{"as_of":"2026-08-17T17:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5df78f7ced6bac57bc51d33a248e49a1d20faba8fd07fe417a98786b81f79e7e","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T04:23:00.476134Z","state":"measured"},{"denominator":50,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":50,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T04:23:00.476134Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-12T04:23:00.508923Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"cited_work":{"arxiv_id":"2412.01476","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.01476","snapshot_observed_at":"2026-08-12T04:23:00.508923Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","venue":"cs.LG","work_id":"b40096c1-c3cf-4124-aff8-edf1c750471b","year":2024},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.476134Z"},"links":{"cited_paper":"/paper/2412.01476","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:e7b901d36a184bfdbe0d7cd46da837900a66f4502004e275ed0e14c3df89b91f","observation_id":"c52ddac5-a0f2-4074-b3da-e1c70aa11030","resolution":{"observed_at":"2026-08-12T04:23:00.515259Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.01476/citation-record","integrity":"/paper/2412.01476/integrity","json":"/paper/2412.01476/citation-record.json","paper":"/paper/2412.01476"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:01.100504Z","title":"Adaptive consistency regular- ization for semi-supervised transfer learning","venue":null,"work_id":"7a05133d-bf38-4577-be8f-4d6d8c8877b1","year":2021},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.280211Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:477dde2f64313caf8a76e08158560723677be349d729505a2847592d5bfe9584","observation_id":"05f90d2b-ea73-4b42-92ae-9056124c5904","resolution":{"observed_at":"2026-08-12T04:23:01.104581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:01.089653Z","title":"The effects of adding noise during backprop- agation training on a generalization performance","venue":null,"work_id":"2cff8367-4e17-4a3f-b53b-d51665745cb7","year":1996},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.285027Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:9bfa15b8cffb886609995b5d779e7ad3dff8f50db0fdf12a163227311a5d25ca","observation_id":"a1e3fe7b-945c-4a91-8acf-07d43eba513e","resolution":{"observed_at":"2026-08-12T04:23:01.093650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:01.073337Z","title":"A closer look at memorization in deep networks","venue":null,"work_id":"a33436ee-124e-4a02-b240-9e11e9f8bcbd","year":2017},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.288948Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:2652f30c59aa3ab47e730df0ef2b9872db52c68f83d357a7e314e39077a7d6a1","observation_id":"957afca1-3380-4f33-81c8-79901e6d0415","resolution":{"observed_at":"2026-08-12T04:23:01.079571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:01.058228Z","title":"Inte- grating structured biological data by kernel maximum mean discrepancy","venue":null,"work_id":"16b06c89-c14f-410f-9cce-a105f5b17ff9","year":2006},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.292852Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:9c25155c2cfa9ccf0bc10c976fac0e27ef15be06346dae223de0b18f4689bce1","observation_id":"2610edfe-987e-4339-8cce-45e000e0f689","resolution":{"observed_at":"2026-08-12T04:23:01.062110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:01.040553Z","title":"Understanding and utilizing deep neural networks trained with noisy labels","venue":null,"work_id":"78715cee-3d9b-4876-8cf7-09ed05424654","year":2019},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.296365Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:475e0030bf4932090d787fe76ba3e7a902bd30b9ddcba6202c6ce15dfac55874","observation_id":"28b2687f-8fb5-4411-acf5-cf07bdcedfab","resolution":{"observed_at":"2026-08-12T04:23:01.046576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:01.027305Z","title":"Sample prior guided robust model learning to suppress noisy labels","venue":null,"work_id":"eaad4c90-22fe-4f6a-a030-9e9afdc2a009","year":2023},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.300704Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:c82c8f66910d6ae9202c598de3eeee119ced72c4f4e80af8b87147a1252755fd","observation_id":"fc5bc05a-92ec-46af-b716-086176d1634a","resolution":{"observed_at":"2026-08-12T04:23:01.031387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11556","last_updated":"2019-09-25T15:35:03Z","snapshot_observed_at":"2026-08-13T06:47:52.053569Z","submitted_at":"2019-09-25T15:35:03Z","title":"Reducing Transformer Depth on Demand with Structured Dropout","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.11556","snapshot_observed_at":"2026-08-12T04:23:00.304717Z","title":"Reducing transformer depth on demand with structured dropout","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.304717Z"},"links":{"cited_paper":"/paper/1909.11556","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:76680585cbf3adfceb7781801a416cbd3be6920dadc99bf0dcbc604cda8530f0","observation_id":"4dc211d0-2bc9-4ebe-b8cc-9511b131ecb6","resolution":{"observed_at":"2026-08-12T04:23:00.304717Z","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":"2026-08-12T04:23:01.012939Z","title":"Unsupervised domain adaptation by