{"as_of":"2026-08-22T13:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a7b2092357d92a3feee320f6358c186b0614e0a895fc1a7cb40ac9b9d5615b51","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T18:00:27.410355Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2411.12071/citation-record","integrity":"/paper/2411.12071/integrity","json":"/paper/2411.12071/citation-record.json","paper":"/paper/2411.12071"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T18:00:28.719485Z","title":"IEEE transactions on Computers , 100(1):90–93, 1974","venue":null,"work_id":"19eaaf8b-3164-4370-a243-6352fed7dc96","year":1974},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.138113Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:122c6216522c79b5997dec8820cd8c9622010093bb4432ffeba28f68f62062f0","observation_id":"62d75834-ed94-47db-8218-740bb40bd4f6","resolution":{"observed_at":"2026-08-12T18:00:28.733160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.684893Z","title":"Square attack: a query-efficient black-box adversaria l attack via random 16 search","venue":null,"work_id":"1d79435b-eaa2-4088-b53d-edf83183bbd0","year":null},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.143871Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:1c9fd23612b4e075fb7b32ec77b625b968164050f32dbb2b4a2382510101012f","observation_id":"e18853f7-3297-452c-b28a-ad45ae9a90fa","resolution":{"observed_at":"2026-08-12T18:00:28.702770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.651252Z","title":"Obfu scated gradients give a false sense of security: Circumventing defenses to advers arial examples","venue":null,"work_id":"dded1b8e-9aa2-44cc-bf27-2884fa67667a","year":2018},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.149248Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:945bd37579b114b6715117be34ccd6829f5dcc700fa20d83ffa5d3305373b27e","observation_id":"f414bfc9-bbdf-44ac-9cdb-a4bce13d7d6a","resolution":{"observed_at":"2026-08-12T18:00:28.661731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08254","last_updated":"2022-09-03T14:11:33Z","snapshot_observed_at":"2026-08-17T05:59:48.347864Z","submitted_at":"2021-06-15T16:02:37Z","title":"BEiT: BERT Pre-Training of Image Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08254","snapshot_observed_at":"2026-08-12T18:00:27.156947Z","title":"Beit: Ber t pre-training of image transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.156947Z"},"links":{"cited_paper":"/paper/2106.08254","citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:0f7c87d802582f8b4bd39c8f57067c3e3e42e11a38a3ecc0c7fa05e30597d73b","observation_id":"9fa1e37d-e554-4db8-b2ad-026b1e190a0b","resolution":{"observed_at":"2026-08-12T18:00:27.156947Z","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":"2026-08-12T18:00:28.627614Z","title":"Dec ision-based adver- sarial attacks: Reliable attacks against black-box machin e learning models","venue":null,"work_id":"184f5f7c-b0ea-43f7-a4dc-9d7ca97cf3d5","year":2018},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.166719Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:2d2310c8e6ef7e0c520976dd6911f24a13488d258ff52f37b3ece04562bb3bf9","observation_id":"e66bed57-6be2-4a7e-be77-9e5a06921c9e","resolution":{"observed_at":"2026-08-12T18:00:28.634497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.603159Z","title":"Towards evaluating t he robustness of neural networks","venue":null,"work_id":"16b7faa3-5d21-42d1-b9bd-b127cc9dd204","year":2017},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.172513Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:c40fccfbf67db14a8390d0197a3bc17a0da9f1bbcbd1d35c49139f1ac6b649aa","observation_id":"7b065a2d-4ea7-4876-a62b-0e9aa82b0047","resolution":{"observed_at":"2026-08-12T18:00:28.611576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.579756Z","title":"H opskipjumpattack: A query-efficient decision-based attack","venue":null,"work_id":"78699d1a-0bb3-48d0-a737-be4837abd116","year":2020},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.179150Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:34833f6910502f27d990da37fb02ba513a30a70645e0f2395c171a7b95e0c0e9","observation_id":"c285f546-123c-4c6c-b341-27f19373a170","resolution":{"observed_at":"2026-08-12T18:00:28.585373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.553304Z","title":"Zoo: Zeroth order optimization based black-box attacks to deep n eural networks with- out training substitute models","venue":null,"work_id":"167362cb-dead-4a22-b702-1e5c57047e10","year":2017},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.185673Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:edd4e132d0d62be30c5678dadef195e66d1e5da86a2764a2953e42dc4ff2494c","observation_id":"4b48bbcc-66e0-4d36-85a6-80f4f37dc33e","resolution":{"observed_at":"2026-08-12T18:00:28.560439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.516994Z","title":"Query-efficient