{"as_of":"2026-08-12T23:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d1d78ee825afc0c96b1d0fcbdacba68c846952ec9b9e237e1b5278500a679b61","coverage":[{"denominator":79,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":79,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T00:44:59.186709Z","state":"measured"},{"denominator":81,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":81,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:31:41.306000Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-22T15:34:57.732409Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19354","snapshot_observed_at":"2026-08-10T14:31:41.306000Z","title":"Federated hybrid training and self-adversarial distillation: Towards robust edge networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15257","last_updated":"2025-04-09T14:55:25Z","snapshot_observed_at":"2026-08-12T11:49:43.799209Z","submitted_at":"2025-01-25T16:04:29Z","title":"Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligence","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T14:31:41.306000Z"},"links":{"cited_paper":"/paper/2412.19354","citing_paper":"/paper/2501.15257"},"observation_digest":"sha256:555d870682c2b8b710eab90ec0be5e29363027f602eaf5aa9616036df9ce964d","observation_id":"ac4901b7-317f-455c-a4e0-ac21e33da83a","resolution":{"observed_at":"2026-08-10T14:31:41.306000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"cited_work":{"arxiv_id":"2412.19354","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.19354","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Federated hybrid training and self-adversarial distillation: Towards robust edge networks","venue":null,"work_id":"6eb71355-41f7-4708-b86f-487927c51ab3","year":2024},"citing_paper":{"arxiv_id":"2505.06907","last_updated":"2026-05-18T08:23:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-11T08:57:53Z","title":"A Survey on Foundation Models for Personalized Federated Intelligence","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-22T15:32:15.293888Z"},"links":{"cited_paper":"/paper/2412.19354","citing_paper":"/paper/2505.06907"},"observation_digest":"sha256:77acd3c036403d0f609f96abf3436e006986de5f64ae7e06bda97f11d97222a2","observation_id":"1a104bbc-4c84-4ab1-a449-68fd9ca21931","resolution":{"observed_at":"2026-05-22T15:34:57.734230Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.19354/citation-record","integrity":"/paper/2412.19354/integrity","json":"/paper/2412.19354/citation-record.json","paper":"/paper/2412.19354"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T00:45:00.154320Z","title":"Edge intelligence: The confluence of edge computing and artificial intelligence,","venue":null,"work_id":"acd232af-eac6-4a88-a6e4-704b8f91ae20","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.873094Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:b84201ede49083237f4201069150d4cdc4a7b5992cab334ba255fb1f054b1ff6","observation_id":"fbae8af7-8414-4109-a7c6-74eaa64210fb","resolution":{"observed_at":"2026-08-11T00:45:00.158509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:45:00.142572Z","title":"Edge comput- ing with artificial intelligence: A machine learning perspective,","venue":null,"work_id":"458c48b7-4159-4b73-b5da-c920e57f93ab","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.878585Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:d2a942b98abedfc2c9c839d760ec2fc24d81f55b5b83302a04ef48a07d9a21ca","observation_id":"2bafdee9-7539-4c24-91e5-fd63a873fd6f","resolution":{"observed_at":"2026-08-11T00:45:00.146880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:45:00.130073Z","title":"Node selection toward faster convergence for federated learning on non-iid data,","venue":null,"work_id":"0bfcfe2b-0cd1-42f7-9108-f1726617e714","year":2022},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.882171Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:656afa6848b6a129f48fef52b2f83981d2e4c70de909accdc14214014d2c3b53","observation_id":"8e18187d-29db-4d8b-bd54-61384fa91fdd","resolution":{"observed_at":"2026-08-11T00:45:00.134151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:45:00.113914Z","title":"Nvm-enhanced machine learning inference in 6g edge computing,","venue":null,"work_id":"c524a911-ddac-4f71-b0b0-fb46925df40a","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.886129Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:e13721397da62ec2553dc8e4e0a6df3fc367a5ef6008b758e3a5829033949fb8","observation_id":"57354caa-acf6-4be3-8ff9-8f0507d349b0","resolution":{"observed_at":"2026-08-11T00:45:00.118081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:45:00.099539Z","title":"Wireless powered mobile edge computing networks: A survey,","venue":null,"work_id":"5d2d7f96-0955-4fa2-b269-3d126f754163","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.889856Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:247d4ef49bc96533c38100330efead379468079811f84c4b2168844026764cb7","observation_id":"f6cd1df6-b15b-473e-92bc-45eb885f1650","resolution":{"observed_at":"2026-08-11T00:45:00.105131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:45:00.085732Z","title":"Mp-fedcl: Multiprototype federated contrastive learning for edge intelligence,","venue":null,"work_id":"d9b24ef6-2d38-4820-b306-7f72531735fc","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.893317Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:b3e9523119256df3dfc637a843908292291ecbd7974e4d521cb6f89257367e71","observation_id":"5eea231f-46d4-4a8f-ac4f-dca057274c83","resolution":{"observed_at":"2026-08-11T00:45:00.089946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:45:00.069317Z","title":"Convergence