{"as_of":"2026-08-09T20:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dd53973558e85c36e7246fc6a339bac56567df0e745e342f732922eb89e87cab","coverage":[{"denominator":92,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":92,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T14:37:13.646442Z","state":"measured"},{"denominator":92,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":92,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2502.15752/citation-record","integrity":"/paper/2502.15752/integrity","json":"/paper/2502.15752/citation-record.json","paper":"/paper/2502.15752"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.228881Z","title":"Universality in learning from linear measurements","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.228881Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:a5f75963ae4c360a04a6db7a3ff9825a84c7ff3a3647d8fb2b933cae60cc85aa","observation_id":"2ccb7b0a-9f83-4716-bfd3-f1740b22088f","resolution":{"observed_at":"2026-08-08T14:37:13.228881Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07356","last_updated":"2024-10-15T17:43:51Z","snapshot_observed_at":"2026-08-09T16:44:25.824725Z","submitted_at":"2024-02-12T01:11:49Z","title":"A Novel Gaussian Min-Max Theorem and its Applications","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07356","snapshot_observed_at":"2026-08-08T14:37:13.234393Z","title":"A novel G aussian min-max theorem and its applications","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.234393Z"},"links":{"cited_paper":"/paper/2402.07356","citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:80ab924c3591b77e621be4796937c979eb8ddbb4f09048928393843ba5f7d351","observation_id":"7197a8f6-aa46-454f-b641-3c5e4eec63f7","resolution":{"observed_at":"2026-08-08T14:37:13.234393Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.239954Z","title":"Regularized linear regression for binary classification","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.239954Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:4cd8904a13c8b89329afd64b44053c70363d740161c84212c03627dffa4a246b","observation_id":"3c52e51b-9d62-4726-99a0-8c9e428a30f8","resolution":{"observed_at":"2026-08-08T14:37:13.239954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.244591Z","title":"Multiple fourier series and fourier integrals","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.244591Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:29bdcf3d1555ba0c869ae6e8e7d99920e0464a7691c9d6a8fa50c3e12312dd58","observation_id":"b576ca13-3a8e-4df2-9495-cf4c48ff7b23","resolution":{"observed_at":"2026-08-08T14:37:13.244591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.13269","last_updated":"2025-05-03T03:39:56Z","snapshot_observed_at":"2026-08-08T06:03:47.362025Z","submitted_at":"2022-06-27T13:02:59Z","title":"Wasserstein Distributionally Robust Estimation in High Dimensions: Performance Analysis and Optimal Hyperparameter Tuning","version":3},"cited_work":{"arxiv_id":"2206.13269","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.13269","snapshot_observed_at":"2026-08-08T14:37:14.045173Z","title":"Wasserstein Distributionally Robust Estimation in High Dimensions: Performance Analysis and Optimal Hyperparameter Tuning","venue":"stat.ML","work_id":"083e8708-8394-4cf7-ac7e-6e8e2e3a7b3d","year":2022},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.249202Z"},"links":{"cited_paper":"/paper/2206.13269","citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:02f1c5b5146ea3b3e9f007ffc9a5ce69301b00dfedbcec2e93f7e011473472b6","observation_id":"df93c902-270f-45ea-95f0-7c24bf3cad2a","resolution":{"observed_at":"2026-08-08T14:37:14.050377Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.254282Z","title":"Limit theorems for distributions invariant under groups of transformations","venue":null,"work_id":null,"year":1960},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.254282Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:4e99cba7d4a8f37017560532ae1604edd674d39e67662a5b3e56c3015976a51e","observation_id":"4a3de194-646d-4f2b-90b3-49cce9908905","resolution":{"observed_at":"2026-08-08T14:37:13.254282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.259356Z","title":"Regularized estimation in sparse high-dimensional time series models","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.259356Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:f71110a28a3b28833d35b1d676f3aece7c59ea163c1279b951738b35b29a76cc","observation_id":"9cc7151d-c0ca-455d-ae45-fa87349e551f","resolution":{"observed_at":"2026-08-08T14:37:13.259356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.263786Z","title":"Reconciling modern machine-learning practice and the classical bias–variance trade-off","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.263786Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:f625c0dee790f04c99b496416dffb4d0617b5c5191679c9da74cc494c9c3a97e","observation_id":"5254d515-04cc-4131-9b07-78bb2a7a8fa0","resolution":{"observed_at":"2026-08-08T14:37:13.263786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.268679Z","title":"Learning invariances in neural networks from training data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.268679Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:54dd54b8ff72b3a970877af07c57821dc2c77bb3e19b5845e9496fe317aac909","observation_id":"3961f29e-8583-4e3f-8458-406c77a113ef","resolution":{"observed_at":"2026-08-08T14:37:13.268679Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.273223Z","title":"Sur l'extension du th \\'e or \\`e me limite du calcul des probabilit \\'e s aux sommes de quantit \\'e s d \\'e pendantes","venue":null,"work_id":null,"year":1927},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.273223Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:606eec3b8decf5035614c099d54a27eb9f24583d713d55a5e323768842951e9f","observation_id":"9390ed00-9aeb-4f56-9fcd-deab2e98b603","resolution":{"observed_at":"2026-08-08T14:37:13.273223Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.279594Z","title":"Probability and