{"as_of":"2026-08-18T05:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9daf3c104e9759ca313901dacbbf14c8f202b5227fe28ba0d0eaae437ea2623b","coverage":[{"denominator":25,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":25,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T22:20:50.360256Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-09T13:55:50.997109Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T17:06:04.572624Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"cited_work":{"arxiv_id":"2412.03666","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.03666","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"4d4d633f-3843-4072-8630-4ca82123ac01","year":2021},"citing_paper":{"arxiv_id":"2605.01621","last_updated":"2026-05-02T22:19:44Z","snapshot_observed_at":"2026-08-16T16:23:15.237794Z","submitted_at":"2026-05-02T22:19:44Z","title":"Bilevel learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-09T13:55:50.997109Z"},"links":{"cited_paper":"/paper/2412.03666","citing_paper":"/paper/2605.01621"},"observation_digest":"sha256:3bfea34d11899ccc53314f114732388ddd765c3798d616597e746226b73b47bb","observation_id":"440a5203-4045-4340-8c95-572dbf95b8d0","resolution":{"observed_at":"2026-05-11T17:06:04.574172Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2412.03666/citation-record","integrity":"/paper/2412.03666/integrity","json":"/paper/2412.03666/citation-record.json","paper":"/paper/2412.03666"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:20:50.778317Z","title":"Weak linear bilevel programming problems: existence of solutions via a penalty method","venue":null,"work_id":"db163471-fdfc-4aed-acad-7dbf28f3543a","year":2005},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.240886Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:287d7d252314a592f5df73e55c8e28022f42145b940090bde3a885329abaf968","observation_id":"8615dbcd-4785-49ab-9b0e-956664df85bb","resolution":{"observed_at":"2026-08-11T22:20:50.783205Z","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":"2026-08-11T22:20:50.762848Z","title":"Model selection via bilevel optimization","venue":null,"work_id":"3351edb4-f04c-44e7-88fa-7b7741964346","year":2006},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.246242Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:ea6ce7e29d8c9e04e1aedeacd426c893b0e91c2de7801d0f367520584d3bac1a","observation_id":"8149eff9-c8ec-48fc-94f5-b8b8b374b862","resolution":{"observed_at":"2026-08-11T22:20:50.767788Z","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":"2026-08-11T22:20:50.747316Z","title":"A regularization method for ill-posed bilevel optimization problems","venue":null,"work_id":"2b586837-30ca-44d7-8031-89247f42c43d","year":2006},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.251276Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:87e88bfa1fb8db78ef54f873628d46eb628be6cca068cace227abae3865fe69d","observation_id":"e79b2c67-a09e-4b95-83f1-4750cf80394b","resolution":{"observed_at":"2026-08-11T22:20:50.752171Z","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":"2026-08-11T22:20:50.731463Z","title":"Evasion attacks against machine learning at test time","venue":null,"work_id":"cdeec93d-69d6-4721-86d9-4db310eb6c42","year":2013},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.256441Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:2684d31e5ac87e0ab72558bf768fbab480b8d2ce84ddb211f876c10c565f4d30","observation_id":"3a8e703d-888d-4b99-ae68-a5169a7f00bb","resolution":{"observed_at":"2026-08-11T22:20:50.736613Z","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":"2026-08-11T22:20:50.261777Z","title":"Foundations of bilevel programming","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.261777Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:b60daf3c45e7f60f3d8c000993dc116cc527c9556ffe5d536cf5a825f5fd33c1","observation_id":"8dcce7df-4477-4598-bf02-25e9d44459fa","resolution":{"observed_at":"2026-08-11T22:20:50.261777Z","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":"2026-08-11T22:20:50.706509Z","title":"Bilevel optimization: