backdoor at- tack through frequency domain","venue":null,"work_id":"1834478a-5650-451d-a9d3-359e515544fe","year":2022},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.021701Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:7838fbf39288c8fca70a5d386e56eb526b64aa501bd3813bab29f527e6814d30","observation_id":"2ae329f9-b45c-40a9-a47f-36041216a137","resolution":{"observed_at":"2026-08-08T18:12:21.406538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.389511Z","title":"Usb: A unified semi-supervised learning bench- mark for classification","venue":null,"work_id":"64ed6f45-d966-48e5-84d7-2d026ba102c2","year":2022},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.025215Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:9f3bfc7fbe3d2df64eb263ee5edd6a9db85a64f7905f41a57c791a65e170f810","observation_id":"d9b994e9-189b-4e71-b1db-5ec9990bfad8","resolution":{"observed_at":"2026-08-08T18:12:21.393222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.378489Z","title":"Freematch: Self-adaptive thresholding for semi-supervised learning","venue":null,"work_id":"3d5834fa-ce78-4a4d-8837-2b51b01eaa58","year":2022},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.029298Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:4c621afb5cef0827d888b52b9c11a80859617a434bb14d0eeac216de3e1705c4","observation_id":"5c567393-9958-46e4-b1e1-674b763f1ca6","resolution":{"observed_at":"2026-08-08T18:12:21.382606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.366704Z","title":"Unsupervised data augmentation for consistency training","venue":null,"work_id":"53903a93-a24e-44db-87d2-a550feddcd27","year":2020},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.032894Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:caa7a0ffd9740d56f2e4c34cdcd2999d91018b516bf4121ea3064c2a697599a9","observation_id":"b2501ea7-8e4a-4c81-a89b-f6389a11b7c6","resolution":{"observed_at":"2026-08-08T18:12:21.371394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.354149Z","title":"Generative- discriminative complementary learning","venue":null,"work_id":"bbf7b855-4d27-42a7-9660-f14b97bbce88","year":2020},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.036187Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:897de521047861b07904ea7c5ab4a8984d9ad9cb399cd60ce02c6e4302f6267e","observation_id":"511417f4-3571-4b82-95eb-f2d0bfba194d","resolution":{"observed_at":"2026-08-08T18:12:21.358096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.342010Z","title":"Dash: Semi-supervised learning with dynamic thresholding","venue":null,"work_id":"9e2b8207-f71a-4ab8-87e2-ec8360892512","year":2021},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.039862Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:e0dba3da8f21a307eeb3399be43e5ce86a01f76614ff666c91c760c233848604","observation_id":"b11a9235-cdb6-49eb-a25c-bcd0696085ef","resolution":{"observed_at":"2026-08-08T18:12:21.345859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.330181Z","title":"Dehib: Deep hidden backdoor attack on semi-supervised learning via adversarial perturbation","venue":null,"work_id":"27bb8fff-5ac5-4b9f-b837-cc13c28d89a9","year":2021},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.043758Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:38d93ff60a00ac751674d14a0556de2baecd15ca9cceab500acc2d78c8262fab","observation_id":"49f02e25-6373-42a2-baef-6112abac0adc","resolution":{"observed_at":"2026-08-08T18:12:21.334429Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.317492Z","title":"Deep neural backdoor in semi-supervised learning: Threats and countermeasures","venue":null,"work_id":"3d0ce40a-963c-4a5e-b5a9-222056e1bef7","year":2021},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.047163Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:168f1f509bc936a73c1734fb73bbd1e7c6a3f8ca62bbd334f7fe61878a8e433e","observation_id":"56a2f69c-e055-4036-97f5-ad77d68b125c","resolution":{"observed_at":"2026-08-08T18:12:21.321362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.305081Z","title":"Learning with biased complementary labels","venue":null,"work_id":"b04bb4db-7678-4d55-a3a1-194a9bce8243","year":2018},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.050708Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:8e9a5c8ce4a35025d7144ca138b2c23786d5159d19fbad5ec810f7737275c2d5","observation_id":"c3f7bfe1-725d-4966-a48c-eb43e2b68622","resolution":{"observed_at":"2026-08-08T18:12:21.309499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.292949Z","title":"Rethink- ing the backdoor attacks’ triggers: A frequency perspective","venue":null,"work_id":"974c665d-70c8-4805-9527-7439034b2b8f","year":2021},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.054289Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:5b58b8f049dd73b7b4ad1dc26fe7ed61f599b38ae684ac7601d60b8b1637d30b","observation_id":"54bc8fc4-ff58-4f54-bb24-b0459b672329","resolution":{"observed_at":"2026-08-08T18:12:21.297046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.172830Z","title":"S4l: Self-supervised semi-supervised learning","venue":null,"work_id":"a6278c15-7579-4492-858b-52d0200692ae","year":2019},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.057991Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:c45ab2bd81a1a4f8cb7e644d8a7390d9b118bd037632c2cbdaa2fc6e6e8e45a5","observation_id":"10ffab7e-f5f5-4504-975c-be63bcbe26b7","resolution":{"observed_at":"2026-08-08T18:12:21.176681Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.161373Z","title":"Flexmatch: Boosting semi-supervised learning with curricu- lum pseudo labeling","venue":null,"work_id":"1ead0d6a-7c49-4d06-b2d0-9022d940e6b7","year":2021},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.061491Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:0f868c548ba6111b9944e4b64bae02ba6c7a5c04782f3110a051b3a76fd08466","observation_id":"437cb077-2cd4-4eaf-aefd-ba8cb1489526","resolution":{"observed_at":"2026-08-08T18:12:21.165622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.149340Z","title":"mixup: Beyond empirical risk minimiza- tion","venue":null,"work_id":"67207261-c746-43c4-964a-ee6eebfd8fb7","year":2018},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.064950Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:68e2ea032039867ad1082d93b99b5938765365c0b384a9232c64ef9d1d7e4955","observation_id":"10f2e22d-3bd5-4fe5-bf30-0444de26b4f9","resolution":{"observed_at":"2026-08-08T18:12:21.154001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.137407Z","title":"Backdoor defense via deconfounded representation learning","venue":null,"work_id":"0ab68a34-0300-4132-b6a3-fd435d93a83c","year":2023},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:21.068376Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:75fe60f97357ad2d8798a53d0e2c2fc090a361e2fb358d620c451202a0fde954","observation_id":"469c6385-111d-4d39-84b4-4b90fa0af656","resolution":{"observed_at":"2026-08-08T18:12:21.141246Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-08T18:12:21.505908Z","title":null,"venue":null,"work_id":"1735b952-4ea4-450e-93eb-f7a411cd31cf","year":null},"citing_paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-08T18:12:20.980607Z"},"links":{"citing_paper":"/paper/2502.05755"},"observation_digest":"sha256:e5ab46d5f33c21fcee80ef8ea29a42df9b8e378fca1e3a29d72f8b718cf50c32","observation_id":"bb78bbb1-9c34-4ade-9428-bc6fe5933af3","resolution":{"observed_at":"2026-08-08T18:12:21.509600Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.05755","last_updated":"2025-02-09T03:22:15Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T03:27:24.878195Z","submitted_at":"2025-02-09T03:22:15Z","title":"Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning"},"reference_resolution":{"displayed":63,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":2,"verified_exact":1,"verified_fuzzy":58},"total_outbound_references":63},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:2502.05755."}