hard-label black-box attack: An o ptimization-based approach","venue":null,"work_id":"68b71bcf-0914-49ff-a366-e679d0fc9cea","year":2019},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.191428Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:72c574267ed091f7722b1d09d296d2ec0ec33cfdb56071fec681653b2c675ea9","observation_id":"7959e538-c28f-421a-b260-efe097ed2d37","resolution":{"observed_at":"2026-08-12T18:00:28.528526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.10773","last_updated":"2020-02-14T01:44:07Z","snapshot_observed_at":"2026-08-18T01:23:27.075245Z","submitted_at":"2019-09-24T09:27:08Z","title":"Sign-OPT: A Query-Efficient Hard-label Adversarial Attack","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.10773","snapshot_observed_at":"2026-08-12T18:00:27.197288Z","title":"Sign-opt: A query-efficient hard-label adver sarial attack","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.197288Z"},"links":{"cited_paper":"/paper/1909.10773","citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:c0ac6309dd2055ae01fc2950e9d4eed068ab15fa4b042bb64e673c42ed6b0172","observation_id":"faea15d1-99e4-4ebf-9609-b6f522c0a3d5","resolution":{"observed_at":"2026-08-12T18:00:27.197288Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-19T07:17:20.004918Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-12T18:00:27.202536Z","title":"Explaining and har- nessing adversarial examples","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.202536Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:5c85e979be96c1e595add014e4bb4321e936ad1f3055cb801be3c2b49edbcc1b","observation_id":"035d3f78-e346-45bd-a31c-9845b43e731f","resolution":{"observed_at":"2026-08-12T18:00:27.202536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00752","last_updated":"2024-05-31T17:55:27Z","snapshot_observed_at":"2026-08-17T20:47:46.242385Z","submitted_at":"2023-12-01T18:01:34Z","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00752","snapshot_observed_at":"2026-08-12T18:00:27.209507Z","title":"Mamba: Linear-time sequence mode ling with selective state spaces","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.209507Z"},"links":{"cited_paper":"/paper/2312.00752","citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:c850f3520b913c4c8ebfb3b9fb29f8b0c813a911c03cb9241e3e368fb4690faa","observation_id":"c6656ab9-66cc-4034-8efd-b834af796782","resolution":{"observed_at":"2026-08-12T18:00:27.209507Z","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":"2026-08-12T18:00:28.481910Z","title":"D eep residual learning for image recognition","venue":null,"work_id":"2f550456-bc28-494a-9b19-a2e7a9288d8e","year":2016},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.216177Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:1b6d8d464d663128f43225b2fb5e8e5374402e8255a6142551de0bf32819d2fa","observation_id":"9be425fb-3a56-4ee5-ba93-6dbe3d4ec34b","resolution":{"observed_at":"2026-08-12T18:00:28.493504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.461975Z","title":"Densely connected convolutional networks","venue":null,"work_id":"e5853bab-e01a-45f5-b1f9-22c21a067000","year":2017},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.221952Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:f5d7b6d4d4e7a95e64ffd7a81c1ee361464267f8560ac041899bd0fcad12a5a1","observation_id":"2ca2b907-4c3d-445d-8a85-be5937249dd9","resolution":{"observed_at":"2026-08-12T18:00:28.469205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1502.03167","last_updated":"2015-03-02T20:44:12Z","snapshot_observed_at":"2026-08-12T21:01:12.961874Z","submitted_at":"2015-02-11T01:44:18Z","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.03167","snapshot_observed_at":"2026-08-12T18:00:27.228337Z","title":"Batch normalization: Accelerating deep n etwork training by reduc- ing internal covariate shift","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.228337Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:dd8deb3b783956063e56d2f79d272eb901b2be2815295c60bc8a10098e5a3399","observation_id":"2bc13463-2db3-4071-8653-9f466d7d8c77","resolution":{"observed_at":"2026-08-12T18:00:27.228337Z","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":"2026-08-12T18:00:28.439498Z","title":"Reinforcement learning: A survey","venue":null,"work_id":"06e99962-885d-47db-90cd-1bf5a7b5b108","year":1996},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.237249Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:b5a381431f3bce189692bf71b9dcabb7a7f4acee849467b3d9fef6a319de1b8d","observation_id":"bafc02b5-d6b6-4ff7-a5c8-f9c366a7ecf0","resolution":{"observed_at":"2026-08-12T18:00:28.445906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.410843Z","title":"Robust