{"as_of":"2026-08-17T22:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d0513b2142e91eac87a1cd8280c4b571a0dac25a6771b8954ff8ca08d80fb645","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:32:58.981877Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2506.23977/citation-record","integrity":"/paper/2506.23977/integrity","json":"/paper/2506.23977/citation-record.json","paper":"/paper/2506.23977"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:32:59.540630Z","title":"Efficient and accurate estimation of lipschitz constants for deep neural networks,","venue":null,"work_id":"6d1aafd0-0a2c-452b-90f2-365f4ad0929c","year":2019},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.843596Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:d68ceeecaaf7d3df3ed2373205338d0eff74e77c4d00eb89c3d195d5bbc0bc37","observation_id":"a53c1a4c-d05e-49c7-8226-d08497901d4f","resolution":{"observed_at":"2026-08-06T21:32:59.545325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.523536Z","title":"Goodfellow, Y","venue":null,"work_id":"21887b1a-433d-48ee-a714-4b18381b4b02","year":2016},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.848741Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:f0209986032614c2a625202ac242ef001f52151a73c5dbc0cdd172025fbbabea","observation_id":"c92f81e2-9650-4045-90c2-b424eb520a02","resolution":{"observed_at":"2026-08-06T21:32:59.528350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:32:58.853529Z","title":"Sequence to sequence learning with neural networks,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.853529Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:bb0569be9a7a67fd133db11b4ca336afe6b73ef8ed018a26d56141de21ca4368","observation_id":"c8ab21f8-714d-49e4-9f2c-879fc3d1f783","resolution":{"observed_at":"2026-08-06T21:32:58.853529Z","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":"2026-08-06T21:32:59.492682Z","title":"Globally-robust neural net- works,","venue":null,"work_id":"d664a0d5-320d-4201-b95e-aa4b63e8a40c","year":2021},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.858394Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:e747f8aed5da4796da01eeeab7097ab006f75208487cda114bb4db730862b561","observation_id":"9cfcb171-d5e8-4e9c-9d07-2f27d3dfbac8","resolution":{"observed_at":"2026-08-06T21:32:59.499314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.05855","last_updated":"2017-12-15T22:01:52Z","snapshot_observed_at":"2026-08-14T20:03:08.264278Z","submitted_at":"2017-12-15T22:01:52Z","title":"A Berkeley View of Systems Challenges for AI","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.05855","snapshot_observed_at":"2026-08-06T21:32:58.863644Z","title":"A berkeley view of systems challenges for ai,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.863644Z"},"links":{"cited_paper":"/paper/1712.05855","citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:67c7ee6b01d08db47f55ad99136214e5fa2d5f31bafec527490079bd1915a42d","observation_id":"f014b281-7b92-4970-ad5b-6191c1ed7bcd","resolution":{"observed_at":"2026-08-06T21:32:58.863644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6199","last_updated":"2014-02-19T16:33:14Z","snapshot_observed_at":"2026-08-15T16:41:15.505782Z","submitted_at":"2013-12-21T03:36:08Z","title":"Intriguing properties of neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6199","snapshot_observed_at":"2026-08-06T21:32:58.869407Z","title":"Intriguing properties of neural networks,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.869407Z"},"links":{"cited_paper":"/paper/1312.6199","citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:a761ede99ea2f822c35ba583692e1c2dda4e4084bded26051d4949858ba413da","observation_id":"b0190c98-f40b-47fc-b88b-3e91e947bea8","resolution":{"observed_at":"2026-08-06T21:32:58.869407Z","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":"2026-08-06T21:32:59.472480Z","title":"Direct parameterization of lipschitz- bounded deep networks,","venue":null,"work_id":"aae0f893-2b58-4c1e-95c5-0b950f9d2699","year":2023},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.875302Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:8912939b1935abb0dcc3c9e9aba665e5e62759bd8dd8ff8c52fd27fa590436a3","observation_id":"b53ac602-03a3-4c32-8384-6a9a2454f3c0","resolution":{"observed_at":"2026-08-06T21:32:59.478716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:32:58.880365Z","title":"Distillation as a defense to adversarial perturbations against deep neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.880365Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:e7ae2c68df7f87614ec0b4d99e253936cc51d325b926d766230b1b2bcf933b77","observation_id":"1a30aeea-b6c4-4df1-95b2-54dd3e0fdd63","resolution":{"observed_at":"2026-08-06T21:32:58.880365Z","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":"2026-08-06T21:32:59.440160Z","title":"To- wards defending multiple lp-norm bounded adversarial perturbations via gated batch normalization,","venue":null,"work_id":"7a566e4a-b225-4840-8add-e19e176aaf82","year":2024},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.885398Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:664cfa56f7fdd063888bccdb9324f1d5024ce20b99e85aec41fff5206b2fc73c","observation_id":"cd1f6c90-935f-42a5-af06-8d2c20417fc3","resolution":{"observed_at":"2026-08-06T21:32:59.447472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.419761Z","title":"Certified ro- bustness via dynamic margin maximization