theory, algorithms and applications","venue":null,"work_id":"9206d821-f9bb-4c91-9ea6-1b37df326eb8","year":2018},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.267677Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:16ce29c0b4c6d2c2b8d4fb2304c107e455d6882ff7905aefbe83a4e18423a307","observation_id":"6e5feca5-4173-4e9b-86d9-2064fac2ee57","resolution":{"observed_at":"2026-08-11T22:20:50.711522Z","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":"2026-08-11T22:20:50.690355Z","title":"Necessary optimality conditions in pessimistic bilevel programming","venue":null,"work_id":"0338916e-3d90-4d8a-90e0-c4e8d227f0fc","year":2014},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.273897Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:7641ff029b34e675cf67627a4424a13f8ba8e1c8d58ed0e41b609a6ec5cd5f3f","observation_id":"cc8c28e1-ed36-49bd-b50e-81a71694771c","resolution":{"observed_at":"2026-08-11T22:20:50.695383Z","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":"2026-08-11T22:20:50.674828Z","title":"Generic methods for optimization-based modeling","venue":null,"work_id":"44f0fd6d-3832-4482-a503-5e1687069fdd","year":2012},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.279222Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:6b7537e678389868527dbd8f27ebfcdb5ef62472eb0b55407d237872fca5c8ea","observation_id":"6969fd3c-ddda-4dd5-a030-8116e8e65f7f","resolution":{"observed_at":"2026-08-11T22:20:50.679580Z","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":"2026-08-11T22:20:50.283922Z","title":"UCI machine learning repository, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.283922Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:f78388a0f8c1e363b7ac89d17464413ef666eb98775c743c036d503fee31f38f","observation_id":"e7d4f756-11ab-4bd9-b8b5-e59dc0927eab","resolution":{"observed_at":"2026-08-11T22:20:50.283922Z","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":"2026-08-11T22:20:50.647347Z","title":"Forward and reverse gradient-based hyperparameter optimization","venue":null,"work_id":"2857f7f8-51d3-4b49-9cc8-e93dd34bbdfe","year":2017},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.288627Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:092feeab1107539e68dea461a2589f251978d681c565a434b17b347694e2113c","observation_id":"400123f8-7dd6-48b9-a25e-7e0cc617cfcf","resolution":{"observed_at":"2026-08-11T22:20:50.653067Z","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":"1806.04910","last_updated":"2018-07-03T14:53:38Z","snapshot_observed_at":"2026-08-14T19:04:21.644005Z","submitted_at":"2018-06-13T09:21:42Z","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","version":2},"cited_work":{"arxiv_id":"1806.04910","doi":null,"metadata_source":"pith","pith_arxiv_id":"1806.04910","snapshot_observed_at":"2026-08-11T22:20:50.443112Z","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","venue":"stat.ML","work_id":"fc250e9b-7ab9-4d97-9f41-cd587d8080c2","year":2018},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.293073Z"},"links":{"cited_paper":"/paper/1806.04910","citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:012b0cd832aaf95357052c786846653351f29478226753b449f90495d77fa18f","observation_id":"7f598fa4-28db-488f-b4a9-18fb97ea896e","resolution":{"observed_at":"2026-08-11T22:20:50.448276Z","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":"2026-08-11T22:20:50.632368Z","title":"Value function based difference-of-convex algorithm for bilevel hyperparameter selection problems","venue":null,"work_id":"2158eb46-d58b-405e-a9ac-808ea0d04098","year":2022},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.298049Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:7c3b9ebe60f5559191108a933aee27b7c23743c7365e266979d88f1b1f51ee87","observation_id":"65b9a67c-e06d-4b41-a49f-5d4f7cbf616e","resolution":{"observed_at":"2026-08-11T22:20:50.637228Z","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":"2026-08-11T22:20:50.617027Z","title":"Deep bilevel