{"as_of":"2026-08-09T20:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0e1aaa974ff75fb418f9c76a8a25624061a9a7870a02eeefb7f9aa60f807b5c0","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:37:55.151302Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.14531/citation-record","integrity":"/paper/2505.14531/integrity","json":"/paper/2505.14531/citation-record.json","paper":"/paper/2505.14531"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:38:02.278689Z","title":"A new backdoor attack in CNNS by training set corruption without label poisoning","venue":null,"work_id":"334d6c56-173f-493a-a817-791d699623c2","year":2019},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:51.991117Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:5e8962cebeba03a75db8c03f8e43b247d289649c3bf7e0b5ec0018f1a3e0f3f9","observation_id":"e6b03d15-69cd-461d-873e-adb676185b59","resolution":{"observed_at":"2026-08-07T15:38:02.379146Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:38:02.038845Z","title":"Deepinspect: A black-box trojan detection and mitigation framework for deep neural networks","venue":null,"work_id":"420b9d95-5963-4022-8978-0a91624b6265","year":2019},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:52.068774Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:8dfdf69e46d41cf5d43f5ea0446f6e132c1098043263566715eab79253fc9323","observation_id":"51f00c75-1e5d-4d42-8765-308e492de4e8","resolution":{"observed_at":"2026-08-07T15:38:02.187260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.05526","last_updated":"2017-12-15T04:26:26Z","snapshot_observed_at":"2026-07-06T06:14:30.795326Z","submitted_at":"2017-12-15T04:26:26Z","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.05526","snapshot_observed_at":"2026-08-07T15:37:52.211981Z","title":"Targeted backdoor attacks on deep learning systems using data poisoning.CoRR, abs/1712.05526, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:52.211981Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:6261c99206af617a4649d1257be905f6c0745ad4b88ead6f68f20b86cb6597db","observation_id":"d4cb2ba2-3643-47fa-96b0-f93cc0ed0208","resolution":{"observed_at":"2026-08-07T15:37:52.211981Z","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":"2026-08-07T15:38:01.858424Z","title":"Sentinet: Detecting localized universal attacks against deep learning systems","venue":null,"work_id":"233b25a3-f4ad-4d30-82ef-d6bff7aee5f2","year":2020},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:52.330141Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:f3f2768367bb48d76fa94d05c2e4ed891cc320f82ec189b25bdbc134a54d5564","observation_id":"a9c7739a-b30f-4e2e-a5cb-d6f2db617629","resolution":{"observed_at":"2026-08-07T15:38:01.945859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:38:01.656657Z","title":"G., Abbasnejad, E., and Ranasinghe, D","venue":null,"work_id":"3953b30a-63fe-4b6b-9b66-4a5a5d3d31a3","year":2020},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:52.470701Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:d822a7b1b3640bdbbb6de21cec340314448e251fd32fa6b4e8fda270321f03bf","observation_id":"9c9ada43-d922-45d6-be73-c0b4ba526b52","resolution":{"observed_at":"2026-08-07T15:38:01.740168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:38:01.517447Z","title":"Black-box detection of backdoor attacks with limited information and data","venue":null,"work_id":"93f69bb2-eb3b-4956-b416-f999b04270d0","year":2021},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:52.583673Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:e7536df62e161129e4c11175df0a2474c216667907bd418314d7b22a20237450","observation_id":"df5fde9f-5262-441b-a0f4-3b2c02bb5f92","resolution":{"observed_at":"2026-08-07T15:38:01.582137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:38:01.280440Z","title":"Differential analysis of triggers and benign features for black-box DNN backdoor detection.IEEE Trans","venue":null,"work_id":"4531f753-10e7-4a15-b2d4-9fc6c7003dc3","year":2023},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:52.726788Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:44228565476012f216f8fac33a721c4b10494427aa3ec42e749e8ac02ef12969","observation_id":"cb01f4e3-cd29-43de-8876-de078df08084","resolution":{"observed_at":"2026-08-07T15:38:01.416743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:38:01.093451Z","title":"C., and