measure","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.279594Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:ccbd9e5ccf95e5d21154634ffbafe2714bf7f9f3c481218040442610077cf29f","observation_id":"8d16462e-29e7-42b1-8dca-4dedbdb172a6","resolution":{"observed_at":"2026-08-08T14:37:13.279594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.283990Z","title":"Logistic regression for dependent binary observations","venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.283990Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:49939336d1570b2d2756e108323d8b4e5155a5fb6330611e42aecbbf756b1e64","observation_id":"17e6b210-d6d1-48ec-8126-11c449502aa4","resolution":{"observed_at":"2026-08-08T14:37:13.283990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.288369Z","title":"Basic properties of strong mixing conditions","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.288369Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:b177bf1118d28235230a2582ee52156511ac65c05fb4bb178fdbc28c9a80392d","observation_id":"f9eebf7b-3976-4075-8997-4e95543b84b5","resolution":{"observed_at":"2026-08-08T14:37:13.288369Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.292777Z","title":"Simple technical trading rules and the stochastic properties of stock returns","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.292777Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:1a101f32dfd4e3c36ba47adf0c6da8c1a9ec5a02b8e9f9b6ffc352d9e89210cc","observation_id":"7ff5e418-91a0-48d4-9823-d05b88028984","resolution":{"observed_at":"2026-08-08T14:37:13.292777Z","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":"2026-08-08T14:37:15.050229Z","title":"Distributional and lq norm inequalities for polynomials over convex bodies in rn","venue":null,"work_id":"6842cd2f-3639-4537-a425-51c11a54ac46","year":2001},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.297272Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:13c1c8924c12ae92663cae5e988dcd0a393ee2b9310db2eee718367edba2dbdb","observation_id":"5ff448db-757e-4baf-a86c-b2935c8852d5","resolution":{"observed_at":"2026-08-08T14:37:15.054872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:15.036099Z","title":"Concentration inequalities with exchangeable pairs","venue":null,"work_id":"d56f4294-25b5-4432-861d-b2a2918659ee","year":2005},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.302032Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:454b1412efa6350f9cbe2d1d35878a3c1ac737d6ff07fd8b612f812216713120","observation_id":"44ab01ef-8d45-4f52-b5f7-4e19184a4440","resolution":{"observed_at":"2026-08-08T14:37:15.040695Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:15.021975Z","title":"A group-theoretic framework for data augmentation","venue":null,"work_id":"1e4c11ba-87ae-4ef9-bc84-99c5685c59df","year":2020},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.306835Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:cc63e0b37c059968c0e43919362ab3e7d948b82094885ec8204fcea81c63d27e","observation_id":"3ecc11f1-38f4-44d1-90d4-fe942349a518","resolution":{"observed_at":"2026-08-08T14:37:15.026621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:15.006929Z","title":"Universality of approximate message passing algorithms","venue":null,"work_id":"bd9d97fa-3ba8-4320-97e7-9716e8521c74","year":2021},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.311356Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:ae6050ec3cf19d91b56591c667dc6353176fa13d7917cd6ccaac9d4b1079bee8","observation_id":"cc0b2df7-0494-4cb8-b160-b29ea9654753","resolution":{"observed_at":"2026-08-08T14:37:15.011636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.316222Z","title":"Statistics for spatial data","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.316222Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:e40dde6afbf7115b872412ff5cd4a571f35aeb56beb6b211a4a846364d58a53e","observation_id":"57d19342-0df9-461a-b820-f30ecb4741ed","resolution":{"observed_at":"2026-08-08T14:37:13.316222Z","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":"2026-08-08T14:37:14.983327Z","title":"Time series analysis, volume 286","venue":null,"work_id":"ac3a1ff2-fb59-4ac9-b8e3-4e908910aff3","year":1986},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.321237Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:e20289287c173def0efe18ded3fad7fa877b6a7189de14a715a9ab048f874a94","observation_id":"2f8514ca-f492-408b-8879-4ea5bf6530b7","resolution":{"observed_at":"2026-08-08T14:37:14.987875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.969103Z","title":"Universality laws for G aussian mixtures in generalized linear models","venue":null,"work_id":"7d49a8c8-9d2d-40e3-895d-09b27241b157","year":2024},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.326060Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:ccfbcb6f7a0db92d243b5755df9c470e0b9da386d7d572b16c844f92d09bd5e6","observation_id":"7006f79c-edc8-4f4b-bc16-57d0a5eba434","resolution":{"observed_at":"2026-08-08T14:37:14.973775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.953352Z","title":"A central limit theorem for globally nonstationary near-epoch dependent functions of mixing processes","venue":null,"work_id":"6b35fd73-df50-49b7-a325-6a8754909c18","year":1992},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.330603Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:b4ccc632854b9401ecd7f019e892c22bdfbaeb72c6c7db3103596b7165eb5ea5","observation_id":"55d31433-fa5b-4c4f-ac31-79c5dea9c230","resolution":{"observed_at":"2026-08-08T14:37:14.958914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.937996Z","title":"A model of double descent for high-dimensional binary linear classification","venue":null,"work_id":"92c38fd0-ed72-4e7a-977d-980bbff78b4f","year":2022},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.335050Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:3f78a0453cad8f075097ff3e385a5c372c85588be5756b8c8725a9bf1db44b58","observation_id":"e9513be3-331e-4c7e-a40f-e5009d36f8f9","resolution":{"observed_at":"2026-08-08T14:37:14.942750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.923830Z","title":"A note on empirical processes of strong-mixing