{"as_of":"2026-08-10T02:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6b9c913f5b53445b00132556290997e54b73510bc836561d1660e2d6a4f2951f","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T15:00:57.690797Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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":"2026-06-30T07:01:04.860047Z","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":"2026-06-30T07:04:21.119128Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"cited_work":{"arxiv_id":"2507.17070","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.17070","snapshot_observed_at":"2026-06-30T07:04:21.119128Z","title":"Advancing ro- bustness in deep reinforcement learning with an ensemble defense approach","venue":null,"work_id":"084f3dbc-55de-4f42-b8fb-05fc791f0957","year":2025},"citing_paper":{"arxiv_id":"2605.03491","last_updated":"2026-05-05T08:30:18Z","snapshot_observed_at":"2026-07-06T23:16:25.301792Z","submitted_at":"2026-05-05T08:30:18Z","title":"Real-Time Evaluation of Autonomous Systems under Adversarial Attacks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-07T16:46:49.471204Z"},"links":{"cited_paper":"/paper/2507.17070","citing_paper":"/paper/2605.03491"},"observation_digest":"sha256:4f948483478b93cd19d474accb45906458db61172ee0026113df5e85e93822e8","observation_id":"a334e2e1-6de8-4c2a-a8c2-34e58f139ffc","resolution":{"observed_at":"2026-05-12T10:51:31.629846Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"cited_work":{"arxiv_id":"2507.17070","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.17070","snapshot_observed_at":"2026-06-30T07:04:21.119128Z","title":"Advancing ro- bustness in deep reinforcement learning with an ensemble defense approach","venue":null,"work_id":"084f3dbc-55de-4f42-b8fb-05fc791f0957","year":2025},"citing_paper":{"arxiv_id":"2606.29867","last_updated":"2026-06-29T07:03:45Z","snapshot_observed_at":"2026-07-07T00:03:45.783349Z","submitted_at":"2026-06-29T07:03:45Z","title":"RoAd-RL: A Unified Library and Benchmark for Robust Adversarial Reinforcement Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-30T07:01:04.860047Z"},"links":{"cited_paper":"/paper/2507.17070","citing_paper":"/paper/2606.29867"},"observation_digest":"sha256:ff0af2cb027f30b0b4baf3eeadab6380f13bd327fe4f474304482c557b041fdf","observation_id":"79908241-b3c5-4e8d-b574-46dddd3606d4","resolution":{"observed_at":"2026-06-30T07:04:21.120740Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.17070/citation-record","integrity":"/paper/2507.17070/integrity","json":"/paper/2507.17070/citation-record.json","paper":"/paper/2507.17070"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.315837Z","title":"Challenges and countermeasures for adversarial at- tacks on deep reinforcement learning,","venue":null,"work_id":"86115852-2db0-4084-b65f-29f03ba80b62","year":2022},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.521632Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:e567e3e4ae39f8542ed820bc8193aaf850605c35b070e2d2b3011d962763e8a0","observation_id":"f2d1d629-9231-4afc-a5f0-b3bd1f62ce85","resolution":{"observed_at":"2026-08-06T15:00:58.320814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.300993Z","title":"A survey on adversarial attacks and defenses in reinforcement learning,","venue":null,"work_id":"066da3e7-9a59-4631-961c-a38ce300a21e","year":2021},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.526450Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:563a056dcd37134bf18db563b4b0a69188cc3fc4c28f0f74297dcbe02a1cb422","observation_id":"9890083e-d429-45c6-98a5-80fa31da6448","resolution":{"observed_at":"2026-08-06T15:00:58.305162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.07006","last_updated":"2019-06-14T06:40:15Z","snapshot_observed_at":"2026-07-06T08:00:49.815158Z","submitted_at":"2019-06-14T06:40:15Z","title":"Anti-plane surface waves in media with surface structure: discrete vs. continuum model","version":1},"cited_work":{"arxiv_id":"1906.07006","doi":null,"metadata_source":"pith","pith_arxiv_id":"1906.07006","snapshot_observed_at":"2026-08-06T15:00:57.845161Z","title":"Anti-plane surface waves in media with surface structure: discrete vs. continuum model","venue":"physics.class-ph","work_id":"3133734f-f3bb-4869-a42f-18c0ff6e7c07","year":2019},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.530614Z"},"links":{"cited_paper":"/paper/1906.07006","citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:114a5b277ee7d2b598b23fe1a0b9f57c3dfd615dcbdb9fd330e45c25e9d1a652","observation_id":"2e79d2fb-9f68-470e-a279-cac019aa79e8","resolution":{"observed_at":"2026-08-06T15:00:57.849452Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.286651Z","title":"A