{"as_of":"2026-08-10T09:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:95b59ec008502e05935bce14da783b329040107dff5bc3d9d0605826b25c8bc5","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T05:40:26.436845Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.05086/citation-record","integrity":"/paper/2509.05086/integrity","json":"/paper/2509.05086/citation-record.json","paper":"/paper/2509.05086"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:40:31.861809Z","title":"Moe-rbench: Towards building reliable language models with sparse mixture-of-experts","venue":null,"work_id":"d4ecde5e-afc7-4188-8c69-0cb364f0484a","year":2024},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:23.934778Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:451ef6e5fb674f767eacd3ec105158aed72e745041a11a8975bbd36e0119e3b4","observation_id":"3f832f14-ccef-4f4b-b437-f16b669bb120","resolution":{"observed_at":"2026-08-05T05:40:31.963725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:31.655710Z","title":"Patch-level routing in mixture-of-experts is provably sample-efficient for con- volutional neural networks","venue":null,"work_id":"22419a57-e9a0-4114-8a1e-c1ae2874f599","year":2023},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:23.984328Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:edf43d7a43485673b82cb96dc421c8e0f50759f6a17fbb0a2260790d748367b9","observation_id":"954aa42d-f801-4a35-b306-1b96c8a031a1","resolution":{"observed_at":"2026-08-05T05:40:31.786419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:31.448891Z","title":"Reliable evalua- tion of adversarial robustness with an ensemble of diverse parameter-free attacks","venue":null,"work_id":"ea162b6e-9f60-4b55-aaf8-349fcd3753b1","year":2020},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.100503Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:0d80a0c116eda4649f61d1ecf823c2a314fb1722a54f434953983a3b18fba719","observation_id":"c064f9ca-efb3-40d3-a962-3d6bf2eda3dc","resolution":{"observed_at":"2026-08-05T05:40:31.562668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.06066","last_updated":"2024-01-11T17:31:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-11T17:31:42Z","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.06066","snapshot_observed_at":"2026-08-05T05:40:24.207845Z","title":"Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models.arXiv preprint arXiv:2401.06066, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.207845Z"},"links":{"cited_paper":"/paper/2401.06066","citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:4478eb769884205192757b8e44aaa374004808db9b0371409d2aec47f43b1594","observation_id":"25a8652f-cab8-4928-a5fc-36a1924cf60d","resolution":{"observed_at":"2026-08-05T05:40:24.207845Z","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":"2026-08-05T05:40:31.209136Z","title":null,"venue":null,"work_id":"1bba3efe-6668-4388-9eaa-cd62e4cbad39","year":2023},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.278976Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:ceb68889db2a3483553819a892e9f68fd415c3430fc1d932c54d0fb2b47361bc","observation_id":"5cd4d17d-e25d-43fd-ab2f-87802020881e","resolution":{"observed_at":"2026-08-05T05:40:31.326764Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:30.999508Z","title":"Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, Barret Zoph, Liam Fe- dus, Maarten P","venue":null,"work_id":"67604d83-7e0d-4804-a744-268a6768725b","year":2022},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.383296Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:2fe9f3be0af9e814ae4f61ef149815a430b2e41bda8b2c8626e87a687a480d4a","observation_id":"5b6ab025-2c4c-40ed-8fd7-0e8798cb46ac","resolution":{"observed_at":"2026-08-05T05:40:31.072376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:30.822518Z","title":"Learning Factored Representations in a Deep Mixture of Ex- perts","venue":null,"work_id":"bdbc552a-6bee-47fa-8ce3-62790396c03d","year":2013},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.422135Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:817904446cafaf0742bcaf7d6872820297cf40cc2318d831ce6a6b89c065d47c","observation_id":"563068bf-01e5-4c48-88d1-4c80957b18f0","resolution":{"observed_at":"2026-08-05T05:40:30.899013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:30.557530Z","title":"Switch transformers: Scaling to trillion parameter models with sim- ple and efficient sparsity.The Journal of Machine Learning Research, 2022","venue":null,"work_id":"9fdc5084-8b31-4feb-be2c-98fa162ae0a5","year":2022},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.475873Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:fbd67f66261ff77f7e163cc11a8bbfce5d99ecf8e0b3d47d2d463b224eb97069","observation_id":"c12f17cd-3d49-4ab7-ba91-abaeb454f26e","resolution":{"observed_at":"2026-08-05T05:40:30.686611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.03635","last_updated":"2019-03-04T15:51:11Z","snapshot_observed_at":"2026-08-05T23:54:27.386622Z","submitted_at":"2018-03-09T18:51:28Z","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.03635","snapshot_observed_at":"2026-08-05T05:40:24.574576Z","title":"The