of edge computing and deep learning: A comprehensive survey,","venue":null,"work_id":"37484397-e667-418e-ae98-7e4cf14be593","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.897943Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:cb9290afcf01df685bb811565693b764a4fadcf4615eb045890adc2023303769","observation_id":"8293d470-1ec7-4291-8521-2fe2f145391a","resolution":{"observed_at":"2026-08-11T00:45:00.074690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:45:00.054998Z","title":"Model aggregation techniques in federated learning: A comprehensive survey,","venue":null,"work_id":"3e9f245f-09d2-49b3-b310-98e4a0e7362c","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.902040Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:a71ccca14c7516a3a71971881fcfeb378b20885e14e240b3529f3be19459628d","observation_id":"8dfab651-7d7f-4b85-8816-f7d723a00398","resolution":{"observed_at":"2026-08-11T00:45:00.059840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:45:00.040090Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":"6ac89272-d708-4a8b-b4b3-b1854c331d47","year":2017},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.905979Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:b3e83e3b077e8c6a3f4994e7a0eb3a961ad7638a9794b6ad7e0266b994709cbe","observation_id":"779df5cd-9c8f-416e-9f32-75b186037e51","resolution":{"observed_at":"2026-08-11T00:45:00.045926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:45:00.025617Z","title":"Fedbn: Federated learning on non-iid features via local batch normalization,","venue":null,"work_id":"85c89b9c-a00b-4b8a-8f44-ec74c920ca40","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.909715Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:308e903112c3bea9c39448a9691fb7613fcdf3bb4cc497a1d3b6e250a5db8cdf","observation_id":"776b4509-9fc8-410d-8248-a7940f564a60","resolution":{"observed_at":"2026-08-11T00:45:00.030219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:45:00.009459Z","title":"Fat: Federated adversarial training,","venue":null,"work_id":"60013ac8-df1e-4c08-ba1b-c9db14e4a496","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.914241Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:bfc842539f5f3c8c882d56a5c3f4adec035b84ad096eb394c2ca4061f107bad5","observation_id":"a04c3e4e-4bb9-4896-963a-45444ea8593c","resolution":{"observed_at":"2026-08-11T00:45:00.014865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.994735Z","title":"Federated robustness propaga- tion: sharing adversarial robustness in heterogeneous federated learning,","venue":null,"work_id":"45e6f9e9-29a7-4f5a-a607-14875ad73a22","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.918176Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:b91c27609ee0fe7ee683efc820bd32f522a700e7528ea13a37919d24b3af493e","observation_id":"99d10cc5-cb32-4199-bb0b-3a6fb843d964","resolution":{"observed_at":"2026-08-11T00:44:59.998617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.983455Z","title":"Privacy and robustness in federated learning: Attacks and defenses,","venue":null,"work_id":"e93d4b29-b282-4f60-96b9-7f0b517ff32d","year":2022},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.922089Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:269a3045ee1612f5ab977451428f9563f50800a19d0ea3ee0e38da46f86ab7d1","observation_id":"b9d043e6-fa4a-4150-9b97-009833e32dfc","resolution":{"observed_at":"2026-08-11T00:44:59.987307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.06776","last_updated":"2024-04-10T06:35:25Z","snapshot_observed_at":"2026-07-06T17:58:05.136931Z","submitted_at":"2024-04-10T06:35:25Z","title":"Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data","version":1},"cited_work":{"arxiv_id":"2404.06776","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.06776","snapshot_observed_at":"2026-08-11T00:44:59.312064Z","title":"Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data","venue":"cs.LG","work_id":"2a2260b3-8dfc-496f-aee2-c8c9bcb9a495","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.925849Z"},"links":{"cited_paper":"/paper/2404.06776","citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:35e4019ae9ee603cd88474871425271f23531ef263dfadada87044ac6657e312","observation_id":"805f7241-3576-4e9f-8af3-5d51ce3ae705","resolution":{"observed_at":"2026-08-11T00:44:59.316590Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.972273Z","title":"A survey on security and privacy issues in modern healthcare systems: Attacks and defenses,","venue":null,"work_id":"e8bfd56d-a4ad-42c9-82dc-522fa4554b0c","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.929915Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:cb767ea802014321a195a5dcccff66f95385b78251dbee36a52e68bed0ed0bd8","observation_id":"87c9d4e3-9abd-47d9-a265-66673de49b14","resolution":{"observed_at":"2026-08-11T00:44:59.976140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.960173Z","title":"Ef- fective adversarial examples identification of credit card transactions,","venue":null,"work_id":"26dab0fe-bb77-48dd-9375-ec804accf650","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.933502Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:b3b856aab157e235009d449bffee6d3d6ee91a6d4842f8508cc030ce8254e632","observation_id":"001ebb1c-84e5-447d-9a5f-0db2279f6cb8","resolution":{"observed_at":"2026-08-11T00:44:59.964377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.949175Z","title":"Explaining and harnessing adversarial