{"as_of":"2026-08-04T15:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e839cb8b12b25e5e0554b5e382db5071c0a842500aab89b6e0acc68c7831636a","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-18T19:32:49.650689Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.08748/citation-record","integrity":"/paper/2509.08748/integrity","json":"/paper/2509.08748/citation-record.json","paper":"/paper/2509.08748"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Evasion attacks against machine learning at test time","venue":null,"work_id":"98b491b9-9d77-475b-9a4a-4afa7b20aeaa","year":2013},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:6d3c53b5d3dcdb3b8d61d846c84536bc2228b4942c63dceac4340ecd845e3cad","observation_id":"127b0590-7eae-44bc-a5b3-369aa3d10131","resolution":{"observed_at":"2026-05-18T19:42:50.483683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Goodfellow, Jonathon Shlens, and Christian Szegedy","venue":null,"work_id":"2f118d86-bc8d-471f-9c51-f49aee3acd81","year":2015},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:d2379c8eda8e4cd807a734ef37c30ff7b082554f321e8c7ab506f57e0aad75d8","observation_id":"5590df51-af74-40c1-9535-4e4015031309","resolution":{"observed_at":"2026-05-18T19:42:50.553437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"LESSON: multi-label adversarial false data injection attack for deep learning locational detection","venue":null,"work_id":"035cb314-7d23-48fe-883f-e6b671b3941a","year":2024},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:c1790ccef57e5aacfeb3b99e95a65774bda47fbc7a4d105236f7dfa3ad7fd644","observation_id":"adab3adc-9558-471e-a4cd-bf12a121c846","resolution":{"observed_at":"2026-05-18T19:42:50.470956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Poisoning attacks against support vector machines","venue":null,"work_id":"f93e6da8-ce02-4144-98bd-0f63b7ab9b3f","year":2012},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:cf963d3cae00c360a963b9e194ce2043d26f7ccadd6fbb33b98bead2ef701090","observation_id":"6ebc646d-50a0-4565-b69c-71dd52e2a29b","resolution":{"observed_at":"2026-05-18T19:42:50.442533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"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":"1708.06733","doi":null,"metadata_source":"pith","pith_arxiv_id":"1708.06733","snapshot_observed_at":"2026-07-11T00:47:43.661742Z","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","venue":"cs.CR","work_id":"7b1cd3ac-9abd-4579-8d13-c75d30c83a5f","year":2017},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"cited_paper":"/paper/1708.06733","citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:022d7e9b23ffa1a63d2bcfee64ae1087432d9b08daf91355efc54ef162ff68f3","observation_id":"b4f34efd-fd66-4882-bdc3-b6250049208a","resolution":{"observed_at":"2026-05-18T19:36:48.209647Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2021.312534","doi":"10.1109/tcyb.2021.3125345","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Joint adversarial example and false data injection attacks for state estimation in power systems.IEEE Transactions on Cybernetics, 52(12):13699–13713","venue":null,"work_id":"153aeb3b-f061-47c1-b5ec-be2faf445656","year":2022},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:b9c5715f5a3198cc0772fe8d5a04c43a8adbbe85013ff84173ce3f44497288ab","observation_id":"9a537ff7-1d26-400f-9898-8395202bca2b","resolution":{"observed_at":"2026-05-18T19:36:47.391062Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"When federated learning meets privacy-preserving computation.ACM Computing Surveys, 56(12):1–36","venue":null,"work_id":"9740069a-3c33-426c-9d7d-986ced297271","year":2024},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:3384fb01c0688aff2caa3125f90a5d727430b94c46bfaf15de8aad686781324a","observation_id":"76d95260-43fc-4db5-b532-e30742f4f1a3","resolution":{"observed_at":"2026-05-18T19:42:50.516875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.10760","last_updated":"2020-08-02T08:38:25Z","snapshot_observed_at":"2026-07-06T09:40:34.148418Z","submitted_at":"2020-07-21T12:49:12Z","title":"Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review","version":3},"cited_work":{"arxiv_id":"2007.10760","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.10760","snapshot_observed_at":"2026-07-04T17:09:58.871595Z","title":"Backdoor attacks and countermeasures on deep learning: A comprehensive review","venue":null,"work_id":"883e572c-19ae-48ac-9193-b0f27f66dfdb","year":2007},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"cited_paper":"/paper/2007.10760","citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:268a5ac2c481084e017195566a7b5146f808851b9e64fc4b420a3c43b27756c7","observation_id":"63385805-bc46-497f-bf47-0691444f6601","resolution":{"observed_at":"2026-05-18T19:36:48.200549Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Wild