lottery ticket hy- pothesis: Finding sparse, trainable neural networks.arXiv preprint arXiv:1803.03635, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.574576Z"},"links":{"cited_paper":"/paper/1803.03635","citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:be504c46780a7fe868dd10801e980927986cb9a2e4a29caab56bbd7e37fb4e03","observation_id":"9cac7396-c4c1-4362-9dd3-9225cbb90f8c","resolution":{"observed_at":"2026-08-05T05:40:24.574576Z","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":"2026-08-05T05:40:30.290382Z","title":"Drawing robust scratch tickets: Subnetworks with inborn robustness are found within randomly initialized networks","venue":null,"work_id":"eee11a9a-9c98-4f61-8096-c5617c451a86","year":null},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.665119Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:576760eaee4c8df71fa4ac7f3eea6460270e255612e8ab2cfc320c55b04d8818","observation_id":"971dda48-0775-475e-ac8c-51ab0cfe5cd8","resolution":{"observed_at":"2026-08-05T05:40:30.417725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:30.118826Z","title":"Explaining and Harnessing Adversarial Examples","venue":null,"work_id":"4ae32541-8f4e-4791-a208-77dddb498eda","year":null},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.733184Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:00bb74829bea7b589dba75604c3f51b42d3a0ea207395302d2adbff804a18167","observation_id":"9fb3b2b4-2b61-4db9-bd86-52b6659b9d71","resolution":{"observed_at":"2026-08-05T05:40:30.218810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:29.925306Z","title":"Sparse dnns with improved adversarial robustness","venue":null,"work_id":"dd3b3ef0-02a7-4aca-921f-965389e6297e","year":2018},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.804245Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:6e926461566ea58139d05e207d89d73ff5610e118712b2068876cdb2b47bf711","observation_id":"c580b59a-c4d4-4ee6-a3ae-ff0f44d75c99","resolution":{"observed_at":"2026-08-05T05:40:30.032316Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:29.753234Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"7c3f6721-4f1c-426b-bcca-da4f222cb518","year":2016},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.890350Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:60fef8e181d254f5d595481085dc2d20459a9e6828727f5d6b4ca7e0b16d2134","observation_id":"73db129c-9ebd-4386-9983-eeec423adc6c","resolution":{"observed_at":"2026-08-05T05:40:29.846665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:29.591910Z","title":"Jacobs, Michael I","venue":null,"work_id":"8b0e4308-5d36-4c8a-bb1c-37a8b44a414c","year":1991},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:24.991770Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:91a6b3f208cfa497d83f006288ea24fcc19a810627a7753005c4c3293bfda379","observation_id":"7bdbd632-5ffe-4b69-88ef-51ea549ff55a","resolution":{"observed_at":"2026-08-05T05:40:29.679810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:29.432724Z","title":"Robustifying routers against in- put perturbations for sparse mixture-of-experts vision trans- formers.IEEE Open Journal of Signal Processing, 2025","venue":null,"work_id":"6a2a4635-8c0f-430a-b983-89c3e7c9966e","year":2025},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.046903Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:d9fe76e4da071f2910edbcb8317dae41e895ea163764485564cbca7289bd9630","observation_id":"290c5ba1-4528-464e-9ade-5b5dc9be14a8","resolution":{"observed_at":"2026-08-05T05:40:29.509483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:25.129806Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.129806Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:86678fe904445af9997f5e12d45bfeca90aff80a4e811fa5c8536c76ad232d5c","observation_id":"ac72bffd-3c19-4583-a70b-595855b5add7","resolution":{"observed_at":"2026-08-05T05:40:25.129806Z","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":"2026-08-05T05:40:29.207140Z","title":"Gshard: Scaling giant models with conditional com- putation and automatic sharding","venue":null,"work_id":"8d60e8d8-ca93-4741-9d61-e7addf4c2740","year":2021},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.184209Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:4f85d692412fa097f9d4f875656c4390442594badb6ba42e9faef6019cd9b071","observation_id":"16dc22ae-1d56-4d5f-963a-72eebb976e99","resolution":{"observed_at":"2026-08-05T05:40:29.330759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:25.263826Z","title":"Modeling task