examples,","venue":null,"work_id":"ca2a5c74-8de2-467a-ba0e-ecece48028db","year":2015},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.937009Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:1675882bec16c01f2c1ba961e83bd046ca2ebae30d4a40c65646683170e24eda","observation_id":"9dbcb674-64e1-47a7-a62a-6a97f128680e","resolution":{"observed_at":"2026-08-11T00:44:59.953093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.937782Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":"6f85e187-e48f-43a3-8966-6580e88c3f50","year":2018},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.940686Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:2768eeea53a541133aea80e784af55285186bf17917f73de58716e8f38787e44","observation_id":"2b7bb53b-c264-45ee-a631-88500bac6b76","resolution":{"observed_at":"2026-08-11T00:44:59.941778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.926624Z","title":"Federated adversarial learning: A framework with convergence analysis,","venue":null,"work_id":"ae261132-2386-4d21-83d1-7a04650d29e6","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.944303Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:f910a5b3dc1f592271da38aaf0039551d0e9fd8a0754859edd1c7c5bb676b510","observation_id":"813f2785-ed4a-4c9f-bc47-2b7aa3451f6a","resolution":{"observed_at":"2026-08-11T00:44:59.930648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.915158Z","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks,","venue":null,"work_id":"821b6de0-8fcc-4ed5-b0e1-80a6a6a0f798","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.948347Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:5a53f7e667b86b8d47bdaf25499604a5976dd7f0120e6bc3cf5b9e678022fead","observation_id":"b362fc1d-e3af-439a-9c46-fa1db1e39757","resolution":{"observed_at":"2026-08-11T00:44:59.919161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.902818Z","title":"Model-contrastive federated learning,","venue":null,"work_id":"25d3dbfb-cf42-438c-b57c-d850905e2100","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.951550Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:07190e5dbd46414358e491e19a0489d24a62f9abc2aee28517faea595ae10bfa","observation_id":"e195b006-afb5-4171-9dcc-a743b036e9ed","resolution":{"observed_at":"2026-08-11T00:44:59.907166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.889976Z","title":"Federated class-incremental learning with dynamic feature extractor fusion,","venue":null,"work_id":"680c6f7d-a928-4653-8944-10f017e1a8bd","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.956290Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:63d2caa0948675a318448b135d1c766a3dbdcc436657787f211cc8f64fb06cd5","observation_id":"ae0025ae-ee0c-410b-8deb-bd6f7282a111","resolution":{"observed_at":"2026-08-11T00:44:59.894098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.877807Z","title":"Knowledge distillation assisted robust federated learning: Towards edge intelli- gence,","venue":null,"work_id":"e81342d3-3b67-44d5-9ab5-a444f35a591e","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.960029Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:5608d5af898305a20fcab2cd294cecd01740362c0b8531a2092a5fb63d71ab3a","observation_id":"d0020612-7cd9-4ce2-b445-7818b8aac943","resolution":{"observed_at":"2026-08-11T00:44:59.882061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.865995Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":"47ac7e8c-0b8e-4a8d-a108-ffb985b884b2","year":1998},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.963420Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:145e5d4aa19e0ad71848588941a33c5073249304736cf9434e5d56dc5afd2204","observation_id":"3cc6f8f3-51b6-4e03-826a-c318f9cf5cf0","resolution":{"observed_at":"2026-08-11T00:44:59.869948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-11T00:44:58.967435Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.967435Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:a745e1cde210d4a56fce9e7c4c58d823ace2347acbdaa1905c82130751554453","observation_id":"beb77e1e-4488-4969-aa02-c704163c28df","resolution":{"observed_at":"2026-08-11T00:44:58.967435Z","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":"2026-08-11T00:44:59.854878Z","title":"Reading digits in natural images with unsupervised feature learning,","venue":null,"work_id":"f2dd8684-c7bf-40b0-b97c-c7b000492dea","year":2011},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.971987Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:ef64fb13c4a06455758e6ce1aefa0b8557a1c356e2080b9485b49141cfb140e9","observation_id":"49a74ad0-667a-4945-8cd1-82b8b5326dbc","resolution":{"observed_at":"2026-08-11T00:44:59.858607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.843053Z","title":"Geodesic flow kernel for unsupervised domain adaptation,","venue":null,"work_id":"bd3d1777-d888-4fc2-9f7d-4271abfe924f","year":2012},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.976173Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:a7ca8c23ede0c4f4c0ad2be903566c9d1fbf6d4202bf07c9c8143aa135317062","observation_id":"9ff88d53-8592-48e6-bfae-bce4ed4ade33","resolution":{"observed_at":"2026-08-11T00:44:59.847289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:58.979691Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.979691Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:3599e7dcf343d1f8efbb6ec771ab01f0f4569510f80f1ec70dac36d3c8935d81","observation_id":"b083e45f-144b-4cde-8583-ca23f3b1b72c","resolution":{"observed_at":"2026-08-11T00:44:58.979691Z","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":"2026-08-11T00:44:59.825655Z","title":"Handling