patterns reloaded: A survey of machine learning security against training data poisoning.ACM Computing Surveys, 55(13s):1–39","venue":null,"work_id":"e9c7c9f8-af33-4cfb-8531-a9062a8dede1","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:41e5e1d6cc13d2ac996a8af0f801c4f7f86566facfb9f5d3efcad28b1fecb9b2","observation_id":"83f6d024-633a-4386-bb08-955903aa93bc","resolution":{"observed_at":"2026-05-18T19:42:50.528328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2024.349229","doi":"10.1109/tsusc.2024.3492290","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Evade: Targeted adversarial false data injection attacks for state estimation in smart grid.IEEE Transactions on Sustainable Computing","venue":null,"work_id":"dba575f8-dfdb-4441-94e0-5a331a30401e","year":2024},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:2c18ad08c7c2d30f75ff5a26d74b8f29657a0c39c9640de73f2b833445071c37","observation_id":"6a85cedd-eb62-452c-a585-619a3a5cfad8","resolution":{"observed_at":"2026-05-18T19:36:47.412569Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An overview of backdoor attacks against deep neural networks and possible defences.IEEE Open Journal of Signal Processing, 3:261–287","venue":null,"work_id":"3df8e37e-22c3-496d-9c0e-25ab1353f7ff","year":2022},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:6c800fbc5eb3657484c4ca3081e941c0992620cf5514b36bc6035b63b136892e","observation_id":"c72204c5-903d-4030-a33e-fbcbc9fdffb6","resolution":{"observed_at":"2026-05-18T19:42:50.502626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Molloy, and Biplav Srivastava","venue":null,"work_id":"2f3e4b6f-032d-4de5-ae7b-00e3ba24ea4f","year":2019},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:54e00104b9857452dbdf40eeed8b831fd64fc7d04208704516167a3707568c8e","observation_id":"5d4b1361-0631-434a-a184-e3d3343018ff","resolution":{"observed_at":"2026-05-18T19:42:50.450223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Miller, and George Kesidis","venue":null,"work_id":"8c09a015-192d-408f-a158-73dea8006330","year":2019},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:f46b99acb8166e40ed420b9c2b5e528dddc5d21ed9d64c886c90602e22840528","observation_id":"3c788749-0aa7-42e6-ba3e-0204acacdd03","resolution":{"observed_at":"2026-05-18T19:42:50.524848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Demon in the variant: Statistical analysis of dnns for robust backdoor contamination detection","venue":null,"work_id":"33f562a7-4fce-42f2-a72b-d0396608e3eb","year":2021},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:782bf1a85e0a3f7656a4e3a559e5b0f4cfe8d0210c2b410d0ec3a0751088c63e","observation_id":"6b945cde-3a78-4676-8c60-d123989602ae","resolution":{"observed_at":"2026-05-18T19:42:50.533029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Training with more confidence: Mitigating injected and natural backdoors during training","venue":null,"work_id":"9b887095-ae1f-4f85-b678-27f2276fc04d","year":2022},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:333af6799bb9ab8f9164c73819f9280ce59d723baae07616c1c8f02d7bf063d8","observation_id":"22db3434-ed62-4631-819d-269b15efeb4b","resolution":{"observed_at":"2026-05-18T19:42:50.538397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2023.332942","doi":"10.1109/tifs.2023.3329426","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Universal detection of backdoor attacks via density- based clustering and centroids analysis.IEEE TIFS","venue":null,"work_id":"5a5df0fb-7a4b-4d6d-826b-fda4670d4e73","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:f5bcfba51178fa8d00d22e792a9b7357a710eabdf733a150bac88c0e5d3db89d","observation_id":"48b28b6b-ba39-4b65-8669-b53657047119","resolution":{"observed_at":"2026-05-18T19:36:47.427078Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The \"beatrix\" resurrections: Robust backdoor detection via gram matrices","venue":null,"work_id":"2b65c55e-a1df-4c6a-91f5-f9bc40b4d427","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:d3c0b1f144d8d1176f2e981891964362cd6556d9e4ea195733af4d53a5f9f706","observation_id":"374d2c0d-df32-4f56-bbab-5bf1725b82b2","resolution":{"observed_at":"2026-05-18T19:42:50.464469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anti-backdoor learning: Training clean models on poisoned data","venue":null,"work_id":"42989a61-dcca-43df-8768-bdf47c3a4c28","year":2021},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:ed51d712aafea65bd46d7c4298dee3faff3a3190edd02c810a425640723941fb","observation_id":"0253d047-6619-49a0-a1de-e43a0a9d7ba8","resolution":{"observed_at":"2026-05-18T19:42:50.542576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Progressive