sequences","venue":null,"work_id":"cb601fa5-17e6-4cd9-a57f-1df7554b3f47","year":1973},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.339579Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:f8bd054eb2769b23770749b692b811f9eddb037f0ca793119241c599e8c1ca69","observation_id":"d581f984-1a2e-477c-83c8-d646ef74bb19","resolution":{"observed_at":"2026-08-08T14:37:14.928480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.908852Z","title":"On the inherent regularization effects of noise injection during training","venue":null,"work_id":"49328eba-e77a-4cf1-8beb-615b2aca3f05","year":2021},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.344054Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:976932e614221ad504b27762555af62801770e5fdfb0e42513e3fc4b327e1601","observation_id":"93d33782-5006-4015-a08c-544a3537105e","resolution":{"observed_at":"2026-08-08T14:37:14.913531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.894054Z","title":"Message-passing algorithms for compressed sensing","venue":null,"work_id":"360cfdc2-036d-4f70-a7ab-58e928e2c972","year":2009},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.348529Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:af6b06be25900543c48807029fe40f038ffd9504aa948ca20f0c55c06aa0dd91","observation_id":"d067d2b4-4d5d-435b-b10e-332bc27d2676","resolution":{"observed_at":"2026-08-08T14:37:14.898779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.880037Z","title":"Lu, and Subhabrata Sen","venue":null,"work_id":"156411c9-1c2b-458c-adfe-d0442650dd42","year":2023},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.352997Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:8e644e7a32ec7ecf1b6a164f9d831b811bfad398db836e699669e538d9526295","observation_id":"1880195c-46a1-43a1-b6c3-78b6d0522bf7","resolution":{"observed_at":"2026-08-08T14:37:14.884447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.357431Z","title":"Handbook of spatial statistics","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.357431Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:c9d89e8cf2b3d98ad7e89def5a5cb16ba8715da793c4b2fe79eedc7cbf7fbd54","observation_id":"22f114c6-2cfb-4d0c-95d9-6ee69d29274e","resolution":{"observed_at":"2026-08-08T14:37:13.357431Z","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":"2026-08-08T14:37:14.855763Z","title":"Gaussian universality of perceptrons with random labels","venue":null,"work_id":"2bbece39-8fb6-4385-bff2-f8797ca9a96d","year":2024},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.361937Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:29b85ad4bce751e484e489a527bf62c1759bd86c0ea9542e8fc44eb2301f7afd","observation_id":"430e0852-f9a8-42fa-aac5-23744bae44f1","resolution":{"observed_at":"2026-08-08T14:37:14.860540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.840908Z","title":"Some inequalities for G aussian processes and applications","venue":null,"work_id":"e8ea64c0-09dc-43b2-9294-65a9be117ac6","year":1985},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.366431Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:3f65715d1b4477c6224994f744d9f30ad50619f6263831b07369739237738706","observation_id":"c073efb6-7e69-41ee-b32f-4ecbde6deb91","resolution":{"observed_at":"2026-08-08T14:37:14.845680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1502.07831","last_updated":"2016-08-30T15:00:51Z","snapshot_observed_at":"2026-07-06T04:10:26.821170Z","submitted_at":"2015-02-27T09:00:36Z","title":"High Dimensional and Banded Vector Autoregressions","version":2},"cited_work":{"arxiv_id":"1502.07831","doi":null,"metadata_source":"pith","pith_arxiv_id":"1502.07831","snapshot_observed_at":"2026-08-08T14:37:14.025388Z","title":"High Dimensional and Banded Vector Autoregressions","venue":"stat.ME","work_id":"879be406-269d-4103-be87-e8105ac50a33","year":2015},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.371332Z"},"links":{"cited_paper":"/paper/1502.07831","citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:32152447086be8b25cb5c40325d4fbdbd8cbcbb5aca2243dde937463aabffcd5","observation_id":"48243055-bc64-4686-98b4-192d575875ce","resolution":{"observed_at":"2026-08-08T14:37:14.030367Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.375922Z","title":"Universality of regularized regression estimators in high dimensions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.375922Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:ee91c16e9a19bf393c5d6b9cf04eed32e46882bced9760942ceb79a7ce15693f","observation_id":"3b2d6598-7c4d-4f9f-8855-b8636a9d4588","resolution":{"observed_at":"2026-08-08T14:37:13.375922Z","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":"2026-08-08T14:37:14.816703Z","title":"Data augmentation as stochastic optimization","venue":null,"work_id":"f3f52c27-59bf-4ce1-af72-22db1edeffe3","year":2020},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.380211Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:00578ae0fb5fd22c6f15262179767209b5ee85702ffe054fe0e787960f171a97","observation_id":"94fffdea-e98c-44c5-afb5-02a66cc36a72","resolution":{"observed_at":"2026-08-08T14:37:14.821563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.800867Z","title":"Analysis of dichotomous response data from certain toxicological experiments","venue":null,"work_id":"99525e6f-68f7-4e7d-952c-4157ac556951","year":1979},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.384511Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:d76707c5cbb168de23a8dfbc720163f123c733a3b864b75f5ab17d1e2291b857","observation_id":"16c49794-381f-48f4-b5e7-391eff19fa18","resolution":{"observed_at":"2026-08-08T14:37:14.805826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.785480Z","title":"Surprises in high-dimensional ridgeless least squares interpolation","venue":null,"work_id":"cb1b7a5d-9f65-4546-b765-c44e39e581f0","year":2022},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.389016Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:86287a91ac5ca290854645b1d77f943b679cc7401ebef7e2da54758c3f2e7583","observation_id":"9dd85d94-c48d-405f-ab79-1437db65e383","resolution":{"observed_at":"2026-08-08T14:37:14.790138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.393538Z","title":"Universality