relationships in multi-task learning with multi-gate mixture-of-experts","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.263826Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:fce0a76f8ed90c0ee9e182147bf9c19eb626b3c641b2b4fb76bd7ce35e8ddc18","observation_id":"8e6af4be-7bca-4997-8e5e-b7b5bd3fd1a5","resolution":{"observed_at":"2026-08-05T05:40:25.263826Z","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":"2026-08-05T05:40:28.954119Z","title":"Towards Deep Learn- ing Models Resistant to Adversarial Attacks.International Conference on Learning Representations (ICLR), 2018","venue":null,"work_id":"936032cb-ad12-43a4-a3ed-22044ee3be51","year":2018},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.343222Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:1c511383f547d79ec4ad323275955c0d4cef3b0dca751b874aebe0ff8965a6c7","observation_id":"d05bb020-1f0d-4334-839e-2a7a69c178df","resolution":{"observed_at":"2026-08-05T05:40:29.079388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:28.648757Z","title":"Choosing smartly: Adaptive multimodal fusion for object detection in changing environments","venue":null,"work_id":"f37cdcc7-176c-47d8-add1-5f02dc29990f","year":2016},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.425102Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:a5aa1044fd278d8982d8dba52773b110a4fe2f00802eb02418aa9c3d50c9f728","observation_id":"2ad716ba-f101-465b-8208-eae519353b72","resolution":{"observed_at":"2026-08-05T05:40:28.789203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:28.331482Z","title":"Is temper- ature sample efficient for softmax gaussian mixture of ex- perts? InInternational Conference on Machine Learning (ICML), 2024","venue":null,"work_id":"6fd00a8d-54ec-44b4-b1a0-a76c7866e604","year":2024},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.506562Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:829824e784b8d573b60d398859298a7ecebeb1b92a6d09df39b1cbe150aba84c","observation_id":"5589a1e6-e2a8-4991-bd13-890d3f2d36c2","resolution":{"observed_at":"2026-08-05T05:40:28.462482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:28.115425Z","title":"Marius Z¨ollner","venue":null,"work_id":"e6f11742-05d3-4c72-873f-814c5ff4626e","year":2023},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.598450Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:79e8dee9ff078b3338fa1a2dcc3829750225044dddec540a6f6cb29565ce5497","observation_id":"0afc3513-158b-4cd7-8d66-072d9bd38c24","resolution":{"observed_at":"2026-08-05T05:40:28.217816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:27.907717Z","title":"Mar- ius Z ¨ollner","venue":null,"work_id":"bf52e510-b3fb-4fbc-a555-970d22d3fe9a","year":2020},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.669182Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:f5f895e1b4b6197371c832ff46d7b190aa9ecf8fb40f73b8f3088118c77254c4","observation_id":"4422ec78-7fa0-4395-9ba6-fe7bc358b7aa","resolution":{"observed_at":"2026-08-05T05:40:28.060237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.10253","last_updated":"2022-10-19T02:24:57Z","snapshot_observed_at":"2026-08-08T09:57:03.732079Z","submitted_at":"2022-10-19T02:24:57Z","title":"On the Adversarial Robustness of Mixture of Experts","version":1},"cited_work":{"arxiv_id":"2210.10253","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.10253","snapshot_observed_at":"2026-08-05T05:40:26.534252Z","title":"On the Adversarial Robustness of Mixture of Experts","venue":"cs.LG","work_id":"ba072851-746b-4dc8-9fa5-e10f6007f53e","year":2022},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.746665Z"},"links":{"cited_paper":"/paper/2210.10253","citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:ba2cec61acfe564ca4ca8e824d50ebd6269889edc2bb71d0855620328d614073","observation_id":"040c1ebd-c80b-4ea3-b1ed-d200385808dc","resolution":{"observed_at":"2026-08-05T05:40:26.591111Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:27.617638Z","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next- Generation AI Scale","venue":null,"work_id":"83e3d02c-43c5-4171-bd6a-5360fa8cb82f","year":2022},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.839212Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:33fb55d3b4faefec05bb79cc0b4f4244f70254bfce619bc5e371a6bdcc0d0296","observation_id":"2b50ea9e-abc7-41ab-9d44-9bf8e25096b4","resolution":{"observed_at":"2026-08-05T05:40:27.783030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:27.284265Z","title":"Scaling vision with sparse mix- ture of experts","venue":null,"work_id":"ae047929-3bbe-48d3-bf98-f644222d1473","year":2021},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.905294Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:2fe943228b22a50a96d02c00714eecac78db0914dd733a78b214ff16f6d6774e","observation_id":"0bf5521e-a68d-4665-86a9-5d82a8cf3b94","resolution":{"observed_at":"2026-08-05T05:40:27.439314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:27.088163Z","title":"Le, Geoffrey