and improved lipschitz regularization,","venue":null,"work_id":"407fba99-9c0b-4138-ac05-c29d53e4f1b5","year":2023},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.890099Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:7e00529a7963129df6cc4813ab58d9ffd4a2e8a9e0b5a014057ca1312a1fccae","observation_id":"47b207ff-1864-4a5f-a3ae-062e66b43fe7","resolution":{"observed_at":"2026-08-06T21:32:59.425690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.400449Z","title":"Training robust neural networks using lipschitz bounds,","venue":null,"work_id":"d8985c46-a6ec-4d82-a3ea-b8ce0e571971","year":2021},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.894917Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:ba0b1057b769b8ca991ef3ee631807344fdb09041b4d8a9912f058de189c54ae","observation_id":"6194965e-d364-4de3-ae84-e6b677adbcea","resolution":{"observed_at":"2026-08-06T21:32:59.405398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:32:58.899943Z","title":"Safe learning in robotics: From learning-based control to safe reinforcement learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.899943Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:fd0e314ff22547e7f8293aed39f43ed8f451c8c1949227f067d208e80471a29c","observation_id":"9ca8f32d-a1b2-42cc-817d-9d69094f65d5","resolution":{"observed_at":"2026-08-06T21:32:58.899943Z","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":"2026-08-06T21:32:59.369278Z","title":"Spectrally-normalized margin bounds for neural networks,","venue":null,"work_id":"4d9d9e82-f5e1-491e-95c4-d37a5e0d9b0a","year":2017},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.904948Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:151e5645a96dcf0ca3cf671acec97a5e0cad42a4ba987e1f6497c420384c5bbf","observation_id":"c712c154-0097-4549-b192-fbb3c699e66c","resolution":{"observed_at":"2026-08-06T21:32:59.375108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.351653Z","title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation,","venue":null,"work_id":"748116b8-31f9-44fe-9d59-93cef20f1f05","year":2018},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.909412Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:c17af9522fbd4d4d9b9dd26dfd11d7026605da28689b0043212cae0f01df0bf6","observation_id":"00bcb5b8-db10-4f4d-b979-7db529d4849e","resolution":{"observed_at":"2026-08-06T21:32:59.356897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.333977Z","title":"Regularisation of neural networks by enforcing lipschitz continuity,","venue":null,"work_id":"bdd6d070-0ca6-47c9-943e-e1d99daa1a8e","year":2021},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.914686Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:e0763ea84bc5e8f37542ad1709876c84d6f1c4c23f6e7480dac636d2dcea0457","observation_id":"ef56b123-94b7-4e38-9ac7-9303c8c7a962","resolution":{"observed_at":"2026-08-06T21:32:59.339950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.09592","last_updated":"2019-02-25T20:04:13Z","snapshot_observed_at":"2026-08-14T17:11:27.185858Z","submitted_at":"2019-02-25T20:04:13Z","title":"Verification of Non-Linear Specifications for Neural Networks","version":1},"cited_work":{"arxiv_id":"1902.09592","doi":null,"metadata_source":"pith","pith_arxiv_id":"1902.09592","snapshot_observed_at":"2026-08-06T21:32:59.054115Z","title":"Verification of Non-Linear Specifications for Neural Networks","venue":"cs.LG","work_id":"f210b07a-953e-40ac-9508-dae5fd8539a3","year":2019},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.919569Z"},"links":{"cited_paper":"/paper/1902.09592","citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:8f9c6a8a8bb82706606db4df6e8036755cec043a1a67cf9fc06cfaf6baad69a3","observation_id":"38c55ea9-2c0e-4ef1-ae66-f67415e7995c","resolution":{"observed_at":"2026-08-06T21:32:59.060301Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.317666Z","title":"Efficiently computing local lipschitz constants of neural networks via bound propagation,","venue":null,"work_id":"36308355-1699-409e-b61f-29b1f906d6d7","year":2022},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.925109Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:095813f6c32ca572e8ef14a8dd5c6e3f5ee65e72f173725cab2dce4d2ccd4405","observation_id":"7b5198bb-76c6-413d-a7d1-2ae9158c7f46","resolution":{"observed_at":"2026-08-06T21:32:59.322404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.301474Z","title":"Chordal sparsity for sdp-based neural network verification,","venue":null,"work_id":"23e8f9af-316d-4bd0-8d3c-8a44a3483e66","year":2024},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.930091Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:9a2463aa11a06b2cfa22b5528dcdee12deb6f1b006c68a62ae6740abea13b416","observation_id":"b601a708-b535-4870-97d6-cf08e08a9127","resolution":{"observed_at":"2026-08-06T21:32:59.306313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.277777Z","title":"Imitation learning with stability and safety guarantees,","venue":null,"work_id":"87f7fc38-1f8b-43ee-9ba8-12e0ae027ec0","year":2021},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.935639Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:f43007e30e74881fd479ef1f4409b6317457fa3a2f7201766dc5f47906dd13d8","observation_id":"013dec9d-0ee1-4666-88e4-0ae00b8776a8","resolution":{"observed_at":"2026-08-06T21:32:59.282503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.260592Z","title":"Learning neural networks under input-output