laws for high-dimensional learning with random features","venue":null,"work_id":null,"year":1932},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.393538Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:62bf18a816b086bc64c9b8ce3d65d2b203a9793546ae4a471c70c0b5f4c5a3e5","observation_id":"0b4b4a42-0326-460a-a422-1968fff18e6c","resolution":{"observed_at":"2026-08-08T14:37:13.393538Z","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":"2202.09134","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.002178Z","title":"Data augmentation in the underparameterized and overparameterized regimes","venue":null,"work_id":"2dffbfee-c254-4875-9897-4452fe7f8c56","year":2022},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.398004Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:3d8a04c8d3444677921fd14795bd6bf2a5a497610499da4114226e548b3c80d2","observation_id":"6730e197-80dc-46e7-9608-850058ab1045","resolution":{"observed_at":"2026-08-08T14:37:14.009539Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.760933Z","title":"A high-dimensional convergence theorem for u-statistics with applications to kernel-based testing","venue":null,"work_id":"5e688f71-5470-4212-a64e-e53e1ab6d42b","year":2023},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.402472Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:6baa7e845574d76109870b29c269e51e4907fc734d70796bc38e9ab1f7b24751","observation_id":"f1dbba7d-12dd-4871-afc3-04219c0d1f84","resolution":{"observed_at":"2026-08-08T14:37:14.765562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.746551Z","title":"Independent and stationary sequences of random variables","venue":null,"work_id":"339a50e4-1bde-46ab-8e2f-e77449037a54","year":1975},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.407302Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:c486269d49d0b5e165adabd6fa3ca4926021e23a54ae018caa8a5d9c2508a56f","observation_id":"af137ab0-1717-4395-8fa0-aa40691cbdfa","resolution":{"observed_at":"2026-08-08T14:37:14.751241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.732721Z","title":"The theory of approximation, volume 11","venue":null,"work_id":"90ab5b7e-2081-4567-b159-9eea03be0534","year":1930},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.411983Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:845be81bd74179043ad8854634845c9c99548bfdcd7e09df0a72baa6d576e8b6","observation_id":"a3f02848-eabb-4bcc-94b1-b372cecb237f","resolution":{"observed_at":"2026-08-08T14:37:14.737373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.716955Z","title":"Precise statistical analysis of classification accuracies for adversarial training","venue":null,"work_id":"4c0959e5-99f6-4347-af06-9db2b79281a5","year":2022},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.416589Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:87fdba24545f04ec79d4c8b78a019bf117b4de4b0737fb7e48980f317bf9fcf4","observation_id":"cd2f4689-3a2e-4d8a-942f-6fa711e32762","resolution":{"observed_at":"2026-08-08T14:37:14.722426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.702808Z","title":"Asymptotic behavior of unregularized and ridge-regularized high-dimensional robust regression estimators : rigorous results, 2013","venue":null,"work_id":"3ac93d3b-3aed-4798-b125-1448225911a6","year":2013},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.421092Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:c62bbd63db64645f4bfe60039cbe7cacb09e809d47826d993638062cc880743a","observation_id":"891e2017-6b24-469a-828f-c47a10b032b8","resolution":{"observed_at":"2026-08-08T14:37:14.707427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.687842Z","title":"Label-imbalanced and group-sensitive classification under overparameterization","venue":null,"work_id":"55a03977-8569-4fc0-b0ad-d0f09f89b65b","year":2021},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.426306Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:02178ca78ded0b654199ddbe236912ac6b764fa36ed394a4834165338a2bd313","observation_id":"868abb53-570f-4da8-b0ad-f498d371d6cc","resolution":{"observed_at":"2026-08-08T14:37:14.692907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.672512Z","title":"Applications of the lindeberg principle in communications and statistical learning","venue":null,"work_id":"588dc9e9-8633-4767-8382-3a6911868cdf","year":2011},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.430701Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:ba9054292b5cfd4a35956f35b0d8dc471167905ad00683d3f379961e8e5335a1","observation_id":"d4f0e21f-5212-47d2-8d5f-e7c3c74ecde1","resolution":{"observed_at":"2026-08-08T14:37:14.677151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.657359Z","title":"Universality in block dependent linear models with applications to nonparametric regression","venue":null,"work_id":"cb8cfe82-8746-4a6f-bef8-fe9b14e720c9","year":2024},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.435118Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:47c6613fda58c18dbc6d433d2d45a2f4719b3af4012f1f91511e9cbf1bdef4b3","observation_id":"d83f31a0-268c-4e51-88d7-d26e9e74258c","resolution":{"observed_at":"2026-08-08T14:37:14.663083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.642922Z","title":"Probability in Banach Spaces: isoperimetry and processes","venue":null,"work_id":"1e36512d-c637-4bf8-9e3e-3389c73a19a5","year":1991},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.439638Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:c8d9ffadf4b4aa0eae8d235a27fb975c83a00fe82445bf653b5653ed98cd92ed","observation_id":"bf9ded2a-e032-4238-ac48-6fe89d983581","resolution":{"observed_at":"2026-08-08T14:37:14.647465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.628108Z","title":"The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective","venue":null,"work_id":"e432eb98-3ed0-4cce-8acb-d97213279e3d","year":2024},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.444226Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:bbebb7ea77d6e374605d3cd2f771ce2f77b7105d8ef3e2fd98b7b5ec7952ea9a","observation_id":"713cabd1-154d-43a2-b652-29e0e49bb624","resolution":{"observed_at":"2026-08-08T14:37:14.632868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.613170Z","title":"On