review of applications of artificial intelligence and blockchain in the energy sector,","venue":null,"work_id":"3f024ba3-e322-4fa2-b455-6d6ff66b595e","year":2020},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.535336Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:9d6fe9202ac3af7b515469376178792a7efa0db136b2fdf28835060340bdfbff","observation_id":"6a1b4c6b-d8f3-48d8-b734-d13e754fdf52","resolution":{"observed_at":"2026-08-06T15:00:58.290927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.272730Z","title":"Adversarial attacks on neural network policies,","venue":null,"work_id":"0592e9af-2fe9-4a2a-8609-b0b87f346b18","year":2017},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.539578Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:14200997daa8c8a658d6b78e6947dfec0a81f5311c7a42a63504709f4bc4d40a","observation_id":"3d7b3e6c-2220-47f5-b441-da71629c97f0","resolution":{"observed_at":"2026-08-06T15:00:58.276819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.09344","last_updated":"2018-05-18T13:31:46Z","snapshot_observed_at":"2026-07-06T06:11:10.025744Z","submitted_at":"2017-11-26T07:39:02Z","title":"Comment on \"Relation between scattering amplitude and Bethe-Salpeter wave function in quantum field theory\"","version":3},"cited_work":{"arxiv_id":"1711.09344","doi":null,"metadata_source":"pith","pith_arxiv_id":"1711.09344","snapshot_observed_at":"2026-08-06T15:00:57.824892Z","title":"Comment on \"Relation between scattering amplitude and Bethe-Salpeter wave function in quantum field theory\"","venue":"hep-lat","work_id":"ebec2676-b523-475d-bc82-2e1ea2511d45","year":2017},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.543764Z"},"links":{"cited_paper":"/paper/1711.09344","citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:6b3f85cf35ac7ad97ed6fad704afc476c2676c71551594f24e7a20cc8818030b","observation_id":"a12c2e59-a6e1-4832-8e07-90fb0933bd3f","resolution":{"observed_at":"2026-08-06T15:00:57.829449Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.259192Z","title":"Robust physical-world attacks on deep learning visual classification,","venue":null,"work_id":"524085ae-3e45-4092-8a6f-98084280ef63","year":2018},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.548994Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:58946b4c3e442fe9048183bde920835890eb664104fcb2019073b3242467e973","observation_id":"57624b68-d8d3-4b20-9866-463b4e7a55dd","resolution":{"observed_at":"2026-08-06T15:00:58.263343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.245109Z","title":"Explaining and harness- ing adversarial examples,","venue":null,"work_id":"13bb5734-c778-48d7-8c51-669f78bb7538","year":2015},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.553153Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:b3e2e6a5b321f0f079a0b81d07ff2dc901183cbc04c183c536159dd422d72726","observation_id":"817b9a12-25c6-4cff-ab90-a41ebe10dcb5","resolution":{"observed_at":"2026-08-06T15:00:58.249422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1709.03423","last_updated":"2018-02-08T08:48:03Z","snapshot_observed_at":"2026-07-06T05:59:06.631941Z","submitted_at":"2017-09-11T15:01:03Z","title":"Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.03423","snapshot_observed_at":"2026-08-06T15:00:57.557138Z","title":"Ensemble methods as a defense to adversarial perturbations against deep neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.557138Z"},"links":{"cited_paper":"/paper/1709.03423","citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:89f5b126ba9e1c4fdb713ff82a1133effaa98e7739fc93cdd4c306ae6d38169f","observation_id":"5acd409e-4bdc-4b0b-b985-130b8cd1d536","resolution":{"observed_at":"2026-08-06T15:00:57.557138Z","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":"2026-08-06T15:00:57.561555Z","title":"An environment for autonomous driving decision- making,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.561555Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:89609c6f5e76ba5875d55709b9f8200e71703bdb4f98af71b9769d40c4755471","observation_id":"60061ba1-a4f1-4138-bc84-9963fc066b24","resolution":{"observed_at":"2026-08-06T15:00:57.561555Z","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":"2026-08-06T15:00:58.221570Z","title":"Perceiver