Nepal, S","venue":null,"work_id":"5e1980a1-49ab-40ab-964d-74d0e0ac2a23","year":2019},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:52.843525Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:562f86dd04dd4badd62e19d897e171c22d6b39f5e76b9c3537fd9c597de88f30","observation_id":"d8224b7f-df79-4833-aa5e-2b9b75f1bc92","resolution":{"observed_at":"2026-08-07T15:38:01.197974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.06733","last_updated":"2019-03-11T20:45:33Z","snapshot_observed_at":"2026-07-06T05:56:16.413472Z","submitted_at":"2017-08-22T17:31:54Z","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.06733","snapshot_observed_at":"2026-08-07T15:37:52.922253Z","title":"Badnets: Identifying vulnerabilities in the machine learning model supply chain.CoRR, abs/1708.06733, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:52.922253Z"},"links":{"cited_paper":"/paper/1708.06733","citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:c52fd18dc4aa458e1df825764866e711c22c2965aee61737ed318cb9baafac61","observation_id":"3a104a68-9a0a-42f2-9894-b994ad61e328","resolution":{"observed_at":"2026-08-07T15:37:52.922253Z","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":"2026-08-07T15:38:00.949574Z","title":"SCALE-UP: an efficient black-box input-level backdoor detection via analyzing scaled prediction consistency","venue":null,"work_id":"b6935381-b5e2-4980-827f-fb8fb89be6b5","year":2023},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.031870Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:ccb111f116cad1a49ba45aa886376c6201712e08c2c241c02abfba953bbebb47","observation_id":"5bb673fc-fe84-4541-b05e-c7d6b147929c","resolution":{"observed_at":"2026-08-07T15:38:01.019558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.11315","last_updated":"2021-04-22T20:49:40Z","snapshot_observed_at":"2026-07-06T11:02:52.792351Z","submitted_at":"2021-04-22T20:49:40Z","title":"SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.11315","snapshot_observed_at":"2026-08-07T15:37:53.115468Z","title":"SPECTRE: defending against backdoor attacks using robust statistics.CoRR, abs/2104.11315, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.115468Z"},"links":{"cited_paper":"/paper/2104.11315","citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:f68ec69fbf29036b97ece7824a81896d7ff17b54eb3fa8f13304017d29d983b9","observation_id":"748303ec-39ce-4762-884d-bb7a7fa4e280","resolution":{"observed_at":"2026-08-07T15:37:53.115468Z","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":"2026-08-07T15:38:00.785698Z","title":"O.The Organization of Behavior: A Neuropsychological Theory","venue":null,"work_id":"9576f0fb-d2c6-4a3a-9f85-c758fcfeb530","year":null},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.200893Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:f00e6e8c95cb370544c77b41b15de5a2991b1e08d8b17a937da5b54d271b2f3e","observation_id":"9d31457d-ca1c-45b6-9931-b57d962e2254","resolution":{"observed_at":"2026-08-07T15:38:00.866802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:38:00.586470Z","title":null,"venue":null,"work_id":"cdf32068-9a14-42e6-aab7-0095883cf360","year":1982},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.263407Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:81d0ca5f248e8d9b82a564e3dafd83552f4a34ee586547365665786fd92d7ea0","observation_id":"d6b7111f-1f29-4798-b106-7d05a95b1918","resolution":{"observed_at":"2026-08-07T15:38:00.665268Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:38:00.420212Z","title":null,"venue":null,"work_id":"274347a8-1b7f-46a1-b39c-3973f85356ef","year":1984},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.343840Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:262ccdd4f96c1d44ca42faa7b47d32d9ff7aef37d404e0e6834f5882f2ad64b7","observation_id":"23f4dee1-0b1f-4db7-976c-e11af0970005","resolution":{"observed_at":"2026-08-07T15:38:00.491247Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:38:00.210994Z","title":"Detection of traffic signs in real-world images: The german traffic sign detection benchmark","venue":null,"work_id":"e0826e19-ec7e-4ffb-8706-059dbcdeda92","year":2013},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.401033Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:682132af5a865be7568828e97cdcc9fac3834168872da0d993776ad7c49f20fe","observation_id":"9d32ecd8-17a6-4109-b7ce-36a279368338","resolution":{"observed_at":"2026-08-07T15:38:00.291872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:38:00.050732Z","title":"Backdoor