the benefits of invariance in neural networks","venue":null,"work_id":"c361bafa-67fa-46ba-b43e-e8726a7a4d93","year":2019},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.448705Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:03c5ef6751f14326ab6e0c21cfba2a68e460c0a951ca91a3880e1adfb7ecd6f8","observation_id":"5b0bb5e1-37bb-4ccb-ac9a-2e9cfb4ab459","resolution":{"observed_at":"2026-08-08T14:37:14.617859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.453054Z","title":"The generalization error of random features regression: Precise asymptotics and the double descent curve","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.453054Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:aa4d8ee0e39c1e4e11426a39c2604c2e351a9deb65680ef7ca6ad963f959fa5c","observation_id":"0a212e06-92b4-4cc2-aaa0-b9089e6bb309","resolution":{"observed_at":"2026-08-08T14:37:13.453054Z","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":"2026-08-08T14:37:14.589412Z","title":"The role of regularization in classification of high-dimensional noisy G aussian mixture","venue":null,"work_id":"c138d52c-0131-4dc0-993a-2653fc3c32d8","year":2020},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.457414Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:d23086da39e9b81bd6ed9c4e8f9598d7f4ee38729fcbb87034b252b162b22324","observation_id":"4aefc7a4-64f8-47c7-be58-b0e650fe7244","resolution":{"observed_at":"2026-08-08T14:37:14.594294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.575255Z","title":"Universality of the elastic net error","venue":null,"work_id":"e867de9d-6cdb-456a-8b17-b3a80b3ba353","year":2017},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.462011Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:0410904c1cbbcca8a1ec455f90b6dea8e78a93900b5064264738f069c510ec58","observation_id":"a2075ad3-40b3-4cd5-ac71-9e2b18d8e407","resolution":{"observed_at":"2026-08-08T14:37:14.579749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.466171Z","title":"Universality of empirical risk minimization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.466171Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:6c8e44edd095e64cc23a2cb0b9794f4c809ca0fa4a2fe0b0fbe8d646a792c100","observation_id":"1af252eb-972c-495e-a871-0e677db81978","resolution":{"observed_at":"2026-08-08T14:37:13.466171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00176","last_updated":"2023-09-29T22:45:56Z","snapshot_observed_at":"2026-07-06T16:25:46.699214Z","submitted_at":"2023-09-29T22:45:56Z","title":"Universality of max-margin classifiers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00176","snapshot_observed_at":"2026-08-08T14:37:13.470662Z","title":"Universality of max-margin classifiers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.470662Z"},"links":{"cited_paper":"/paper/2310.00176","citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:25ccd75ce34aa8c1ec7586259f91d7343acf8b744a8bc71c3cf516d238637d89","observation_id":"5e6d5f04-4fcd-452a-809b-05fd50ccb850","resolution":{"observed_at":"2026-08-08T14:37:13.470662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.03200","last_updated":"2024-09-24T10:54:56Z","snapshot_observed_at":"2026-07-06T11:55:13.881828Z","submitted_at":"2021-10-07T06:19:11Z","title":"High Dimensional Logistic Regression Under Network Dependence","version":3},"cited_work":{"arxiv_id":"2110.03200","doi":null,"metadata_source":"pith","pith_arxiv_id":"2110.03200","snapshot_observed_at":"2026-08-08T14:37:13.730977Z","title":"High Dimensional Logistic Regression Under Network Dependence","venue":"math.ST","work_id":"48bff3f7-e460-46dd-9e7e-5ed99034242e","year":2021},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.475292Z"},"links":{"cited_paper":"/paper/2110.03200","citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:7eba14439998327969d8e73d77cb8a2786222a68e80cc91daa29d75487ffe466","observation_id":"f5b37fe2-7e7b-4354-a6a0-ff1490d0620d","resolution":{"observed_at":"2026-08-08T14:37:13.848819Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.551346Z","title":"Least squares regression with markovian data: Fundamental limits and algorithms","venue":null,"work_id":"ff375b66-8198-4c9b-a03c-4f7409247030","year":2020},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.479993Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:52426874d361056c1e71c1b77ba55937480b78830b1edaf8ee185dad1a7e421d","observation_id":"2e5c82dc-3a0f-4f59-8ba0-419796cac167","resolution":{"observed_at":"2026-08-08T14:37:14.555911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.537499Z","title":"Nicholson, Ines Wilms, Jacob Bien, and David S","venue":null,"work_id":"52151b3b-1170-49ad-937b-00adbb3ce740","year":2020},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.484243Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:160fb3609daf42dd5b52e090eb8f238cb9ff391f5ca955da8b77bd7baffd8868","observation_id":"026ed7dc-ece0-430b-a339-9c6169e08664","resolution":{"observed_at":"2026-08-08T14:37:14.541980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.523408Z","title":"From naive mean field theory to the tap equations","venue":null,"work_id":"0c5bcdd5-d3cc-44ff-a317-943bec8c8b2b","year":2001},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.488494Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:f6e4c91cedebb5cb95115329fead57db45d0653cc046c827fb70d15097a623d5","observation_id":"2f173875-2ddf-4037-a4a2-00a3178e6e1d","resolution":{"observed_at":"2026-08-08T14:37:14.527986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.509942Z","title":"Universality laws for randomized dimension reduction, with applications","venue":null,"work_id":"7dc6a503-16dc-4cb0-92b7-670b8585621c","year":2018},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.492664Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:baf57afff4147009d361ac515843517070612bcb50fbaaa8d093fd0bc28c7657","observation_id":"dcb93acd-54f6-4d06-a310-c1bf6a3b211a","resolution":{"observed_at":"2026-08-08T14:37:14.514469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.496482Z","title":null,"venue":null,"work_id":"b5b7e926-1183-4a71-bbe1-daa2457ea0e7","year":2019},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.497179Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:6ac7bb0b0af37b353f9f8c96a18d1d99d5ad9d64f7adda1c804f1ca6197b1c07","observation_id":"e16a9352-58a6-457f-985c-7ec28e5a09f6","resolution":{"observed_at":"2026-08-08T14:37:14.500922Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.482622Z","title":"Correlated