both stragglers and adversaries for robust federated learning,","venue":null,"work_id":"c2c28390-ccc3-4b9e-8276-39977c64c4c2","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.983028Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:e0be51a19ed9315b624a3a722acf596e3775ec1ebefe29e3d34adfc2538722ca","observation_id":"ce86ca3d-f059-4bdd-8b64-a3be9d82a11c","resolution":{"observed_at":"2026-08-11T00:44:59.829076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.814926Z","title":"Fe- dat: a high-performance and communication-efficient federated learning system with asynchronous tiers,","venue":null,"work_id":"ba41a88c-ab82-40e6-8d05-457d2a4c2b12","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.986835Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:8aecb0220e028b700e801710994870e62223ab6e1aab5cfa4b807250c165db43","observation_id":"93136e32-6af5-44e7-8b6d-a68f335b5aa9","resolution":{"observed_at":"2026-08-11T00:44:59.818868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.803406Z","title":"Cdfed: Contribution-based dynamic federated learning for managing system and statistical heterogeneity,","venue":null,"work_id":"acebbab9-e8f6-4af3-a717-000458bd2d45","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.991459Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:fc3aa1b5754c2cbe35b5cb5b26b70c1b0258394310d4772bb3bf549a8db35d74","observation_id":"c21c0420-4367-419b-9910-491e30b4fb0c","resolution":{"observed_at":"2026-08-11T00:44:59.807204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.792549Z","title":"Federated learning with sparsified model perturbation: Improving accuracy under client-level differential privacy,","venue":null,"work_id":"eaeccd94-8e6d-4ab3-add3-f271e1d36aa2","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:58.995952Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:7b6e3e02dd222b56754a85c340140c7648bdc8d482f31c19483b14cd4f77cee5","observation_id":"be88bc86-7757-416a-834c-64d1a511d550","resolution":{"observed_at":"2026-08-11T00:44:59.796420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.781708Z","title":"Representative kernels-based cnn for faster transmission in federated learning,","venue":null,"work_id":"7fdc896d-a0df-43b6-ae7b-79e06e645ecd","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.000894Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:c17cd4d2cbc2cbdf879650916800a3f658d9cddc9c51eb370afc3ee6754e7af2","observation_id":"6f04b533-6b8b-4613-813b-44b5d910ffe0","resolution":{"observed_at":"2026-08-11T00:44:59.785576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.769719Z","title":"The analysis and optimization of volatile clients in over-the-air federated learning,","venue":null,"work_id":"92020b58-c021-42ca-99b2-0fe83f37b736","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.005035Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:be9998c20234142b67fd4eb748fabd0544f317e83b3c45b93f4de622fa055cd1","observation_id":"82e7d2f2-3708-46f4-a6fe-f6ce817d909c","resolution":{"observed_at":"2026-08-11T00:44:59.773690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.758177Z","title":"Scaffold: Stochastic controlled averaging for federated learn- ing,","venue":null,"work_id":"8cb0042f-7c34-4c17-9a04-79b8511d42b6","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.008826Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:1a82551d565b2ac3d617a8868d4187716a6f1601ff26b5bfbd46d9c946cc07ca","observation_id":"3b987c5b-8dfd-4673-a0d6-b546cd0a8acd","resolution":{"observed_at":"2026-08-11T00:44:59.762456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13214","last_updated":"2023-11-07T02:15:59Z","snapshot_observed_at":"2026-07-06T15:58:08.777051Z","submitted_at":"2023-07-25T02:55:33Z","title":"FedMEKT: Distillation-based Embedding Knowledge Transfer for Multimodal Federated Learning","version":2},"cited_work":{"arxiv_id":"2307.13214","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.13214","snapshot_observed_at":"2026-08-11T00:44:59.283331Z","title":"FedMEKT: Distillation-based Embedding Knowledge Transfer for Multimodal Federated Learning","venue":"cs.LG","work_id":"e31ff14d-48e6-4f46-8e40-18db32cd0228","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.013253Z"},"links":{"cited_paper":"/paper/2307.13214","citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:1004a8cd62127b1ea88a8fa57f6be2742c457de1c126187429dd5fec5ee5d1dd","observation_id":"23457ebc-0998-4fbd-bd66-a7acae0f773b","resolution":{"observed_at":"2026-08-11T00:44:59.289278Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.747398Z","title":"Fedproto: Federated prototype learning across heterogeneous clients,","venue":null,"work_id":"fdfbf3dc-6b93-4440-a73f-1f6964e02ff9","year":2022},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.018073Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:79973bdcbe75e525959f6d95b8b58b8607e2cfa5b5c187b79cb41323a99faadf","observation_id":"874338ab-fb41-484a-aeac-163a4f67f7c5","resolution":{"observed_at":"2026-08-11T00:44:59.751169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.732124Z","title":"Personalized federated learning with moreau envelopes,","venue":null,"work_id":"0a738496-c737-45cb-8d3c-8f67149f0337","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.021582Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:89a842093b2babd1be2e0d5824b415084843ca192c4a83b31fe5ce31db38f95f","observation_id":"2a0ac0e5-2d5e-41aa-ab9e-ddc5dd72c44a","resolution":{"observed_at":"2026-08-11T00:44:59.735824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.720838Z","title":"Multi-level