hopfield pooling for dynamic multi-modal and multi-instance fusion,","venue":null,"work_id":"f141287b-5dd3-447c-ba8f-f7da8fdb23c9","year":2022},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.565569Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:9eaf3b68614eee0c7a66765bddd9e31248b9869a7e57ce9dd46aeec555fc3958","observation_id":"910061f0-f936-47c1-8992-b1d7f488f09e","resolution":{"observed_at":"2026-08-06T15:00:58.226211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.208129Z","title":"A survey on attacks and their coun- termeasures in deep learning: Applications in deep neural networks, federated, transfer, and deep reinforcement learning,","venue":null,"work_id":"6da224d2-55d3-4e06-8375-1d3ff9db4026","year":2023},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.569765Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:12c84fe1531d1af40b2102d9c98fef89675b5071b519c378e7f9589aa7453135","observation_id":"602207ce-bf46-47c9-86a9-0eaf7f50d8d2","resolution":{"observed_at":"2026-08-06T15:00:58.212428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.06752","last_updated":"2018-07-18T02:57:16Z","snapshot_observed_at":"2026-07-06T06:50:50.677421Z","submitted_at":"2018-07-18T02:57:16Z","title":"Gradient Band-based Adversarial Training for Generalized Attack Immunity of A3C Path Finding","version":1},"cited_work":{"arxiv_id":"1807.06752","doi":null,"metadata_source":"pith","pith_arxiv_id":"1807.06752","snapshot_observed_at":"2026-08-06T15:00:57.787603Z","title":"Gradient Band-based Adversarial Training for Generalized Attack Immunity of A3C Path Finding","venue":"cs.LG","work_id":"c8745237-848c-4d87-b064-7f03ef2cef27","year":2018},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.573812Z"},"links":{"cited_paper":"/paper/1807.06752","citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:fc3057a294826767f711c3df53fa94601c806631dd297d82e3997cb33747cc1e","observation_id":"ca52872b-9a9d-4f9d-93bc-572a5c88d443","resolution":{"observed_at":"2026-08-06T15:00:57.792808Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.194776Z","title":"Adversarial attacks on neural network policies,","venue":null,"work_id":"a743d248-0acd-497a-b811-b1b2d122f1dd","year":2017},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.578334Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:d46fcdc0df6e5a02e8fa94c96545ede613ad6fda23b618296114d5c1a5af70f2","observation_id":"173f3584-1698-4fb2-b3a3-523ad9e8a260","resolution":{"observed_at":"2026-08-06T15:00:58.198911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.180093Z","title":"Vulnerability of deep reinforcement learning to policy induction attacks,","venue":null,"work_id":"84d7c7cf-6a43-4c07-9ff2-c7362c44d418","year":2017},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.582543Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:7bbec479dc0b942bbad354f16836c95046f4e351d6e7898749609344781be0d8","observation_id":"15136c24-74eb-464d-aeac-02f4a514bbda","resolution":{"observed_at":"2026-08-06T15:00:58.184339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.166351Z","title":"Delving into adversarial attacks on deep policies,","venue":null,"work_id":"1e575f2c-40c5-4516-98c0-ecaa88aef7cc","year":2017},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.586399Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:66a1533975ce021fa049cce64f3537463416d5c218e93be2c653212683db42e6","observation_id":"5522851d-1202-496b-bd1d-9cdf2066b8dc","resolution":{"observed_at":"2026-08-06T15:00:58.170590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.152864Z","title":"A malicious attack on the machine learning policy of a robotic system,","venue":null,"work_id":"9d9862ef-9463-4775-b3a4-f861d99276eb","year":2018},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.590453Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:a40fa398f3a502662da581c514d5803518c19c528ef723a754523701cc8c3c14","observation_id":"1e930cb6-4b46-479e-8d20-f127bf7479af","resolution":{"observed_at":"2026-08-06T15:00:58.157345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.138829Z","title":"Copycat: Taking control of neural policies with constant attacks,","venue":null,"work_id":"ded16be7-4696-4679-9688-bfcd3aba5d5e","year":2019},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.594441Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:b1a5a0c388b64610f1a7c55b0f849e32ccd5f49467f9c41fcf3fb08faccde886","observation_id":"5239040d-365c-4c07-ba71-30638ef70846","resolution":{"observed_at":"2026-08-06T15:00:58.143069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.125551Z","title":"Acadia: Efficient and robust adversarial attacks against deep reinforcement learning,","venue":null,"work_id":"f770067c-4141-4a57-9cce-586667c18762","year":2022},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.598422Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:6d36d9991524eff1d43019ad80ea7190205c9658e795b60b90f9c32db9cd8727","observation_id":"d96eaa9a-5404-4017-a687-e50fefcd5e27","resolution":{"observed_at":"2026-08-06T15:00:58.129650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.111087Z","title":"Adversarial attacks in consensus-based multi-agent reinforcement learning,","venue":null,"work_id":"3f9d9dab-9322-49ce-a911-a10e4776092d","year":2021},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.602274Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:217d87d20fb62e4ef66133a641fbdc8ae07b200c42c372e889ababd073a67f73","observation_id":"5dc85bb0-227e-41af-bc32-c7ce7c76b9a2","resolution":{"observed_at":"2026-08-06T15:00:58.115750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.096393Z","title":"Tactics of adversarial attack on deep reinforcement learning agents,","venue":null,"work_id":"53e7edc0-d88b-4d54-9b71-6a686237a759","year":2017},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.606414Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:94ebeb2901807bbe6ddce79882cd1b240c2f21eb87163e52f4cffb4448a2fd48","observation_id":"95bce60b-a025-4b0a-900b-ca63c9e626ef","resolution":{"observed_at":"2026-08-06T15:00:58.100949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.081928Z","title":"Sequential attacks on agents for long-term adversarial goals,","venue":null,"work_id":"f4614656-0d7d-4267-b797-64577c23decb","year":2018},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.610299Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:ee8719cba31eb52d420ca9fc0f8eaf268e6c1fcc536f42f77fd81c60cc15ec91","observation_id":"dcc9b26d-374c-4817-ba84-1966882f39c9","resolution":{"observed_at":"2026-08-06T15:00:58.086200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.067800Z","title":"Trojdrl: Trojan at- tacks on deep reinforcement learning agents,","venue":null,"work_id":"a8973241-f6d1-4840-9420-334d3548b4e5","year":2020},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.614350Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:091af05b6d854000844c5a68270c79859e8fcf9a92fb58e7fa04d73d0a4afb8d","observation_id":"3235f9d0-6109-4658-976a-5d6748225cdc","resolution":{"observed_at":"2026-08-06T15:00:58.072056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.054237Z","title":"Stealthy and efficient adversarial attacks against deep reinforcement learning,","venue":null,"work_id":"1ddaaf84-b14c-4375-9ee5-78e439868608","year":2020},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.618253Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:ac66cb94b1b0204b67488e57e5c0b23274216aaec4086335ac7b320e9a2ee510","observation_id":"a84d6b37-87ab-48a0-b403-ee6d6c50165f","resolution":{"observed_at":"2026-08-06T15:00:58.058653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.040145Z","title":"Provably efficient black-box action poisoning attacks against reinforcement learning,","venue":null,"work_id":"80f90b88-257f-4bf6-813a-e32c82c5f141","year":2021},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.621972Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:ad878d420b234d036f1f9a77f3615108e0816bdd79b180b1df8508ace293b5f0","observation_id":"39993b91-3c61-4303-8d7e-09cc20a89a47","resolution":{"observed_at":"2026-08-06T15:00:58.044683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.025908Z","title":"Strategically-timed state- observation attacks on deep reinforcement learning agents,","venue":null,"work_id":"e594b1e8-4705-493d-92ce-e72934fdde18","year":2021},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.625809Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:3ffb9955c18d90363f8a05a09590f59c88c3a53b0edd26c2e2cb744cd9255bf8","observation_id":"dabeefeb-4202-47bb-9319-b9b2f113cf63","resolution":{"observed_at":"2026-08-06T15:00:58.030305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:58.011453Z","title":"Robust deep reinforcement learning with adversarial