learning","venue":null,"work_id":"a6fa1a80-aaad-4c05-99ff-f0f5b3624c63","year":2018},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.302913Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:59439d68b2a7fb78419ed5eada3a23c43e5a2993e73ec810c34f00dd2f7328f1","observation_id":"c007c077-7b59-4c7c-9916-f4a4da315984","resolution":{"observed_at":"2026-08-11T22:20:50.622262Z","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":"2026-08-11T22:20:50.601641Z","title":"Bilevel model selection for support vector machines","venue":null,"work_id":"e12788ff-53eb-4291-b947-33cb74fce3bb","year":2008},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.308059Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:2720d8532ef245b96b5477ad6c8f9605280d25687a9728c5d466a370957891f0","observation_id":"b4e392a0-b0ee-449c-99b8-508ab7398136","resolution":{"observed_at":"2026-08-11T22:20:50.606327Z","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":"2026-08-11T22:20:50.586737Z","title":"Pessimistic bilevel optimization: a survey","venue":null,"work_id":"1b62218e-04cf-4f59-9e58-1d1de798a278","year":2018},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.312589Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:1657ac1c11fd5cf095dd3c6956477b494c2bd130341056c11643545d71da2a48","observation_id":"f42ebaab-2a69-4eb5-b0db-5bdd5ed9d381","resolution":{"observed_at":"2026-08-11T22:20:50.591348Z","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":"2026-08-11T22:20:50.571255Z","title":"A generic first-order algorithmic framework for bi-level programming beyond lower-level singleton","venue":null,"work_id":"e28b93e3-cdd1-4a21-9e60-7c3a7f15e582","year":2020},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.317273Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:d677f78c093cbcd11613bd79c0adf3267fdfe5da44bb122e4d767002eaff8830","observation_id":"cdcab41c-0688-4b4e-acef-d4928ef2b4fc","resolution":{"observed_at":"2026-08-11T22:20:50.576250Z","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":"2026-08-11T22:20:50.555846Z","title":"A value-function-based interior-point method for non-convex bi-level optimization","venue":null,"work_id":"e0164912-9fe7-4bc9-8fa8-0543a87fdd55","year":2021},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.322025Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:5580db1f765662e9538ed37a513a873ff7c28106fd5b6859078715d5d7d3f920","observation_id":"d5f18534-2aa4-40e3-a456-26df585c9884","resolution":{"observed_at":"2026-08-11T22:20:50.560853Z","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":"2026-08-11T22:20:50.540538Z","title":"Weak via strong stackelberg problem: new results","venue":null,"work_id":"de2245f2-99b3-4b51-8b1f-a2eb3b1e88e9","year":1996},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.326668Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:24af2b0a57e92fda5f37639170938609fd4773889b9c117750dc5e73d83b1841","observation_id":"eb8d02df-6665-43db-ba6b-1b4678e0155c","resolution":{"observed_at":"2026-08-11T22:20:50.545336Z","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":"2026-08-11T22:20:50.523919Z","title":"Gradient-based hyperparameter optimization through reversible learning","venue":null,"work_id":"c89ffb22-3ba2-4c6b-a0b3-06dea7d4bf8a","year":2015},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.331162Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:bd286db139df7f2e74ecaa43544545b0ba61f58babcc118b47243000db5af516","observation_id":"b38bf1fe-2d10-4a31-a94b-9484be176ad8","resolution":{"observed_at":"2026-08-11T22:20:50.528918Z","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":"1911.03432","last_updated":"2021-10-05T21:25:32Z","snapshot_observed_at":"2026-08-16T18:36:54.853945Z","submitted_at":"2019-11-08T18:33:29Z","title":"Penalty Method for Inversion-Free Deep Bilevel Optimization","version":6},"cited_work":{"arxiv_id":"1911.03432","doi":null,"metadata_source":"pith","pith_arxiv_id":"1911.03432","snapshot_observed_at":"2026-08-11T22:20:50.421791Z","title":"Penalty Method for Inversion-Free Deep Bilevel