personalized feder- ated learning on heterogeneous and long-tailed data,","venue":null,"work_id":"019ea5f2-8c02-42c0-a8f9-7e2cae1349d3","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.025341Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:036f38aaaab73bbc32aa184534736956b0d75306172df46553bb89ec008deb1a","observation_id":"39a9b6ba-6d36-4e2d-9c55-d24942307bec","resolution":{"observed_at":"2026-08-11T00:44:59.724766Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.709414Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":"b063fa3a-1e0b-4128-9d9b-7822173a5918","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.030324Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:8a0a842b911d03b5b18b2aaccfc5aa38bd449f7f0fe127406546b7fb299a8c59","observation_id":"40a89706-5ba3-408b-9ca2-dc481e64b3f4","resolution":{"observed_at":"2026-08-11T00:44:59.713529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.699036Z","title":"Fedfed: Feature distillation against data heterogeneity in federated learning,","venue":null,"work_id":"0a820f46-6a5f-4948-ab5d-9cfb6784c142","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.034344Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:927d8ac02d12a19826c4a3b0c09214b55180bc50c7a67d7aa0fb0d406814a9f1","observation_id":"97ac5200-a003-4c10-9ec5-e91ad47e2779","resolution":{"observed_at":"2026-08-11T00:44:59.702391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.688451Z","title":"An aggregation-free federated learning for tackling data heterogeneity,","venue":null,"work_id":"e43fdc5a-dbf4-43f5-b8b2-328c8fc0190f","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.038250Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:1f5e8bbd70bec88af65b494ba30a1dce88a3c21d12d7069c6991cc28fdf0b34f","observation_id":"81d58091-6eb8-4316-af19-bed989f08a14","resolution":{"observed_at":"2026-08-11T00:44:59.692027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.677205Z","title":"Dfrd: Data-free robustness distillation for heterogeneous federated learning,","venue":null,"work_id":"97087d89-86bc-49a0-a3f5-2958020b984f","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.042298Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:dc14a6a11d22b88aec823511d77534df7e927e21e8a953d40c6858f5fb41d735","observation_id":"a345dcae-a9b2-4b73-88c6-74994eef13b0","resolution":{"observed_at":"2026-08-11T00:44:59.681485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-11T00:44:59.046556Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.046556Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:63c954cad6b8e03ccc01ea09f207a067261873fe415257abea1c1f789a34308e","observation_id":"e7762b95-414a-4409-8c8e-8cc503bfac5e","resolution":{"observed_at":"2026-08-11T00:44:59.046556Z","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":"2026-08-11T00:44:59.665089Z","title":"Logit standardization in knowledge distillation,","venue":null,"work_id":"b8e723dd-7705-4d2b-97fc-eb0153595c36","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.051285Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:075f239b8eb3cc2467a14c64a1862d1ca138291a3b4f918f2d6ad5abd2be8412","observation_id":"eddfae1e-be13-44d8-bc71-636d28fa9a3b","resolution":{"observed_at":"2026-08-11T00:44:59.669237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.653966Z","title":"Differentiable feature aggregation search for knowledge distillation,","venue":null,"work_id":"f23c0b37-d79a-4a04-be43-4ca6e5074f9c","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.055084Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:309926aae074027f0ca14203f92cfa1047d983633fe7d0538cd95ae41b73c99f","observation_id":"9bc8c379-ed97-4b2c-b77a-7124379b7516","resolution":{"observed_at":"2026-08-11T00:44:59.657875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.641607Z","title":"Data-free knowledge distillation via feature exchange and activation region constraint,","venue":null,"work_id":"ab436ab7-6dc5-4a83-9496-0f78d780f9b4","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.058821Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:f42a9f777514f5514d6c22111c7369dfc49c8da32325c39e299396100c1deb4b","observation_id":"e968ae0f-fad1-4664-98f4-03798479b2aa","resolution":{"observed_at":"2026-08-11T00:44:59.645821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.629650Z","title":"Probabilistic knowledge transfer for lightweight deep representation learning,","venue":null,"work_id":"21e93add-faa7-434c-8003-43200582a5db","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.062669Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:8daf2c786d72e4691ede059a7c3e10366af05b2fcea01cb69e682d5c6f5f903d","observation_id":"e0cd431d-c987-48fd-bb55-7d6604d8abcd","resolution":{"observed_at":"2026-08-11T00:44:59.633734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.617452Z","title":"Pairwise difference relational distillation for object re-identification,","venue":null,"work_id":"303db70b-8ceb-4d57-b4bb-def9ec85cc0f","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.066795Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:76d096fb74c62face37b7b9aa8e87e73c5ff23a498f073dce8fa7034c23fb64e","observation_id":"2c54fb1c-d7a6-4971-b5e7-540b360b7d1f","resolution":{"observed_at":"2026-08-11T00:44:59.621348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.603846Z","title":"Knowledge distillation and student-teacher learning for visual intelligence: A review and new