d ecision-based black-box adversarial attack via coarse-to-fine random sea rch","venue":null,"work_id":"1f7f683d-aa9d-422d-92c3-71aa78a73c14","year":2021},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.243769Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:68f447aa7618442ce3c51becddfb6420f82f862838b09cfcb2f99585fccbe84d","observation_id":"24f04f29-55c2-4b8e-a2f6-6fda62aa88b5","resolution":{"observed_at":"2026-08-12T18:00:28.420673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.387049Z","title":"Big transfer (bit): Genera l visual representation learning","venue":null,"work_id":"5452d3f5-9c16-411f-bf2e-c1240ccb6299","year":2020},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.249980Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:91d6f438029185646c185d3bfe2f055e85d5a86537fa46b3cb06008c7c280e6a","observation_id":"89fa69b4-5c73-43d1-8725-e052e75ee754","resolution":{"observed_at":"2026-08-12T18:00:28.393869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.339544Z","title":"Adve rsarial examples in the physical world","venue":null,"work_id":"707afe21-b27d-4002-9a56-2b3f0e72822d","year":2018},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.255714Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:a2acaab7bd480ab80c6c98945198f4a7b6b18d3dce7d25b90ba6d9317b013e82","observation_id":"9b1557c3-8d15-4019-8ad0-6d10e519290d","resolution":{"observed_at":"2026-08-12T18:00:28.369544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-12T18:00:27.264845Z","title":"Pre-training of deep bidirec tional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.264845Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:8e6939c4e64b9e7cca7fe83801c0b3863722a45b6f081ae0eb0b6c04465b68e6","observation_id":"d398ed80-934f-465a-8167-9ccb7d3f4218","resolution":{"observed_at":"2026-08-12T18:00:27.264845Z","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":"2026-08-12T18:00:28.312658Z","title":"Qeba: Query- efficient boundary-based blackbox attack","venue":null,"work_id":"df03530c-80af-4932-8963-8cfddc9f46ca","year":2020},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.272852Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:55b84b328400c8990fe11a5632b1c2e2ac816feb1eae8e332a79d512f382d0ac","observation_id":"a618ed5c-71ee-4a4b-8bc4-167d2da737e3","resolution":{"observed_at":"2026-08-12T18:00:28.321435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.02797","last_updated":"2021-12-06T05:59:30Z","snapshot_observed_at":"2026-08-16T17:36:51.652608Z","submitted_at":"2021-12-06T05:59:30Z","title":"ML Attack Models: Adversarial Attacks and Data Poisoning Attacks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.02797","snapshot_observed_at":"2026-08-12T18:00:27.280507Z","title":"M l attack models: Adversarial attacks and data poisoning attacks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.280507Z"},"links":{"cited_paper":"/paper/2112.02797","citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:aa95e5ac79e2046e877fc98b83e17db118426a0b7572d611fe85add74090210d","observation_id":"e604c534-3a77-4f20-8921-69bbc5083b08","resolution":{"observed_at":"2026-08-12T18:00:27.280507Z","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":"2026-08-12T18:00:28.272147Z","title":"A geometry- inspired decision-based attack","venue":null,"work_id":"255293f1-2d6a-4244-81f7-3116fc90d8a9","year":2019},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.286841Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:c13f719b2ea54ae74c827d85774ce899c455a649b6d8d54589394db8f5fe6696","observation_id":"8f283728-b53f-4eda-bed9-c0880b92436d","resolution":{"observed_at":"2026-08-12T18:00:28.281203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.240450Z","title":"Back in black: A comparative evaluation of recent state-of-the- art black-box attacks","venue":null,"work_id":"1e7db844-1ef5-40ea-aac0-c5aeb6177cac","year":2021},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.292693Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:d9eb0ab048462e00a9bede072e96cdc709b90d6fbca4fcc5f95e6848f82bf9d4","observation_id":"32023d30-4d03-4139-96b7-90dbc17c2493","resolution":{"observed_at":"2026-08-12T18:00:28.250978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.215197Z","title":"On t he robustness of vision transformers to adversarial examples","venue":null,"work_id":"947710cd-8dec-4276-9385-30ed1a85d580","year":2021},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.298352Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:e5a7c814894047b2b62470e1cf79c53a3fb900b0cf1a8f8755780bd811bd3be3","observation_id":"d8544d71-2a62-41d6-abd8-d4781704e92b","resolution":{"observed_at":"2026-08-12T18:00:28.222263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.188581Z","title":"Surfre e: a fast surrogate- free black-box attack","venue":null,"work_id":"16c65c73-4616-4fa7-9937-c89ee0dda594","year":2021},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.304665Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:4c7dc19dc5f405af602234841639f3dd6cdb975a32d322e6ad6c1c1cf7e4b046","observation_id":"03e243cb-fd95-4c59-87ff-17733b9d17a7","resolution":{"observed_at":"2026-08-12T18:00:28.195097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.161073Z","title":"Convergence of q-learning: A simple p roof","venue":null,"work_id":"fc73f7f8-5ebc-4e11-a4c9-b21483342736","year":2001},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.310644Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:f63d02958c2a255d210f127796caeeae704de6cc277ad06394aa7524139a5fbc","observation_id":"078e4e3a-9fc9-412f-870f-78c4f01a5000","resolution":{"observed_at":"2026-08-12T18:00:28.171482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.133067Z","title":"Human-level control through deep reinfor cement learning","venue":null,"work_id":"566dd664-962e-4388-99bd-ef89ba67a48c","year":2015},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.317948Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:7341911c5e2919c90f5d6923eff59b65ff26bd01455d0af99e417811b01a6e1f","observation_id":"f1ea7674-7738-4135-9e6d-ec7b42bc6e84","resolution":{"observed_at":"2026-08-12T18:00:28.142873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.096922Z","title":"Practical black-box attacks agai nst machine learning","venue":null,"work_id":"426b32d7-1037-45c1-b5fa-610acf659fb0","year":2017},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.324179Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:c953f7cc5f8a07054a1053b5954ba35874c2e99f1b16a72d56bf52137c8848d1","observation_id":"218c58b0-ab4b-4194-964d-bf10811a428c","resolution":{"observed_at":"2026-08-12T18:00:28.107036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.064090Z","title":"Geoda: a geometric framework for black-box adversarial att acks","venue":null,"work_id":"22ec3f19-1007-435d-972b-3a73747815f2","year":2020},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.330314Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:f38464e58974da282d4c34ef2be0cda6ca946bc84efd2c394f9e5969bdd205de","observation_id":"5c0a8c8c-00d8-48fa-97f2-c904bf92c270","resolution":{"observed_at":"2026-08-12T18:00:28.072916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:28.033211Z","title":"Cgba: curvature- aware geometric black-box attack","venue":null,"work_id":"2dad49aa-f503-40da-b37c-ffe2147d831a","year":2023},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.335938Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:4560312fe207dc0f3d092de39d37b3cbd2b725b7e082188cc5c0246e93e8bf59","observation_id":"4fddfd8d-96a3-4d1e-8bde-5a414af40210","resolution":{"observed_at":"2026-08-12T18:00:28.042475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:27.998837Z","title":"Decision- based query efficient adversarial attack via adaptive bounda ry learning","venue":null,"work_id":"2d93f0b4-5ab5-4814-9511-bcf48180c357","year":2023},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.341879Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:4b4000b0f10d9258c1279c95cc6ca5eb13dd57e8099ec99e245fde84f3cdf3c7","observation_id":"4650ed7f-67c4-41a2-b970-471724d8e1c9","resolution":{"observed_at":"2026-08-12T18:00:28.005015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:27.976083Z","title":"D ecision-based black- box attack against vision transformers via patch-wise adve rsarial removal","venue":null,"work_id":"2bbda57b-0129-46d2-aecf-3d8d97e733e1","year":2022},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.348556Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:76518a82866793d932691e246a748332320dbc35b322278f475f478e3d8ce4f8","observation_id":"fc1d788d-0efb-479e-ab37-935c537245d4","resolution":{"observed_at":"2026-08-12T18:00:27.982005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-17T19:17:06.411141Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-12T18:00:27.354361Z","title":"Very deep convolutional networks for l arge-scale image recog- nition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.354361Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:eb35cdc53af21a067b0bb3ce8058f71040636d7a98dca40cbfedcc5a86ed2d52","observation_id":"909b9f32-4878-4f4c-83a5-eafee1e9dfba","resolution":{"observed_at":"2026-08-12T18:00:27.354361Z","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":"2026-08-12T18:00:27.938657Z","title":"Bounceat tack: A query-efficient decision-based adversarial attack by bouncing into the wil