binary regression with covariates specific to each binary observation","venue":null,"work_id":"c9ba682b-24db-42f1-b3ad-965a2452e825","year":1988},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.501385Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:1d1b46b02679bb20659dae5e10fad5a774b725c2417a2d2269976531d9c41882","observation_id":"118a6ea9-e8c1-44c4-bc8c-fc469e570ae2","resolution":{"observed_at":"2026-08-08T14:37:14.487085Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.469107Z","title":"Locally dependent latent class models with covariates: an application to under-age drinking in the usa","venue":null,"work_id":"bb18f4cf-83bd-4d2b-abac-1c70a8b848ee","year":2008},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.505551Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:76524d6c7cc5348ff470c1d0f79b4b56d5d9235cb4b4b2ffe26f39d33925c6ea","observation_id":"cf824fdb-f586-4cd1-a649-1663a1c78299","resolution":{"observed_at":"2026-08-08T14:37:14.473742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.455349Z","title":"Linear models in statistics","venue":null,"work_id":"8b0296a3-9abb-46fe-8eaa-b289165c1b6a","year":2008},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.509591Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:e69765c51be97ed7023783a6aa6b6a5c06e68b67c6f90391dddedafdfc1b26f3","observation_id":"12e62e7b-ef47-4ba3-b58b-fb108c788d0e","resolution":{"observed_at":"2026-08-08T14:37:14.459972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.441491Z","title":"Tyrrell Rockafellar","venue":null,"work_id":"b8380a37-fa36-4c9f-a96c-22189e89e393","year":1970},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.513769Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:8113e32ce863a3a96e1468b0a1d808d0df225644af85ce42baf3eb6cda11a35b","observation_id":"069baf87-b0ad-4eea-b30e-cf410786cc51","resolution":{"observed_at":"2026-08-08T14:37:14.445982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.426754Z","title":"Fundamentals of Stein’s method","venue":null,"work_id":"e79362c8-71c6-4482-ba85-37af141e0b47","year":2011},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.518523Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:a04c7ce1a8a02116917dde1641eaf585833dc156169d4035040f0c3931a22599","observation_id":"f805e8f3-22ce-442f-a253-5183238243e1","resolution":{"observed_at":"2026-08-08T14:37:14.431450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.411528Z","title":"Hanson-wright inequality and sub-gaussian concentration, 2013","venue":null,"work_id":"5b98947c-b33b-4789-b52c-84772f1b005a","year":2013},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.523163Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:4863108050ecbdc26f08a2236814571b0578cdae940137e0c86c7670d92192bb","observation_id":"2f4b82c0-fc9c-4835-b1df-7ed88dfaab03","resolution":{"observed_at":"2026-08-08T14:37:14.416238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.396325Z","title":"The impact of regularization on high-dimensional logistic regression","venue":null,"work_id":"a339842c-50e8-4d6d-88d4-12c6b5ad0975","year":2019},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.527469Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:99860f1ca3b77b9f6f257e181778971b4ec8b31c90ec1440962ca683b622ccab","observation_id":"fcebb612-797e-4e90-8f8d-27fc4d3f943b","resolution":{"observed_at":"2026-08-08T14:37:14.401168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.381982Z","title":"Local dependence in random graph models: characterization, properties and statistical inference","venue":null,"work_id":"93974a50-7ba8-43d6-8913-284741344f04","year":2015},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.532021Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:6297419012be0ded546f16f7a381f873c8219e51fbf02d82626ab39161d49d9b","observation_id":"fb854ead-1a23-4ec4-b10b-62fdac500cf8","resolution":{"observed_at":"2026-08-08T14:37:14.386608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.366302Z","title":"Advanced Data Analysis from an Elementary Point of View","venue":null,"work_id":"292f4a2f-56dc-4c17-af4f-077e24b31e44","year":2019},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.536456Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:b8bf8ea7f37d22ecbc1df3c0dfbc6ff1fdc7d395b8cdce03c55c3854cf11e7e2","observation_id":"03960834-aa5a-4714-8307-19b61022ba02","resolution":{"observed_at":"2026-08-08T14:37:14.371579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.350810Z","title":"Shorten and T","venue":null,"work_id":"732a9ca8-7361-479c-8da8-de9c32c4b40b","year":2019},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.540834Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:59ca53a9e2576dc36a6644340a53dd2a9f1b9992f19bf5643623682731ca4c97","observation_id":"404aefa0-1e2b-4f88-9e83-c4f26d030acb","resolution":{"observed_at":"2026-08-08T14:37:14.355554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.336240Z","title":"Text data augmentation for deep learning","venue":null,"work_id":"042b2f38-20f8-45e4-a4d5-a1cbaab46bff","year":2021},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.545299Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:95b1032c499efbcf952bd2c8fcf53bddce8451dffcef4129bc974e938b6aa69b","observation_id":"7b0dd421-5e9c-471e-830b-5af6c179d660","resolution":{"observed_at":"2026-08-08T14:37:14.341179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1303.7291","last_updated":"2013-03-29T03:55:09Z","snapshot_observed_at":"2026-07-06T03:09:54.070461Z","submitted_at":"2013-03-29T03:55:09Z","title":"A framework to characterize performance of LASSO algorithms","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1303.7291","snapshot_observed_at":"2026-08-08T14:37:13.549753Z","title":"A