attacks,","venue":null,"work_id":"d2ba491d-27be-47af-9d5a-52b1b5407ae8","year":2018},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.629789Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:14fd2b98fb9259e2e9dca3784395739e00fa645ad842448f182f71fc11fa3780","observation_id":"63a92385-4d5b-49b7-b94e-7b4b04a3e90b","resolution":{"observed_at":"2026-08-06T15:00:58.016079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:57.997451Z","title":"Deep reinforcement learning with robust and smooth policy,","venue":null,"work_id":"0a97b3b8-0589-4b50-a5e3-3878759b5c18","year":2020},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.634394Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:3a8765252db413b4fb3d272038fa63cbb3f9d18d8bb8bd319d270acd8187ef2a","observation_id":"50714ca1-1e70-4c51-8bfd-a05828cff298","resolution":{"observed_at":"2026-08-06T15:00:58.002205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:57.984091Z","title":"Robust reinforce- ment learning on state observations with learned optimal adversary,","venue":null,"work_id":"8eb1db27-4353-421c-b0fc-ba5b7db0456a","year":2021},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.638428Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:4a0e3e643fdfba8c99666fdcd569a446f64a3cd02d9072620cef06f0260b3881","observation_id":"4e150d26-eeaa-4078-9931-a623a384ae5b","resolution":{"observed_at":"2026-08-06T15:00:57.988237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:57.969869Z","title":"Action robust reinforcement learning and applications in continuous control,","venue":null,"work_id":"88b169e1-bef7-4fe2-b0ca-6fd0e1807323","year":2019},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.642349Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:c4b8f15c6b19603c5fd32aa41e397263256cb25c23eeb2e1b9560e23cc9dc125","observation_id":"8cbf8f5d-228e-4a8b-a3bf-0007fea2f7f6","resolution":{"observed_at":"2026-08-06T15:00:57.974344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.00814","last_updated":"2017-10-02T17:56:26Z","snapshot_observed_at":"2026-07-06T06:02:22.062525Z","submitted_at":"2017-10-02T17:56:26Z","title":"Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.00814","snapshot_observed_at":"2026-08-06T15:00:57.646471Z","title":"Detecting adversar- ial attacks on neural network policies with visual foresight,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.646471Z"},"links":{"cited_paper":"/paper/1710.00814","citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:ee2d0155bc09a8705e0bbe32940df17fe7acd1696aba92eb3ed96baa88a35127","observation_id":"c69e4ee5-bacd-4528-8fe6-03e06e3db605","resolution":{"observed_at":"2026-08-06T15:00:57.646471Z","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":"2026-08-06T15:00:57.955822Z","title":"A pca-based model to predict adversarial examples on q-learning of path finding,","venue":null,"work_id":"2811fcf5-76f4-4eb5-a0c1-54675e3d911f","year":2018},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.650763Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:a9dd374d78430a5ec5188205c0c708f7a91148e1f61ffb4d4248a8d8a9f55225","observation_id":"ead37161-246f-479f-b4a5-f1fc4591bc23","resolution":{"observed_at":"2026-08-06T15:00:57.960127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.13548","last_updated":"2019-07-31T15:16:00Z","snapshot_observed_at":"2026-07-06T08:11:31.472773Z","submitted_at":"2019-07-31T15:16:00Z","title":"Optimal Attacks on Reinforcement Learning Policies","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.13548","snapshot_observed_at":"2026-08-06T15:00:57.654907Z","title":"Optimal attacks on reinforcement learning policies,","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.654907Z"},"links":{"cited_paper":"/paper/1907.13548","citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:84a4d178661ba424e441921c7a0a4347ff3dbccceb2abc8204951c14a217bd34","observation_id":"feb37fde-8bda-4d96-957e-d5466711557b","resolution":{"observed_at":"2026-08-06T15:00:57.654907Z","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":"2026-08-06T15:00:57.941933Z","title":"Robust deep reinforcement learning against adversarial perturbations on state observations,","venue":null,"work_id":"6fe309e3-4b5f-4255-b775-2ebe6aa2a6f1","year":2020},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.659722Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:f420b932f3061ac1e3e552930319a3d6dda063c738ce5feec2629c0685764b88","observation_id":"35884ab3-0563-4fc3-837e-19d5df41dfe4","resolution":{"observed_at":"2026-08-06T15:00:57.946294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.00887","last_updated":"2019-11-22T07:12:00Z","snapshot_observed_at":"2026-07-06T08:34:21.494347Z","submitted_at":"2019-11-03T13:44:42Z","title":"Online