outlooks,","venue":null,"work_id":"7ba473b1-d5ce-4db2-ba9f-6f7d92696d7e","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.070881Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:36335d379da903b0e304ad57e1bd6cc38795e2eab3ffcf7d6a3cfc235770b329","observation_id":"39c80b32-0d7e-4118-adc2-99dc3956e85d","resolution":{"observed_at":"2026-08-11T00:44:59.607739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.08564","last_updated":"2024-04-02T03:42:18Z","snapshot_observed_at":"2026-08-12T12:02:30.541620Z","submitted_at":"2024-04-02T03:42:18Z","title":"Federated Distillation: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.08564","snapshot_observed_at":"2026-08-11T00:44:59.074797Z","title":"Federated distillation: A survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.074797Z"},"links":{"cited_paper":"/paper/2404.08564","citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:24b2600d336a94fce7334665bbabd4e7d69750c02bf1478649ce28566a79c86c","observation_id":"c02637c3-e886-426d-a37e-b1e7bbfb736c","resolution":{"observed_at":"2026-08-11T00:44:59.074797Z","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":"2026-08-11T00:44:59.591429Z","title":"Federated learning with label-masking distillation,","venue":null,"work_id":"a3110977-3cd2-4879-8e10-14cfa35f0f57","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.079093Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:490a816d1760dabc4422a9e6c630627aae0e2c12873f4ff52ac15ed2ae07905c","observation_id":"493a1a1e-c61f-475e-abd7-8edf9aaf470b","resolution":{"observed_at":"2026-08-11T00:44:59.595461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.11006","last_updated":"2020-03-02T12:12:43Z","snapshot_observed_at":"2026-08-04T04:04:57.045893Z","submitted_at":"2019-12-23T18:08:33Z","title":"Data-Free Adversarial Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.11006","snapshot_observed_at":"2026-08-11T00:44:59.083110Z","title":"Data-free adversarial distillation,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.083110Z"},"links":{"cited_paper":"/paper/1912.11006","citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:7c13928fd629f52ab7cab2585f7fea2b0dc089dea41ae2b540bee5b31ff53700","observation_id":"d7388bb6-761b-46c8-a824-1ac5e8559297","resolution":{"observed_at":"2026-08-11T00:44:59.083110Z","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":"2026-08-11T00:44:59.580509Z","title":"Adversarially robust distillation,","venue":null,"work_id":"8187c422-768f-4162-b430-933bc9115a19","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.087682Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:9e6036bc102a5920b1970a334e6739a10921778ae8b2c6f2f599febaf8669918","observation_id":"d2948649-22d7-4834-b697-d79d465baac8","resolution":{"observed_at":"2026-08-11T00:44:59.584549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.569350Z","title":"Delving into the adversarial robustness of federated learning,","venue":null,"work_id":"f47306c8-a029-4b07-8a70-d182579f01b9","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.091602Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:1cc08a86ee5b6b1e1cce62549afb1b56530aa3583db75dbb78c326baf0ae4ade","observation_id":"999dec77-77e6-4003-ae4d-aef0b2878e1a","resolution":{"observed_at":"2026-08-11T00:44:59.573418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.559873Z","title":"Continuous multivariate distributions,","venue":null,"work_id":"a3a6d47e-306b-4180-beb1-68586685033c","year":2014},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.095289Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:6e1821e6a93021c72873ae4557530b44734094c0ae98b5c62f5cbf19678550bd","observation_id":"285bb77c-b7dd-42b2-93ec-e7d16a8a54d0","resolution":{"observed_at":"2026-08-11T00:44:59.563082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6199","last_updated":"2014-02-19T16:33:14Z","snapshot_observed_at":"2026-07-06T03:31:33.797310Z","submitted_at":"2013-12-21T03:36:08Z","title":"Intriguing properties of neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6199","snapshot_observed_at":"2026-08-11T00:44:59.098536Z","title":"Intriguing properties of neural networks,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.098536Z"},"links":{"cited_paper":"/paper/1312.6199","citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:557121599f1a33008ff95cd52f8330a62ec45df6aafc817606fdbd6284441594","observation_id":"75723d57-8e46-4e9e-9182-d9edaea4994a","resolution":{"observed_at":"2026-08-11T00:44:59.098536Z","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":"2026-08-11T00:44:59.550224Z","title":"Towards robust federated learning via logits calibration on non-iid data,","venue":null,"work_id":"3d59e496-a8ce-4853-8e0f-a0b0ba0c8f67","year":2024},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.103244Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:8213452a4f7eaae3613017e83440230b0f43a9ce6f4391117ada887ac69ede29","observation_id":"79bb39a2-ea79-4060-bd36-f265b9f4ca46","resolution":{"observed_at":"2026-08-11T00:44:59.553596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.539954Z","title":"Adversarial examples in the physical world,","venue":null,"work_id":"a2310deb-d0be-423e-977a-d98408d273fe","year":2018},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.107684Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:896e5ed6f2b82b10c704571f0881d7b6b322743442bc3fc2e543d850db1910f7","observation_id":"0df04547-fd24-4341-9c65-ec5113e9fa6d","resolution":{"observed_at":"2026-08-11T00:44:59.543421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.528898Z","title":"Square attack: a query-efficient black-box