framework to characterize performance of lasso algorithms","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.549753Z"},"links":{"cited_paper":"/paper/1303.7291","citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:755a5f9e30c8282cbb230f9ffa0fc6b96856e6387e456dc66bb10fe8d02a21e1","observation_id":"d5dddfc6-07ea-4ab9-9f57-e1eee70da46b","resolution":{"observed_at":"2026-08-08T14:37:13.549753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1303.7289","last_updated":"2013-03-29T03:44:53Z","snapshot_observed_at":"2026-07-06T03:09:54.070461Z","submitted_at":"2013-03-29T03:44:53Z","title":"Upper-bounding $\\ell_1$-optimization weak thresholds","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1303.7289","snapshot_observed_at":"2026-08-08T14:37:13.554923Z","title":"Upper-bounding _1 -optimization weak thresholds","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.554923Z"},"links":{"cited_paper":"/paper/1303.7289","citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:66d4536e073f24605ea29f0e91896b75dc692a0bf13e8a4f640ad25e9787937e","observation_id":"34a4cd53-7eea-49ec-89fe-6ba30b94328d","resolution":{"observed_at":"2026-08-08T14:37:13.554923Z","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":"2026-08-08T14:37:14.321942Z","title":"A modern maximum-likelihood theory for high-dimensional logistic regression","venue":null,"work_id":"05ada476-e1b5-4d48-8e45-548a83f919ff","year":2019},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.559583Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:a717788364c670507b1fe9c8de3ce5608dde784152e4b5a7c8a9a301538d89da","observation_id":"4ca2f5a0-9cd6-4555-94e0-5d97d46349df","resolution":{"observed_at":"2026-08-08T14:37:14.326651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.308072Z","title":"The impact of multi-optimizers and data augmentation on tensorflow convolutional neural network performance","venue":null,"work_id":"fdf07aa9-7ac2-4cd6-97cf-bfe2a21dc613","year":2018},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.564499Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:683b4a3687ebef898f032f48c96413ab45a4a5ab064978a4efedad67e05dac24","observation_id":"51c8b5e3-9561-41d6-a3b4-250a7d97e57b","resolution":{"observed_at":"2026-08-08T14:37:14.312647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.293702Z","title":"Recovering structured signals in high dimensions via non-smooth convex optimization: Precise performance analysis","venue":null,"work_id":"5663a082-9156-4bd6-bbea-873d79bb51c0","year":2016},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.568968Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:0e90f30f1585ee509c7f7ac58f3cc02b33e9742c51364c94b3d70bae6d7a1461","observation_id":"c79cd2aa-6f56-4fa8-8541-3387defbe0c1","resolution":{"observed_at":"2026-08-08T14:37:14.298447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1408.4837","last_updated":"2015-03-03T09:18:18Z","snapshot_observed_at":"2026-07-06T03:52:14.820700Z","submitted_at":"2014-08-20T23:24:09Z","title":"The Gaussian min-max theorem in the Presence of Convexity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1408.4837","snapshot_observed_at":"2026-08-08T14:37:13.573836Z","title":"The G aussian min-max theorem in the presence of convexity","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.573836Z"},"links":{"cited_paper":"/paper/1408.4837","citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:d1cc439420322f5d7a058483eb6fe8113977334b7103b5fbe2e11394413aae65","observation_id":"85f64c7a-560d-4e42-b223-3feecd69343b","resolution":{"observed_at":"2026-08-08T14:37:13.573836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.578609Z","title":"Regularized linear regression: A precise analysis of the estimation error","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.578609Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:746b7344608511db8eb3cb7a54068bacc36e7847de6aa820eb1d1cdd74137e5e","observation_id":"8cd9d62a-53e2-49da-aadb-014274d996f4","resolution":{"observed_at":"2026-08-08T14:37:13.578609Z","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":"2026-08-08T14:37:14.270046Z","title":"Precise error analysis of regularized m -estimators in high dimensions","venue":null,"work_id":"dec8bc42-87b6-452d-9dd1-3e1e87da8748","year":2018},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.583188Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:95baf51b22b89b3781c1ee93ca73f78b89d665bea35ddd16fd5a99a1c32173da","observation_id":"ecfea4fa-28a7-4fdb-9328-292bacdfa85b","resolution":{"observed_at":"2026-08-08T14:37:14.275048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.255334Z","title":"Analysis of financial time series","venue":null,"work_id":"24dcccc4-e094-4eb7-b567-998487f13b8d","year":2005},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.587597Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:0dc601bdffa76a30de7c873607fcfdc0d13074e484807af0385e59577cc0b8d8","observation_id":"5ef4f1f9-6b62-4649-83f4-0ab239be924d","resolution":{"observed_at":"2026-08-08T14:37:14.260107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.240748Z","title":"Some mixing properties of time series models","venue":null,"work_id":"6e2c2383-9ff9-4ee9-a959-626c327d0506","year":1985},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.592245Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:3c106d062c33bc7c15f9c823185f6c8b4a101f8260edb28461fce34f7673a70e","observation_id":"b777d44f-1375-44e2-83d7-1914b46b554f","resolution":{"observed_at":"2026-08-08T14:37:14.245367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.596660Z","title":"High-Dimensional Probability: An Introduction with Applications in Data Science","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.596660Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:3a3124d62d45b11ce4f19bc2daaed1113fbc471a22a782ba051fe4fc92935d98","observation_id":"00f8eca7-cf7a-4155-899f-d470eecb4679","resolution":{"observed_at":"2026-08-08T14:37:13.596660Z","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":"2026-08-08T14:37:14.217026Z","title":"An overview on data augmentation for machine