Optimization","venue":"cs.LG","work_id":"23900a45-6a3d-4dea-89f6-0b213d1dc6fb","year":2019},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.336285Z"},"links":{"cited_paper":"/paper/1911.03432","citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:510eda3fd6d8eb39536c1ee46f7e122d7c48d8b1c4518156cd5c0e89521f8c25","observation_id":"7a250592-0733-40dd-a773-68eaa80b9c76","resolution":{"observed_at":"2026-08-11T22:20:50.427030Z","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":{"arxiv_id":"1912.10013","last_updated":"2022-05-13T16:15:10Z","snapshot_observed_at":"2026-08-17T23:53:40.946622Z","submitted_at":"2019-12-20T18:41:37Z","title":"secml: A Python Library for Secure and Explainable Machine Learning","version":2},"cited_work":{"arxiv_id":"1912.10013","doi":null,"metadata_source":"pith","pith_arxiv_id":"1912.10013","snapshot_observed_at":"2026-08-11T22:20:50.395721Z","title":"secml: A Python Library for Secure and Explainable Machine Learning","venue":"cs.LG","work_id":"804d9ea0-5604-46aa-b89a-9099997e35c4","year":2019},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.341285Z"},"links":{"cited_paper":"/paper/1912.10013","citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:41db90306122b1ba7e0233157d58e9b12e6b4b72cee9a18a8c5da89ef4d24186","observation_id":"c201e4fd-7457-438a-a751-3673ceefa07d","resolution":{"observed_at":"2026-08-11T22:20:50.404750Z","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":"2026-08-11T22:20:50.507547Z","title":"Hyperparameter optimization with approximate gradient","venue":null,"work_id":"e4d63464-0320-4eca-ba9d-ef22844c772b","year":2016},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.346373Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:47164c05512f3d6e011b26e8bc15609982307eee11df5e863f174117d100d9ec","observation_id":"a22c8212-1e09-4ad6-a349-3321a1132bda","resolution":{"observed_at":"2026-08-11T22:20:50.513017Z","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":"2026-08-11T22:20:50.490247Z","title":"Pessimistic bilevel optimization","venue":null,"work_id":"3a862054-d4dd-4853-8755-d49a578aabfe","year":2013},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.351105Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:d676362b3c3d059f4673b4911ee352e7bfc6be5631e52bd86957e9199f3da65f","observation_id":"96b47c4a-7851-499a-b3a4-89e471a699d2","resolution":{"observed_at":"2026-08-11T22:20:50.495705Z","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":"2026-08-11T22:20:50.474529Z","title":"A practical scheme to compute the pessimistic bilevel optimization problem","venue":null,"work_id":"31267ac3-f133-4cf0-a1cc-7b1ff4ebcfa0","year":2020},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.355632Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:74e7d28933a388428b52767a19b759245e2dbd4b5ad0ed23c8ba043322fba208","observation_id":"6ad5b034-7701-4819-bf4a-ae1f6c008cd5","resolution":{"observed_at":"2026-08-11T22:20:50.479463Z","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":"2026-08-11T22:20:50.459303Z","title":"A solution approach to the weak linear bilevel programming problems","venue":null,"work_id":"f3260f7d-a761-41a3-8444-75e02739a051","year":2016},"citing_paper":{"arxiv_id":"2412.03666","last_updated":"2024-12-04T19:01:20Z","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-11T22:20:50.360256Z"},"links":{"citing_paper":"/paper/2412.03666"},"observation_digest":"sha256:a88dc19deffe26e896b6e528226ea8f68345c5e15e3f10a04a3da037a119ed67","observation_id":"ab750a23-4562-4b6d-9cee-94d0a5dba30e","resolution":{"observed_at":"2026-08-11T22:20:50.464103Z","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":"2412.03666","last_updated":"2024-12-04T19:01:20Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T20:13:17.941122Z","submitted_at":"2024-12-04T19:01:20Z","title":"Hyperparameter Tuning Through Pessimistic Bilevel Optimization"},"reference_resolution":{"displayed":25,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":2,"verified_exact":3,"verified_fuzzy":20},"total_outbound_references":25},"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 18 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 1 inbound Pith citation observation for arXiv:2412.03666."}