defense via decoupling the training process","venue":null,"work_id":"d74bed90-83da-4d59-ad61-9bf0abbaf47e","year":2022},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.464096Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:4c57a893b93e1f4960ec094847018f8190f97ffb63d185d5a45cc38e208e1dc7","observation_id":"3e9ec9da-055f-4eb0-88b6-2591d17172f4","resolution":{"observed_at":"2026-08-07T15:38:00.149603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:59.867224Z","title":"Beitrag zur theorie des ferro-und paramagnetismus.Zeitschrift für Physik, 31(1): 253–258, 1925","venue":null,"work_id":"97e0c7e1-c0ec-4fe0-a904-e55935e4c2d8","year":1925},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.521423Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:645641d9c62eac4a2837963af216bf6e811435e95c45ca415a1f5433bf89137e","observation_id":"a64a67b9-1273-459b-9e65-3adf0f45d6af","resolution":{"observed_at":"2026-08-07T15:37:59.954847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:59.650589Z","title":"Ising ferromagnets and antiferromagnets in an imaginary magnetic field.Physical Review E, 105(5):054112, 2022","venue":null,"work_id":"5f0db819-bd18-41df-93dc-febe56a42ace","year":2022},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.597038Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:7a706c5e04e59b5c9b32e4737228a3cfe9ff56822b74d1f617d705db9b253db9","observation_id":"a7532cb6-21ff-424c-8af4-c00ad1da5993","resolution":{"observed_at":"2026-08-07T15:37:59.760072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:37:53.677198Z","title":"and Hinton, G","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.677198Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:7cfe96d80e146caffb0a2676375cc6141ad132e50f15d24c4c274da359f9bf33","observation_id":"ea99c7d8-6eeb-4cdb-9b92-bb3e24cd153a","resolution":{"observed_at":"2026-08-07T15:37:53.677198Z","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":"2026-08-07T15:37:59.456836Z","title":"Baybfed: Bayesian backdoor defense for federated learning","venue":null,"work_id":"bae74036-63eb-4e53-97f7-487be8d2d89e","year":2023},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.735535Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:1ce5297ea5d89e7b6ec86b55bf2938307c8fdb6a0489c400d1856e3079e780ef","observation_id":"6c6affb8-b389-4481-b621-675fdf855b9d","resolution":{"observed_at":"2026-08-07T15:37:59.540548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:59.257825Z","title":"Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324, 1998","venue":null,"work_id":"66cfd404-0dbf-4037-adf2-6a94c1f9dfa7","year":1998},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.793173Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:2e56eef1a11483fe6680fddcfdd3379580794a76c5aa5911b704cb64e9775208","observation_id":"3db47071-07fa-40f5-83f0-e1b5c47e026b","resolution":{"observed_at":"2026-08-07T15:37:59.346406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:59.078353Z","title":"and Lin, S.-L","venue":null,"work_id":"62fee807-4474-4b22-8c5f-e861de9be0d6","year":2006},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.874517Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:9a117ead1921df8ddd488dd9efc52bcb5252c42e6a3e6a1c50592014bf85b310","observation_id":"2adcdc25-c215-424f-8221-c8b9eea924c0","resolution":{"observed_at":"2026-08-07T15:37:59.141144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:58.887033Z","title":"and Yuan, S.-K","venue":null,"work_id":"f2edb40b-994c-4096-97d9-fe82e22e6011","year":1999},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:53.931377Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:e6daba151528a07addfc226259ee791be5b5438a114fb00c3b2f991335969b4f","observation_id":"a74a5b24-c3cf-4c03-9a73-de67c7b1247d","resolution":{"observed_at":"2026-08-07T15:37:58.966139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:58.651551Z","title":"Detecting backdoors during the inference stage based on corruption robustness