poisoned data isolation for training-time backdoor defense","venue":null,"work_id":"040cca59-5770-4728-bd89-48c74f7dc9c5","year":2024},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:7f1bdbeb8764df67adee0891651d9fd5731f5d76fc7a867ca4e1e7b62ef92f51","observation_id":"e5c79d20-3539-41eb-97a3-ecd010e5a16a","resolution":{"observed_at":"2026-05-18T19:42:50.492447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Backdoor defense via adaptively splitting poisoned dataset","venue":null,"work_id":"5767816b-a2bf-4039-89c2-267d1c7e1f90","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:2d47b72f016edfcb548bf8e63d6b9d086e163adadd0c0f3ac586c180b7885027","observation_id":"853f5de6-84c8-4b01-956b-1e33ae67f934","resolution":{"observed_at":"2026-05-18T19:42:50.453581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Backdoor defense via deconfounded representation learning","venue":null,"work_id":"88b15d3d-2709-49f2-9eab-e3541d4da726","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:85257bccd0465844bb69f9a765f40a8ab483b997abc6c9a9f8919d5bd7190e5a","observation_id":"53da56fc-1130-4be6-b035-207577abb12d","resolution":{"observed_at":"2026-05-18T19:42:50.556442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Backdoor defense via decoupling the training process","venue":null,"work_id":"63179da0-7b9a-47cb-ab07-a79f2f546f46","year":2022},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:fd7f26daade62b8994c9be3636f8aa70c10f7ca1c93cbea83621ec0ecf0b7575","observation_id":"e39ea733-6096-4491-863f-0ec71f768a91","resolution":{"observed_at":"2026-05-18T19:42:50.477125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Effective backdoor defense by exploiting sensitivity of poisoned samples","venue":null,"work_id":"fb2a75f0-9c63-4227-984a-e2daecc149a2","year":2022},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:128ea42cc4a3295d4f29acc59da05e7574f694693e25290d68c5d02ec598fa67","observation_id":"adef28e8-3824-4746-9f6c-a61f18244b31","resolution":{"observed_at":"2026-05-18T19:42:50.431304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards a proactive{ML} approach for detecting backdoor poison samples","venue":null,"work_id":"77dca6a9-8a62-486f-9f67-8ad838b873fe","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:855f5f44c98cfc334d1d09be402907b84d86e1aa9c074be55804e4ec5cc2b152","observation_id":"a12e9c79-e9c7-43b3-b451-452a0fe9a446","resolution":{"observed_at":"2026-05-18T19:42:50.434268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The victim and the beneficiary: Exploiting a poisoned model to train a clean model on poisoned data","venue":null,"work_id":"ddf2d863-54d2-43d4-9093-2d8786cef260","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:b18cfa8db82ec630e5e30a129490bf7458fb7ef04f26c46860e1f5a7a7d0b09b","observation_id":"ecd8e335-2105-495f-9e7d-5576dae44689","resolution":{"observed_at":"2026-05-18T19:42:50.498657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Bypassing backdoor detection algorithms in deep learning","venue":null,"work_id":"0e5008d1-6292-4d88-9baf-41024a977bf9","year":2020},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:e33bc015e3ac938039e0111171a4dfe2f4fff134d99ca1f7da044ca0e1f5649e","observation_id":"1c3cd6d3-fa28-4a03-8fec-4bc79c123b98","resolution":{"observed_at":"2026-05-18T19:42:50.447527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An embarrassingly simple backdoor attack on self-supervised learning","venue":null,"work_id":"76007f49-090d-4240-86f9-9c543b20d882","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:2e5e0db207c7ed6cd929584c402c622241b376ca873f00410fa0f64f00db38e9","observation_id":"8e67b022-e916-435f-9109-614d4e25ef1f","resolution":{"observed_at":"2026-05-18T19:42:50.479974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The perils of learning from unlabeled data: Backdoor attacks on semi-supervised learning","venue":null,"work_id":"bfb658a3-9261-440c-b89b-28aca75a10e9","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:f2a7a9348ceedc00b83d674432ec6bbb1e3e0491d0d50790cd698567f525d3fa","observation_id":"bdc84830-c72c-4f5b-bcf3-f8b003399cd5","resolution":{"observed_at":"2026-05-18T19:42:50.495495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Revisiting the assumption of latent separability for backdoor defenses","venue":null,"work_id":"80083b3a-6321-4569-9871-e105057b3ec2","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:138ca134917dfba0bbecc63b402c2836c33f088da32ad23ebc9d8a421d94adae","observation_id":"75eb1818-5128-4494-b6fa-2d10837bb736","resolution":{"observed_at":"2026-05-18T19:42:50.437643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sinkhorn