E","venue":null,"work_id":"ceecfcb2-8c91-401a-8477-6e9943f4e566","year":2017},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:25.982754Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:54c6e39c5dae1dc1f05ff79900e956c98e1f15a845eb0a27e5cf2999635a63f1","observation_id":"352ab2da-29b9-4a26-a328-f72ad1cb4708","resolution":{"observed_at":"2026-08-05T05:40:27.113345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:26.953049Z","title":"Goodfellow, and Rob Fergus","venue":null,"work_id":"06dda69c-9df0-424e-b06a-ad392d108731","year":2014},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:26.059191Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:2eb0bbe96faeb96d1089069d1c306a02be83977d92940cab7beb35dfbaf504cd","observation_id":"ca2d1a11-6356-4faf-a607-8960108f69ed","resolution":{"observed_at":"2026-08-05T05:40:27.018466Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:40:26.107431Z","title":"Convo- luted mixture of deep experts for robust semantic segmenta- tion","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:26.107431Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:8136e4d8add4e61815ad4549db441a34e78e13b5c4a73b751bf3a3af7e34c23c","observation_id":"af15c498-e4a3-4f75-813e-d0bc53ed822f","resolution":{"observed_at":"2026-08-05T05:40:26.107431Z","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":"2026-08-05T05:40:26.818452Z","title":"Gonzalez","venue":null,"work_id":"50849105-808a-40c0-b1dc-6f4a517b16d5","year":2019},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:26.153125Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:20b9784b64bb0a35a6819b11c7bad546da8803016469e003366d5f223d110cd4","observation_id":"8afb7f30-1f97-4607-8217-9e85cb08a043","resolution":{"observed_at":"2026-08-05T05:40:26.869716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.14711","last_updated":"2025-02-27T16:33:09Z","snapshot_observed_at":"2026-08-09T03:21:13.453412Z","submitted_at":"2024-12-19T10:21:20Z","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.14711","snapshot_observed_at":"2026-08-05T05:40:26.258436Z","title":"Remoe: Fully differentiable mixture-of-experts with relu routing.CoRR, abs/2412.14711, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:26.258436Z"},"links":{"cited_paper":"/paper/2412.14711","citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:26e1c80e522c4140c9937aab49dda3eab2595c8003b6e98993e8b81937f2950c","observation_id":"b36adb7c-a25d-4662-a606-32fe8b5dd342","resolution":{"observed_at":"2026-08-05T05:40:26.258436Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04004","last_updated":"2025-03-20T13:53:48Z","snapshot_observed_at":"2026-08-09T11:01:39.321850Z","submitted_at":"2025-01-07T18:59:58Z","title":"LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.04004","snapshot_observed_at":"2026-08-05T05:40:26.327329Z","title":"Limoe: Mixture of lidar representation learners from automotive scenes.CoRR, abs/2501.04004,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:26.327329Z"},"links":{"cited_paper":"/paper/2501.04004","citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:9e6e0e7ae4fce09962bf64e24ede7f00d53bda06152d67cae0f14da5500c0aa2","observation_id":"bcf1c4c8-753b-473f-86b6-7d36f45fc4e4","resolution":{"observed_at":"2026-08-05T05:40:26.327329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:40:26.382238Z","title":"Learning a mixture of granularity-specific experts for fine- grained categorization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:26.382238Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:271c9f0a2a8d502bf71c25d207d3baa7c2772ed9c3f0b3f2ae8df2c3f66b0f6b","observation_id":"93c217f8-2995-431f-b80c-c84a5279d64a","resolution":{"observed_at":"2026-08-05T05:40:26.382238Z","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":"2026-08-05T05:40:26.671001Z","title":"Robust mixture-of-expert training for convo- lutional neural networks","venue":null,"work_id":"ae30b94c-6fc8-442b-8b7e-bf6cfd79f213","year":2023},"citing_paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T05:40:26.436845Z"},"links":{"citing_paper":"/paper/2509.05086"},"observation_digest":"sha256:f39c723dc7e74dd3b3a1623f1012f81355f292d7095ff9afc09d54b6fdce909b","observation_id":"ca501cd3-3e24-451a-ab7a-6f6f71389c1c","resolution":{"observed_at":"2026-08-05T05:40:26.740897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.05086","last_updated":"2025-09-05T13:25:33Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T22:30:50.854960Z","submitted_at":"2025-09-05T13:25:33Z","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":1,"verified_fuzzy":24},"total_outbound_references":34},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2509.05086."}