learning","venue":null,"work_id":"72f0d88e-f7dd-49f2-8d26-cffb26060a4a","year":2024},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.600961Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:7ad7cc001d7487cd26c5789fc315050e7c3f5ec5a5d4f99fdaf540c51ee89d20","observation_id":"e54eca60-3ba1-4a11-8d47-167f4bd4fa7d","resolution":{"observed_at":"2026-08-08T14:37:14.221660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.201773Z","title":"Multivariate geostatistics: an introduction with applications","venue":null,"work_id":"d1472d96-7c8c-48f0-a321-ba5e7f827a17","year":2003},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.605599Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:99f59cb6a6477cf10779eba8d3492e50fbb1aa90d2377a006bd2c9cd89538a91","observation_id":"c0b4453e-a4e2-4792-bf89-f88fdd34a537","resolution":{"observed_at":"2026-08-08T14:37:14.206890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.185337Z","title":"Universality of approximate message passing algorithms and tensor networks","venue":null,"work_id":"4c64ad9e-93a8-4bf6-8789-c3b29160d89e","year":2024},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.610520Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:eefdc4c6fca033e1d9c166ccc1cc3d9526224bf5b79c4725f932a713973f0cf9","observation_id":"f0bc6e26-c88e-46de-a0a7-eabf1839d4dc","resolution":{"observed_at":"2026-08-08T14:37:14.190045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.171227Z","title":"Regularized estimation in high dimensional time series under mixing conditions","venue":null,"work_id":"120cfcf6-244f-4bd7-bea5-3191023eb92a","year":2016},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.614988Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:d82c45c3f96247a2f772b30319ec8d71efe53c32755c2f1ab4ae898f656e9a81","observation_id":"1a07c62d-bb0d-4ffb-9359-f270abf89805","resolution":{"observed_at":"2026-08-08T14:37:14.175912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.156662Z","title":"Lasso guarantees for -mixing heavy-tailed time series","venue":null,"work_id":"7cc3f452-ba7f-4cf6-8e87-f245a93ff419","year":2020},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.619572Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:0d33ec5cbc923a839db7557d534a28889cdf03ecfdbff0ba24760847d5da785c","observation_id":"273b0a90-b22c-47fe-a8fc-25640a770a76","resolution":{"observed_at":"2026-08-08T14:37:14.161677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.141842Z","title":"On the use of repeated measurements in regression analysis with dichotomous responses","venue":null,"work_id":"5d2598e7-3350-426c-ad32-1d3d8a89d096","year":1979},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.623815Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:36e2737c3cd81bf77e544ddc9f1aa68c6c9a63be8634388a5bef3e34e013e439","observation_id":"f9d0593d-da00-4169-87b4-018aeea08c40","resolution":{"observed_at":"2026-08-08T14:37:14.146713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.127453Z","title":"Generative adversarial symmetry discovery","venue":null,"work_id":"44152ba3-5f24-4983-aa9a-9669cb8ae39b","year":2023},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.628345Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:64090b5e8b1845c004bb523a14998298cc323b69edbf00b5b8d86a57cbbdc32d","observation_id":"ee68baaa-9779-4659-9bd2-7b6221b7d965","resolution":{"observed_at":"2026-08-08T14:37:14.132139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:13.632681Z","title":"Rates of convergence for empirical processes of stationary mixing sequences","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.632681Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:acc64a63f336153b67e13d84410b00dba21fa21d63a059a5bf573efbdd5ce929","observation_id":"a6573a08-8e49-43ee-b362-076dcbcdee36","resolution":{"observed_at":"2026-08-08T14:37:13.632681Z","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":"2026-08-08T14:37:14.103912Z","title":"Learning local dependence in ordered data","venue":null,"work_id":"cbbc8407-24d6-407b-a6db-b198ccefae20","year":2017},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.637270Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:249eb908037829990c2ebba4a58b6d48819a012330b25474f4b93e25bfa77020","observation_id":"ce2e537c-6eb5-4a4d-a1f3-974b9bfcb576","resolution":{"observed_at":"2026-08-08T14:37:14.108760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.089453Z","title":"Generalized estimating equation models for correlated data: A review with applications","venue":null,"work_id":"922c62dc-2e07-4d15-806b-e906505137e9","year":2001},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.641999Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:ef84eb6040d228b69079f7dce5e875a883bd57c24b692abf4d72f1ea4db47ee6","observation_id":"504e73dc-042e-412c-89fb-47724494c32e","resolution":{"observed_at":"2026-08-08T14:37:14.093970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:37:14.074617Z","title":"The generalization performance of erm algorithm with strongly mixing observations","venue":null,"work_id":"756dd066-7678-4f3c-9463-d7d0bb9d7577","year":2009},"citing_paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation","version":4},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-08T14:37:13.646442Z"},"links":{"citing_paper":"/paper/2502.15752"},"observation_digest":"sha256:2710af449558aae35fd31d39f683d3ee7e6919675cc87c79acaa4b9bd05ff8d3","observation_id":"a3109f0c-d0eb-40cd-bd9f-ea7ed1f8d3b0","resolution":{"observed_at":"2026-08-08T14:37:14.079320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.15752","last_updated":"2026-07-07T03:51:47Z","latest_version":4,"primary_category":"math.ST","snapshot_observed_at":"2026-08-08T14:26:15.859427Z","submitted_at":"2025-02-10T18:04:53Z","title":"Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation"},"reference_resolution":{"displayed":92,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":27,"verified_exact":4,"verified_fuzzy":61},"total_outbound_references":92},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 92 of 92 outbound references and 0 inbound Pith citation observations for arXiv:2502.15752."}