distances: Lightspeed computation of optimal transport","venue":null,"work_id":"95dddf2e-7e08-493d-a161-a66aa7c615e6","year":2013},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:7d1b5dab48efc28ce5f7aab7660e1281bab17c79fca2ca983661c711497e162f","observation_id":"405cf7f7-8fd3-419c-910f-66c8fa4a3c94","resolution":{"observed_at":"2026-05-18T19:42:50.489748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.03426","last_updated":"2020-09-18T01:56:41Z","snapshot_observed_at":"2026-08-02T15:32:07.466568Z","submitted_at":"2018-02-09T19:39:33Z","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","version":3},"cited_work":{"arxiv_id":"1802.03426","doi":"10.1037/adb0001138","metadata_source":"pith","pith_arxiv_id":"1802.03426","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","venue":"stat.ML","work_id":"54c15172-6304-4008-a3b6-c4cc0803c054","year":2018},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"cited_paper":"/paper/1802.03426","citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:23dea891e89f206562063d82665ded6a39ecabe305f4b0fb38a89b610fc2cd0c","observation_id":"d94044dc-d9e0-48af-90f3-ec6864e23da2","resolution":{"observed_at":"2026-05-18T19:36:48.218037Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-05-25T15:24:07.856203+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T15:24:07.856203+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1109/cvpr.2016.90","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T09:16:59.350888Z","title":"Deep residual learning for image recognition","venue":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","work_id":"b353bda2-591d-479a-9c8b-22dfcba12431","year":2016},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:e08d720a5ebe298f6372790098b484f23eafa98de8d71eaefcbd5e63f7979a98","observation_id":"d755d38a-3ae4-49a3-a661-d9d45d2bc629","resolution":{"observed_at":"2026-05-18T19:36:47.400476Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-03T17:08:01.374485+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-03T17:08:01.374485+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unsupervised learning of visual features by contrasting cluster assignments","venue":null,"work_id":"d10ffa39-ebd6-477b-9631-a2ca1dacc917","year":2020},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:84ff3ae8b2c200888f85a0010b3b0b5026a87cc2317a07f83d95bb9fc7a2c082","observation_id":"c1583bea-c538-4722-bab1-981b7bc24208","resolution":{"observed_at":"2026-05-18T19:42:50.550498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Progressive poisoned data isolation for training-time backdoor defense","venue":null,"work_id":"dd3b679f-c7ae-451a-8202-ae089335176e","year":2024},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:aba4416c23649dadb81ec3d472d0c7de72e9c37e3fbf0bf3ecd457fafa3507f3","observation_id":"558dbc3d-5d76-4de6-be44-9a09a4379798","resolution":{"observed_at":"2026-05-18T19:42:50.487083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":"98da514c-605e-429e-b456-71ef7bd2d985","year":2015},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:bab6a8dc61a24e97a4dadafb1ebce1ca4c57c75dc6fab461f8d3a49a64ee6ae9","observation_id":"67c3289b-afe8-482a-9498-f8dec55f0edd","resolution":{"observed_at":"2026-05-18T19:42:50.505734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Weinberger","venue":null,"work_id":"315c02de-703e-4448-83d8-deabcca0c62b","year":2017},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:d52262f09dfddd59b91eb621bac39830e212c0cfb0a82163cca6062a8d1d4f84","observation_id":"f898f685-c033-4617-b2ce-13a22f8af5ad","resolution":{"observed_at":"2026-05-18T19:42:50.458926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"7f11eb30-07c2-46c3-ac99-f238e0aa429e","year":2021},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:e25b212d0c45b8a6f7c25ea9ee7ce9e15de8d4c81b1c1ad2b5b0a07e3dd1a422","observation_id":"6280be4d-a7c5-4557-8c43-330889cf8f30","resolution":{"observed_at":"2026-05-18T19:42:50.461654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Wanet - imperceptible warping-based backdoor attack","venue":null,"work_id":"f84e5a16-df49-4655-b05d-dfdae630c262","year":2021},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:8f823e8ed857c13a32a55778ecbf81be13586f36c76b01296a08eedb82637d97","observation_id":"69e88d7a-8e75-4ee7-b4cd-fe0e1df90eff","resolution":{"observed_at":"2026-05-18T19:42:50.509551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Can you hear it? backdoor attacks via ultrasonic