consistency","venue":null,"work_id":"981232b0-b5d1-46a8-8553-fe2f77e25388","year":2023},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.002867Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:c0e58d0dbb3413ac52ef13f185426048d5f3666cf4c33663e8f784b8497466e7","observation_id":"fae2b70e-4c1d-4161-9d2f-b14ed8d47ffe","resolution":{"observed_at":"2026-08-07T15:37:58.753381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:58.505804Z","title":"The \"beatrix\" resurrections: Robust backdoor detection via gram matrices","venue":null,"work_id":"bce4b0d5-bf1e-466b-9d36-a24c153bbaed","year":2023},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.082621Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:fe42ea07d7c531707f15b1d2e1e52050673c85fcd5b3ca30f6760766e387e3fe","observation_id":"b2ed6f59-4f1b-4ff8-9dce-a53079cd5c29","resolution":{"observed_at":"2026-08-07T15:37:58.564459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:58.415360Z","title":null,"venue":null,"work_id":"d84c885b-5050-443a-af4a-343f3d1c93e7","year":null},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.142129Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:1e4c25f98540be3590e3cd17ec8cafd7c96de2c36db62953d5f2fd3cf66fe3d3","observation_id":"1cd9a62c-0df0-4e35-aef9-df7b24d73d7d","resolution":{"observed_at":"2026-08-07T15:37:58.465964Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:58.235640Z","title":null,"venue":null,"work_id":"b62d9f11-e631-4bfa-96fd-e1cf6a480b71","year":2021},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.149033Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:d8eb2541685d3f3e4a1644e914cb5193f065e46ff738c1f92699ee4176e6f0c1","observation_id":"05dec05b-9f1d-4887-a29c-b7d4f467e974","resolution":{"observed_at":"2026-08-07T15:37:58.304713Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:57.965885Z","title":null,"venue":null,"work_id":"171f43e0-8492-4917-9f92-e3426ca3d378","year":2020},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.153840Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:4a330f7bed2244dafbd1edb91bbeed7b90c0d11191ef16091963799db5bfef41","observation_id":"aa93670f-9d34-4d50-a487-4e5a6d218676","resolution":{"observed_at":"2026-08-07T15:37:58.123629Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:57.804046Z","title":"D., Rieger, P., Chen, H., Yalame, H., Möllering, H., Fereidooni, H., Marchal, S., Miettinen, M., Mirhoseini, A., Zeitouni, S., Koushanfar, F., Sadeghi, A., and Schneider, T","venue":null,"work_id":"fd123fa3-dcb7-467a-9ba3-bb1893c63c66","year":2022},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.159576Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:959cd05945fc33c012bca82546c3b7137e39068276fb51dbcd2efa00795d5b8f","observation_id":"fdc9f123-46a2-400b-a75c-2ad326356a34","resolution":{"observed_at":"2026-08-07T15:37:57.875986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:57.497215Z","title":"A threshold selection method from gray-level histograms.IEEE Transactions on Systems, Man, and Cybernetics, 9(1):62–66, 1979","venue":null,"work_id":"5e29c7ff-f881-42d7-a02d-ad44fe2e11ce","year":1979},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.197497Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:e2f0d2eeeae10912642de16693a7c517636b03f185ff6d263bd5351a92b8dff9","observation_id":"648371ab-1646-415a-ae4d-bc22b577f57b","resolution":{"observed_at":"2026-08-07T15:37:57.643248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:57.252776Z","title":"T., Wu, T., Mahloujifar, S., and Mittal, P","venue":null,"work_id":"bcb4ad6e-a561-473e-aaa0-65b4b4b2b775","year":2023},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.287781Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:bd56c19dfa0ff7ff4679a52208d4c6e5ef65a547e0f74efd63b4c72ceb7cdb1b","observation_id":"ebc43943-3a80-4b87-90b9-e750eceb7987","resolution":{"observed_at":"2026-08-07T15:37:57.368777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:57.008699Z","title":"P., Kopp, M","venue":null,"work_id":"56035a5d-5bed-4ad7-825f-88eb0feeb2e8","year":2021},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.384748Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:313012b5f40c6ee2efabfe43b2044e07c41e1bb0c00cc0a0470fa3659750c486","observation_id":"91d16cc9-6c73-4409-ad6b-0d551a002adb","resolution":{"observed_at":"2026-08-07T15:37:57.115557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:56.702754Z","title":"Backdoor suppression in neural networks using input fuzzing and majority voting.IEEE