d","venue":null,"work_id":"22e4de24-c96f-42b9-a60a-d57be8f09d59","year":2024},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.360706Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:a18d9cf75aac1733aee1b4625b59e195d2147c816d9592f9876a87dffafc20ce","observation_id":"e4a08276-fc33-4de6-bb78-44b40b890a6d","resolution":{"observed_at":"2026-08-12T18:00:27.946614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.10609","last_updated":"2021-03-19T03:10:32Z","snapshot_observed_at":"2026-08-16T18:37:50.393278Z","submitted_at":"2021-03-19T03:10:32Z","title":"Boosting Adversarial Transferability through Enhanced Momentum","version":1},"cited_work":{"arxiv_id":"2103.10609","doi":null,"metadata_source":"pith","pith_arxiv_id":"2103.10609","snapshot_observed_at":"2026-08-12T18:00:27.499224Z","title":"Boosting Adversarial Transferability through Enhanced Momentum","venue":"cs.CV","work_id":"f6184cf4-0794-45d3-99ee-2b4f37b0a7ff","year":2021},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.366846Z"},"links":{"cited_paper":"/paper/2103.10609","citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:9ed6b6b092c448188f45fb9f799ec6ff54ac46b0964788d877a1e36f6d6b5df9","observation_id":"501b26de-f309-48fa-b1fc-cb82a7e1bc19","resolution":{"observed_at":"2026-08-12T18:00:27.511101Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:27.900836Z","title":"Triangle attack: A query-efficient decision- based adversarial attack","venue":null,"work_id":"df9cd636-d286-43f5-be3a-b0f644db92ef","year":null},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.378223Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:b28e06b7939c8d012726832d7b4f046911488e07d6bdab9a5b8c6a27f59911f4","observation_id":"89a4ffcc-ed33-4886-b79f-c27c5a8973a0","resolution":{"observed_at":"2026-08-12T18:00:27.915361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:27.864754Z","title":"Better diffusion models further improve adversarial traini ng","venue":null,"work_id":"897def9d-5e9a-4eef-b8a8-f246d3267b0d","year":2023},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.384260Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:79ee99a9b3562bc173006dfa000f9e31612a1491a5cd9689514d3e909f96a550","observation_id":"722a6c35-88ca-4517-b439-6ddc3d4792e4","resolution":{"observed_at":"2026-08-12T18:00:27.873641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:27.832312Z","title":"Q-learning","venue":null,"work_id":"18a52e1b-f555-4f74-a0fa-73bc230d9f7d","year":1992},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.391025Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:3dd980840e7deb74682e5bef2b21e128b1798d29d9767b8a9f32d78a8b2c7474","observation_id":"128fbe44-6a89-489e-8d02-3d7c7ffefd86","resolution":{"observed_at":"2026-08-12T18:00:27.839983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:27.803503Z","title":"Learning fr om delayed rewards","venue":null,"work_id":"af9034c8-b538-443b-878c-27a5e789b0c9","year":1989},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.397520Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:bf8f555c8dbf183da699dbf48a1740c1ce0d43c60df4ea840fa0acfe821d7eb8","observation_id":"c4075266-5b45-4a38-a079-f9d94588a486","resolution":{"observed_at":"2026-08-12T18:00:27.810790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-12T18:00:27.781993Z","title":"Qe-dba: Q uery-efficient decision-based adversarial attacks via bayesian optimiza tion","venue":null,"work_id":"ff0467ee-4743-4ff8-94b6-05d9147847ea","year":2024},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.402690Z"},"links":{"citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:60a762a274795eb46aa4b0e89c51450eb38ccfae0176ae8b05971f36161e6efe","observation_id":"c76907bf-9c5d-4b5a-8561-4abc77fcfd04","resolution":{"observed_at":"2026-08-12T18:00:27.789117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.09417","last_updated":"2024-11-14T02:00:33Z","snapshot_observed_at":"2026-08-14T11:12:31.002605Z","submitted_at":"2024-01-17T18:56:18Z","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.09417","snapshot_observed_at":"2026-08-12T18:00:27.410355Z","title":"Vision mamba: Efficient visual representation lea rning with bidirec- tional state space model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T18:00:27.410355Z"},"links":{"cited_paper":"/paper/2401.09417","citing_paper":"/paper/2411.12071"},"observation_digest":"sha256:8d218ebabfa0edc84146790805c51eee49c0eeeeffe797c02e3e4a482e5f5982","observation_id":"217a918f-b974-49c3-8630-8fd0e26ef302","resolution":{"observed_at":"2026-08-12T18:00:27.410355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.12071","last_updated":"2024-11-18T21:31:24Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T16:33:16.054505Z","submitted_at":"2024-11-18T21:31:24Z","title":"Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":1,"verified_fuzzy":32},"total_outbound_references":42},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2411.12071."}