triggers","venue":null,"work_id":"c2212729-579a-41fc-a628-3e56cf49ad46","year":2022},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:ae53bde2fefa1d9efd76f12020dd632e331ba83d3354bc7e2d748ceeeee26ddd","observation_id":"9dc933e9-2d39-4a73-b716-6644459060f6","resolution":{"observed_at":"2026-05-18T19:42:50.456363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"COMBAT: alternated training for effective clean-label backdoor attacks","venue":null,"work_id":"a7a1cf71-b716-449a-8786-7152cdfbd97d","year":2024},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:92b68cad06dd3c430a7916f4ee4f6a077e90ab8367ae7f95c6e63b7ca7fae63f","observation_id":"56f4b7bd-e753-43ab-9007-757f584937e5","resolution":{"observed_at":"2026-05-18T19:42:50.473597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lotus: Evasive and resilient backdoor attacks through sub-partitioning","venue":null,"work_id":"33758b35-12a1-41b5-8e6b-d64ac01861cb","year":2024},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:32cfac820a6f0bda51cab399db3f5c662f233a47b33cc52396a12d33620347eb","observation_id":"0d9d7a46-ced7-417a-96b5-4166c6a35133","resolution":{"observed_at":"2026-05-18T19:42:50.547255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Narcissus: A practical clean-label backdoor attack with limited information","venue":null,"work_id":"5d55605b-a8ae-48f7-8346-a50911cc56d8","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:0e32acbc6052261e9da044769ba847d571f5dd6d9e29efc46d2bc9fa06d23a5e","observation_id":"233332f1-222d-47c4-93ef-4289868b9bc9","resolution":{"observed_at":"2026-05-18T19:42:50.521588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ff35c3b7-d875-4511-8520-48f2279f3ada","year":2020},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:f2373596a2a375a9a654404ca8b663c66284b9484161c7e67e38b89df7852354","observation_id":"36425ec6-f3bb-4d2a-be66-46788fd0b3af","resolution":{"observed_at":"2026-05-18T19:42:50.513147Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03209","last_updated":"2018-04-09T19:58:17Z","snapshot_observed_at":"2026-07-06T06:32:32.083176Z","submitted_at":"2018-04-09T19:58:17Z","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","version":1},"cited_work":{"arxiv_id":"1804.03209","doi":"10.48550/arxiv.1804.03209","metadata_source":"pith","pith_arxiv_id":"1804.03209","snapshot_observed_at":"2026-07-10T15:47:23.257270Z","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","venue":"cs.CL","work_id":"f4d53a51-5741-47e1-b328-d6503065d1bd","year":2018},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"cited_paper":"/paper/1804.03209","citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:956f68fe60135f01740fd2637c7ee15885a9b8066eec5148c1a9bbe4dd8c04b6","observation_id":"369b2986-6add-4fe2-9bf7-ed70b4aafe08","resolution":{"observed_at":"2026-05-18T19:36:48.223547Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A temporal chrominance trigger for clean-label backdoor attack against anti-spoof rebroadcast detection.IEEE TDSC, 20(6):4752–4762","venue":null,"work_id":"0a4bbc25-078d-4636-bee7-bbd4bf9d12de","year":2023},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:0a32e8736c1351a5af1434926d766b6f9b0c2129f2037e41b4f0f9a2759630d8","observation_id":"9639dbfd-a51c-40de-9fa1-35e4d3e8c631","resolution":{"observed_at":"2026-05-18T19:42:50.467891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07863","last_updated":"2024-04-11T15:55:53Z","snapshot_observed_at":"2026-07-06T17:58:56.081219Z","submitted_at":"2024-04-11T15:55:53Z","title":"Backdoor Contrastive Learning via Bi-level Trigger Optimization","version":1},"cited_work":{"arxiv_id":"2404.07863","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.07863","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Backdoor contrastive learning via bi-level trigger optimization","venue":null,"work_id":"7bf44848-86f1-4e66-9e40-06a526d5615e","year":2024},"citing_paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-18T19:32:49.650689Z"},"links":{"cited_paper":"/paper/2404.07863","citing_paper":"/paper/2509.08748"},"observation_digest":"sha256:6c35493c7ee28d16f16eb6f9a8902c625a3cb150f8bae30f7d54d66033072d5e","observation_id":"17679dfb-5f84-45bd-8688-bd21703de4c6","resolution":{"observed_at":"2026-05-18T19:36:48.195662Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.08748","last_updated":"2026-04-26T09:02:25Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-07-06T22:27:44.275482Z","submitted_at":"2025-09-03T14:41:54Z","title":"Prototype-Guided Robust Learning against Backdoor Attacks"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":9,"verified_fuzzy":36},"total_outbound_references":46},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2509.08748."}