adversarial attack via random search,","venue":null,"work_id":"005297c4-992a-46f0-ba87-388beaaceeab","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.111324Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:05b5a56e32c23d16f74d85fbf7205b56e4e9cdb95e7348b2d701e3cb1b35228e","observation_id":"e69ee11e-d884-40fa-afab-14f70e73f4e7","resolution":{"observed_at":"2026-08-11T00:44:59.532937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.517493Z","title":"Towards evaluating the robustness of neural networks,","venue":null,"work_id":"fca57325-9185-4be8-ab37-821dec7ca423","year":2017},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.115182Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:234fb576ccabffe12eae274a38a8c608c4c5412b160a18198f0297f102998d98","observation_id":"5b049118-2427-4220-bf8b-8a3b3fce6cce","resolution":{"observed_at":"2026-08-11T00:44:59.521414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.504913Z","title":"Data augmentation can improve robustness,","venue":null,"work_id":"f8972055-afd1-484a-804b-13dc83895b03","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.119417Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:471d365c0fcf463b20818a8978ea194872a5c23f174d96a91cf4fca47fac09f6","observation_id":"52d9938d-0f5b-4598-910f-12afa7166505","resolution":{"observed_at":"2026-08-11T00:44:59.508892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.494286Z","title":"Maximum-entropy adver- sarial data augmentation for improved generalization and robustness,","venue":null,"work_id":"75427ce9-9451-4771-b59f-55b03d4af425","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.123743Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:966b9bbd4e4b0396b387bff7557295b28462594be514cabef75e255e5a7f20e7","observation_id":"1c74985f-c6e3-45f3-ae7f-657af7a1c4e2","resolution":{"observed_at":"2026-08-11T00:44:59.498044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.482153Z","title":"Towards robustness of deep neural networks via regularization,","venue":null,"work_id":"c3c2cee7-a4cc-49c3-9b89-81c4c38fed85","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.128643Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:4f7a49b4bf91dfdf01b45b203ca89f43714ec2ece4e56b9f2ab0c5a331232634","observation_id":"b20139ce-1e91-4eff-8da6-3a1831f6aecc","resolution":{"observed_at":"2026-08-11T00:44:59.486506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.470673Z","title":"Improving dnn robustness to adversarial attacks using jacobian regularization,","venue":null,"work_id":"9afbbf84-32ba-4c7f-b61f-1758a0962af7","year":2018},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.132692Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:a2bfa701e8ead6843e0542f959063c6d36f41d4d3567bc3bcfcd92328254cd13","observation_id":"7c4056e4-462c-4621-a6cd-b21bbae32cac","resolution":{"observed_at":"2026-08-11T00:44:59.474915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.458983Z","title":"Advances in adversarial attacks and defenses in computer vision: A survey,","venue":null,"work_id":"062dee76-4274-4b0b-a4bc-c7ef7540cdbc","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.136337Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:880aad843a1283d20108d577157fefc6947eed14fc7eb68f9b78b4f0e16e2d36","observation_id":"e4079a89-2dab-4790-b566-6069b816b0cb","resolution":{"observed_at":"2026-08-11T00:44:59.462988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.445660Z","title":"On adversarial robustness: A neural architecture search perspective,","venue":null,"work_id":"b3a81eb6-ab84-4024-b81a-0f2a97a0c07a","year":2021},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.139773Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:87eb988ae2d0af0336f0bc7676662f34e399d03493e865d6e42631d80c49c2c5","observation_id":"727b6321-a780-45ba-9f10-d437314dc67b","resolution":{"observed_at":"2026-08-11T00:44:59.450024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.433295Z","title":"The limitations of adversarial training and the blind-spot attack,","venue":null,"work_id":"e89d275e-d0e3-4fb6-af9f-f539ade9f4fd","year":2019},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.144106Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:a5b92ef5a8da31c9dca577feb456492d6e6aeacf76997c55c670ae6faca4e8de","observation_id":"2ac09c4a-5537-4eee-b138-ee44fd50144b","resolution":{"observed_at":"2026-08-11T00:44:59.437351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.421614Z","title":"Calfat: Calibrated federated ad- versarial training with label skewness,","venue":null,"work_id":"c37d3ad3-77c0-486a-a27f-0e1604b544c2","year":2022},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.148297Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:219e6e57187e8034d836bb6f9fb5411c0234d70b82f827b598f487ee13675541","observation_id":"2459ff05-8378-4296-a457-b8a577dac6ac","resolution":{"observed_at":"2026-08-11T00:44:59.425872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03286","last_updated":"2018-04-10T04:54:29Z","snapshot_observed_at":"2026-07-06T06:32:34.687885Z","submitted_at":"2018-04-10T04:54:29Z","title":"On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03286","snapshot_observed_at":"2026-08-11T00:44:59.151554Z","title":"On the robustness of the cvpr 2018 white- box adversarial example defenses,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.151554Z"},"links":{"cited_paper":"/paper/1804.03286","citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:148bf595664dd1687fadd10e573acf18a70a3cf7de2ad8a249fc3a3075b32eac","observation_id":"9e124d30-a264-403e-a0d7-31c3eafbc55b","resolution":{"observed_at":"2026-08-11T00:44:59.151554Z","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":"2026-08-11T00:44:59.409222Z","title":"Fedccl: Federated dual-clustered feature contrast under domain heterogeneity,","venue":null,"work_id":"dea673ee-bf6a-4d9b-9edd-e20ef4be3d70","year":2025},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.155515Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:85ba7ca75deff8c038a10aabb084125504dc9f75ae936a145d76babcab6f6cc6","observation_id":"03f59a9a-f964-4408-b062-2ee0880169a7","resolution":{"observed_at":"2026-08-11T00:44:59.412840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.397550Z","title":"Ensemble federated learning with non-iid data in wireless networks,","venue":null,"work_id":"469f2350-7937-47bb-887e-0d82279b7984","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.160183Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:4aa40af5c9d407e8fc5730137f43856fbff388b54645d2cc7c6fe6a9f3c028db","observation_id":"edaf937e-a1b3-441d-bb5f-bd56a3c82742","resolution":{"observed_at":"2026-08-11T00:44:59.401576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.385491Z","title":"Fraug: Tackling federated learning with non-iid features via representation augmenta- tion,","venue":null,"work_id":"c0772727-962d-43b6-9189-a681dd211e4d","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.164338Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:39cf9a16a599c3463a05cd0921a694cf5f856e44dff166794c842ac1f20a6cde","observation_id":"9e1dd134-ea58-47f9-9d0a-3bdad4b82645","resolution":{"observed_at":"2026-08-11T00:44:59.389678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.372569Z","title":"Fedproc: Prototypical contrastive federated learning on non-iid data,","venue":null,"work_id":"b004f3ea-942c-4333-9d67-48b2cee85fe9","year":2023},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.168067Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:e56cca03ca9fcf8a39c06f03a2709de967677defc5bca504d11eb600ff5dc05b","observation_id":"1a98bb23-e8c6-4abf-96bd-e478587a6702","resolution":{"observed_at":"2026-08-11T00:44:59.377077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.06373","last_updated":"2018-03-16T19:03:45Z","snapshot_observed_at":"2026-07-06T06:28:44.644165Z","submitted_at":"2018-03-16T19:03:45Z","title":"Adversarial Logit Pairing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.06373","snapshot_observed_at":"2026-08-11T00:44:59.171677Z","title":"Adversarial logit pairing,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.171677Z"},"links":{"cited_paper":"/paper/1803.06373","citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:c0523d6529f90df223a6a57d9d0f40fb22f7d98b92cbdd26a465ff84b4a16503","observation_id":"2f7fec41-f7cb-4688-b2e6-5de0d7095272","resolution":{"observed_at":"2026-08-11T00:44:59.171677Z","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":"2026-08-11T00:44:59.360654Z","title":"Adversarial vertex mixup: Toward better adversarially robust generalization,","venue":null,"work_id":"1e1f406e-170c-4e63-b366-261573687340","year":2020},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.176173Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:c3666cdb2e230f2d373e69dd801f2272972392ad8fd88d79c6e5636bcc139981","observation_id":"22f866d4-63c0-48fc-8b6b-fd519dc15485","resolution":{"observed_at":"2026-08-11T00:44:59.364792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.348864Z","title":"Theoretically principled trade-off between robustness and accuracy,","venue":null,"work_id":"8675a262-f808-482d-a037-97a6ce3be597","year":2019},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.179477Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:203eb1174fc75b62e81fe3e6f5f2f6aa99d07e7ecd1b7b16e039b96577ecde9b","observation_id":"91495a22-33c6-4238-9172-a33c0d409325","resolution":{"observed_at":"2026-08-11T00:44:59.352910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.336771Z","title":"Bayesian nonparametric federated learning of neural networks,","venue":null,"work_id":"75dfdf86-6f8a-4810-9abf-b7a88501da57","year":2019},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.183158Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:3752e9ce7c2886178823d048f3675003f93f1904364a48ab3cb9751af82fe7cf","observation_id":"503bdca1-e535-446e-916c-3a45800e57c9","resolution":{"observed_at":"2026-08-11T00:44:59.340893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T00:44:59.325018Z","title":"V-measure: A conditional entropy- based external cluster evaluation measure,","venue":null,"work_id":"61eea5c0-672d-4b39-b476-e9f9a30e84ad","year":2007},"citing_paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T00:44:59.186709Z"},"links":{"citing_paper":"/paper/2412.19354"},"observation_digest":"sha256:f1805f090fdbae95eead87e678600032a2623a3c532a6f759800dffd7ac0e24b","observation_id":"d661226f-31ff-40d3-b8b5-6b9e189818f2","resolution":{"observed_at":"2026-08-11T00:44:59.329353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.19354","last_updated":"2024-12-26T21:32:08Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T08:23:03.853466Z","submitted_at":"2024-12-26T21:32:08Z","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks"},"reference_resolution":{"displayed":79,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":2,"verified_fuzzy":69},"total_outbound_references":79},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 79 of 79 outbound references and 2 inbound Pith citation observations for arXiv:2412.19354."}