specifications,","venue":null,"work_id":"7ccf4f86-461f-44c7-8ca3-f3de7799b60f","year":2022},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.940587Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:0c8b1fd2dd6c4744e267f6aa928dfee3d748d6df1c6bd26824464f1dd86685c6","observation_id":"437cfbde-9307-4778-973a-289b0d1a55c7","resolution":{"observed_at":"2026-08-06T21:32:59.265372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.244966Z","title":"Neural network training under semidefinite constraints,","venue":null,"work_id":"11b2f1d0-12df-4179-8091-fca8bd6c447a","year":2022},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.945832Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:6447197bbac944c9b537d060adc0f58f81f71246cb558af23eb9f9e4a04b1cbd","observation_id":"e7b7a4c7-72b9-4900-ac3e-e10ea875316c","resolution":{"observed_at":"2026-08-06T21:32:59.249937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.226445Z","title":"Chordal and factor-width decompositions for scalable semidefinite and polynomial optimization,","venue":null,"work_id":"180a8ff3-41d5-4dfe-9116-776db83e664e","year":2021},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.950656Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:e96eedce48fef2a9948507df58501ea01bd0d12d3231cd6196ca5d575aa4e37d","observation_id":"066f82a0-912d-4dbe-99f6-9abf64009aa2","resolution":{"observed_at":"2026-08-06T21:32:59.232460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.194528Z","title":"Cosmo: A conic operator splitting method for convex conic problems,","venue":null,"work_id":"bb64f809-24b2-4b47-b196-c13bc4722e0c","year":2021},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.955381Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:2841620cac8561bf9394cead16968ec075ede8d7937d1b5950d4d5e1a112b68f","observation_id":"552fd2f6-c9aa-4cf5-badb-c6e2173ca7a9","resolution":{"observed_at":"2026-08-06T21:32:59.202281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.173877Z","title":"On the scalability and memory efficiency of semidefinite programs for lipschitz constant estimation of neural networks,","venue":null,"work_id":"f61f4f6e-f71d-4b1a-bba6-020b30b1b791","year":2024},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.960662Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:d0585ef01ac9109710b615e2a56766368599707cea0269c6822272c0d2544030","observation_id":"faf571c5-8dcf-4e3c-a173-eef8d204b974","resolution":{"observed_at":"2026-08-06T21:32:59.180597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.11432","last_updated":"2025-02-06T04:29:53Z","snapshot_observed_at":"2026-08-17T09:35:47.971379Z","submitted_at":"2024-05-19T03:27:31Z","title":"On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks","version":3},"cited_work":{"arxiv_id":"2405.11432","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.11432","snapshot_observed_at":"2026-08-06T21:32:59.025661Z","title":"On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks","venue":"cs.LG","work_id":"a37a8e73-c8a5-4395-9637-6cf7b8d1759b","year":2024},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.966103Z"},"links":{"cited_paper":"/paper/2405.11432","citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:4017d77b4708ec8c9ea3b0067cc17e5503ba5bf10d4f758fccdb859fc12d9ad5","observation_id":"de42dd65-0663-4869-91e1-e59e5e24e0a3","resolution":{"observed_at":"2026-08-06T21:32:59.033488Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.154450Z","title":"Safety verification and robustness analysis of neural networks via quadratic constraints and semidefinite programming,","venue":null,"work_id":"32247665-a659-49fd-b59e-ed20dc841fab","year":2020},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.971360Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:c44ec2c5acc8ddf3409c0f898dd771208761869f3bae78fe4fd88694036bf486","observation_id":"8f885437-4b77-4064-9d48-dd5f0c01a476","resolution":{"observed_at":"2026-08-06T21:32:59.161299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.136571Z","title":"S-procedure in nolinear control theory,","venue":null,"work_id":"159927bd-be18-49ba-adaf-dcfcbb2d7d70","year":1971},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.976788Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:881f5dca6da50928d948d3c71059ef9bcf1b2711c2e0d063037c5747e32bd6c2","observation_id":"64464053-16de-4649-9cb4-fe47ab7ab47f","resolution":{"observed_at":"2026-08-06T21:32:59.141496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-06T21:32:59.117185Z","title":"Randomized sketches of convex programs with sharp guarantees,","venue":null,"work_id":"e5ea3269-d413-4524-af3d-7b730a0135de","year":2015},"citing_paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T21:32:58.981877Z"},"links":{"citing_paper":"/paper/2506.23977"},"observation_digest":"sha256:9d99fad340139ff83d6be04059bd66df6ee4b36783514985e946bc2fabde5d47","observation_id":"eb4ab0b5-54fc-4eca-bf74-a0a72ab881a3","resolution":{"observed_at":"2026-08-06T21:32:59.122439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.23977","last_updated":"2025-06-30T15:42:23Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T10:14:36.132582Z","submitted_at":"2025-06-30T15:42:23Z","title":"A Scalable Approach for Safe and Robust Learning via Lipschitz-Constrained Networks"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":2,"verified_fuzzy":21},"total_outbound_references":28},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2506.23977."}