Robustness Training for Deep Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"1911.00887","doi":null,"metadata_source":"pith","pith_arxiv_id":"1911.00887","snapshot_observed_at":"2026-08-06T15:00:57.730134Z","title":"Online Robustness Training for Deep Reinforcement Learning","venue":"cs.LG","work_id":"8a915bb2-8866-4356-9299-690503408e69","year":2019},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.663825Z"},"links":{"cited_paper":"/paper/1911.00887","citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:61f414b3ccfdf9e5acf0fab8f1da5940a570903ecbdf692b398a6f057cf6ee60","observation_id":"9ccd6462-8518-4031-bcf8-dcc6cad74966","resolution":{"observed_at":"2026-08-06T15:00:57.737034Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:57.928277Z","title":"Rl-vaegan: Adversarial defense for reinforcement learning agents via style transfer,","venue":null,"work_id":"a85a4130-ec1f-49d5-948c-b61f759c585d","year":2021},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.668269Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:13fad9edcbeda9de2517b7acb835ec7490a6e6016830622c1b50d62c04c0404c","observation_id":"2fd0a059-780f-47f0-a074-61b7f81d85f0","resolution":{"observed_at":"2026-08-06T15:00:57.932591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:57.913998Z","title":"Certified adversarial robustness for deep reinforcement learning,","venue":null,"work_id":"6211d054-3ec9-4102-b223-e4b380c3f9be","year":2020},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.672531Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:3f44136998565147a616469e5699dbfea53cd758e9477dd16c163f822bb807a3","observation_id":"e61f5d43-90b2-452f-bbdf-76af83a0994d","resolution":{"observed_at":"2026-08-06T15:00:57.918505Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:57.899840Z","title":"Robust deep reinforcement learning through adversarial loss,","venue":null,"work_id":"98aaa9ff-8e2f-4a16-8eb5-293da6b7b013","year":2021},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.678036Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:1b95ff4e046bfcbae86f444fb2fdcd77ee39803d2cc1d6769fc75ba2184d47c0","observation_id":"647ab421-c57d-4060-8e3c-9735c1d73ff3","resolution":{"observed_at":"2026-08-06T15:00:57.904335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:57.885946Z","title":"Adversarial attacks and defense in deep reinforcement learning (DRL)-based traffic signal controllers,","venue":null,"work_id":"34e6e4c7-71cc-4226-b568-201924dc6920","year":2021},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.682551Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:7835da5967811fe590bdf1196502c1e910d92b94db2afc4716dda85deb604037","observation_id":"efd12c68-667c-4ee8-89c5-4b18cada1355","resolution":{"observed_at":"2026-08-06T15:00:57.890488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:57.872338Z","title":"The evolution of criticality in deep reinforcement learning,","venue":null,"work_id":"a33c862a-7069-45f5-a7fa-1a7750e2ba80","year":2025},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.686742Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:79a5bea55e0544abe68eabaa6bb5dc840bd0d19e0b2412226e7401eb59357cde","observation_id":"c2cc25dd-5c59-46e3-a36b-5278d7746d60","resolution":{"observed_at":"2026-08-06T15:00:57.876441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:00:57.859069Z","title":"Stable-Baselines3: Reliable reinforcement learning im- plementations,","venue":null,"work_id":"04a0eecc-ab56-41b5-b16c-7b8ab3d3eace","year":2021},"citing_paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T15:00:57.690797Z"},"links":{"citing_paper":"/paper/2507.17070"},"observation_digest":"sha256:2df6f6bcc4bb812365d89b0187c7183304b8ed8956e24cd3d8b55d862d68df8f","observation_id":"23385722-cab6-4b71-b966-41f7e374622d","resolution":{"observed_at":"2026-08-06T15:00:57.863157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.17070","last_updated":"2025-07-22T23:15:11Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T22:20:04.873484Z","submitted_at":"2025-07-22T23:15:11Z","title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":4,"verified_exact":2,"verified_fuzzy":33},"total_outbound_references":41},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 2 inbound Pith citation observations for arXiv:2507.17070."}