Des","venue":null,"work_id":"a2f26db9-9d72-4bbe-a519-51ed607155ec","year":2020},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.496201Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:9583887127840255030b0c358a0c2ad9dc09524e7a87fc84688228af28c1a9e5","observation_id":"23c90e6a-461b-402e-86be-d19adfef4a52","resolution":{"observed_at":"2026-08-07T15:37:56.820787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:56.377005Z","title":"Demon in the variant: Statistical analysis of dnns for robust backdoor contamination detection","venue":null,"work_id":"fc5dd5e8-6ab4-4e96-86ba-3197de02480a","year":2021},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.578286Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:5c156acf67839aa291de0fbabe84e78e821f70208c826f3dad3d9de3e6f18acd","observation_id":"87c62a88-82d7-43e6-ad37-f60a06cb7adc","resolution":{"observed_at":"2026-08-07T15:37:56.511162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:56.037104Z","title":"Spectral signatures in backdoor attacks","venue":null,"work_id":"4636529c-25bb-48cd-989c-ba2d6ae0193b","year":2018},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.667803Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:5721005fe3122de5e6645c2c48e7e4e8fe18ffb5f1f0b8895a1fe0237e76fd63","observation_id":"6a1cc961-3635-4f23-90ef-c6600af99a4a","resolution":{"observed_at":"2026-08-07T15:37:56.170929Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T15:37:55.803752Z","title":null,"venue":null,"work_id":"5b4be873-5e70-47f4-8836-c138f49d0414","year":2019},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.775208Z"},"links":{"citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:9af5d090c69c4ab60ae22df24bd167cb54e5dc4c214effb9f151c87951456298","observation_id":"1cc02d98-6940-4827-8b5b-74a5f7009088","resolution":{"observed_at":"2026-08-07T15:37:55.890636Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.19845","last_updated":"2024-07-29T09:57:03Z","snapshot_observed_at":"2026-07-06T18:53:13.875335Z","submitted_at":"2024-07-29T09:57:03Z","title":"BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.19845","snapshot_observed_at":"2026-08-07T15:37:54.876072Z","title":"Backdoorbench: A comprehensive benchmark and analysis of backdoor learning.CoRR, abs/2407.19845, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:54.876072Z"},"links":{"cited_paper":"/paper/2407.19845","citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:ba4a90ea9a3f37e4640d1fae4c40506ca7c8808251f0ae89fb1b9816088f4cfd","observation_id":"2cba6008-4cb1-4895-8938-098b6b53832f","resolution":{"observed_at":"2026-08-07T15:37:54.876072Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-07T15:37:55.002297Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms.CoRR, abs/1708.07747, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:55.002297Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:1d89ff697e890f0e8e2b78bcd6c0881bf5e70c79b0bb0bc841ffc158f359f204","observation_id":"1ae5fb4f-28a0-44be-8a37-ccb7bb8a8427","resolution":{"observed_at":"2026-08-07T15:37:55.002297Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.06230","last_updated":"2024-05-28T03:36:40Z","snapshot_observed_at":"2026-07-06T16:59:40.293700Z","submitted_at":"2023-12-11T09:17:33Z","title":"Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks","version":2},"cited_work":{"arxiv_id":"2312.06230","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.06230","snapshot_observed_at":"2026-08-07T15:37:55.344909Z","title":"Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks","venue":"cs.CR","work_id":"11d830ab-482f-4c6b-8235-42c0722fa6e7","year":2023},"citing_paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T15:37:55.151302Z"},"links":{"cited_paper":"/paper/2312.06230","citing_paper":"/paper/2505.14531"},"observation_digest":"sha256:2f34bd5fea215d9a78a308d444847963184a68cb8e30359344df135a30a574ea","observation_id":"501d6c92-3305-41bf-a945-02e386bfdb66","resolution":{"observed_at":"2026-08-07T15:37:55.500774Z","resolver_source":"local_arxiv","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.14531","last_updated":"2025-05-20T15:51:17Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T15:30:21.370675Z","submitted_at":"2025-05-20T15:51:17Z","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":26},"total_outbound_references":39},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2505.14531."}