backpropagation","venue":null,"work_id":"2d4c34fc-92bb-4349-b852-e026a859bccb","year":2015},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.309210Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:139189815d749e85fbfef1b086e7a49ed22f0a17c21de68ab525622d99b4b1a4","observation_id":"a1c0aaf1-01fe-456b-ade4-2b4cf9d9214a","resolution":{"observed_at":"2026-08-12T04:23:01.017507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:01.000362Z","title":"Regu- larization theory and neural networks architectures","venue":null,"work_id":"f39bd07d-b64e-4a67-9c8c-b5e8665c42be","year":1995},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.312704Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:dead486480441a2af0e562a24ac75f30ba949ea0b47a0cc65727949678b12e06","observation_id":"3acbaa6d-29a7-40a2-af38-4e84037f43e1","resolution":{"observed_at":"2026-08-12T04:23:01.004941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.987612Z","title":"Connecting the dots with landmarks: Discriminatively learning domain- invariant features for unsupervised domain adaptation","venue":null,"work_id":"a87a8a6b-731a-4acb-ac90-277e7ec089ae","year":null},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.316122Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:281a492bb79c00a39a450f4019b703eb698371cd64089f999165494123e0e197","observation_id":"e807949b-a6b1-4314-97c1-42424faddd9a","resolution":{"observed_at":"2026-08-12T04:23:00.992170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.320169Z","title":"Generative adversarial nets","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.320169Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:5855e5851926cdbf078133dc522d156c92ad2409a832e71ce4965522dee9a938","observation_id":"8b6be91a-0084-414e-ac36-4457a82ef966","resolution":{"observed_at":"2026-08-12T04:23:00.320169Z","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":"2026-08-12T04:23:00.966998Z","title":"Natural adversarial examples","venue":null,"work_id":"d8d6e8c9-8e81-4518-87b0-981b122eb505","year":2021},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.323839Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:092f8f7150e5bfd45a71a0ecd416d478e366f9054ce7b1f72ef10f57c2570941","observation_id":"56fe05d4-dbff-470e-900c-94d2f8b549c8","resolution":{"observed_at":"2026-08-12T04:23:00.971641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.03852","last_updated":"2020-11-12T10:35:59Z","snapshot_observed_at":"2026-08-14T19:05:23.443036Z","submitted_at":"2018-06-11T08:10:18Z","title":"Data augmentation instead of explicit regularization","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.03852","snapshot_observed_at":"2026-08-12T04:23:00.327607Z","title":"Data augmen- tation instead of explicit regularization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.327607Z"},"links":{"cited_paper":"/paper/1806.03852","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:21a25229432cc6e25ab1e199d3cc106542a05c78deb3de3e119aeec39371e209","observation_id":"759b4bb3-2ca6-4aa1-aad2-52c8ba07fa3f","resolution":{"observed_at":"2026-08-12T04:23:00.327607Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1612.02649","last_updated":"2016-12-08T14:11:10Z","snapshot_observed_at":"2026-08-14T21:26:29.466258Z","submitted_at":"2016-12-08T14:11:10Z","title":"FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.02649","snapshot_observed_at":"2026-08-12T04:23:00.332216Z","title":"Fcns in the wild: Pixel-level adversarial and constraint-based adaptation","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.332216Z"},"links":{"cited_paper":"/paper/1612.02649","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:2884c9e37b89f5f01cfe151f0bedfa2e933457479be3fffd3b04440d24f53430","observation_id":"b334aefc-0860-4ea8-b6e8-bf2e8a4b9097","resolution":{"observed_at":"2026-08-12T04:23:00.332216Z","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":"2026-08-12T04:23:00.953570Z","title":"Searching for mo- bilenetv3","venue":null,"work_id":"9e6277f3-4e8c-4b1a-985f-020ed0ab0a5c","year":2019},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.337598Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:92a82575775713ca192c4df0cfb3a7402b2cce0ee87d6285506d616d63474bfb","observation_id":"4ce8cf5b-9496-46f9-b2b6-1091c2fc05e9","resolution":{"observed_at":"2026-08-12T04:23:00.957489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.942208Z","title":"Deep networks with stochastic depth","venue":null,"work_id":"a480d52b-f655-4e24-8095-f4602d5444a8","year":2016},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.341484Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:489b12eb2b834c8ea57143884a166a6e9faa52c957c76c651bd9fed8c0da62d2","observation_id":"3ccd0530-4d6b-452e-95a4-ea783d5e5650","resolution":{"observed_at":"2026-08-12T04:23:00.945903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.930042Z","title":"Correcting sample selection bias by unlabeled data","venue":null,"work_id":"d74d41fc-f452-4904-a09f-5d06226b8fda","year":2006},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.345373Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:55abdc30ba30a232fb31ad1b802eff97e82334ed496987033c4369d461806bf6","observation_id":"e798f247-24fe-467f-a432-605f98f2abed","resolution":{"observed_at":"2026-08-12T04:23:00.934003Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1502.03167","last_updated":"2015-03-02T20:44:12Z","snapshot_observed_at":"2026-08-12T21:01:12.961874Z","submitted_at":"2015-02-11T01:44:18Z","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.03167","snapshot_observed_at":"2026-08-12T04:23:00.349426Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.349426Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:e24e163acf0a1118af35509d05b16f73f899c303644c99be0e2d09287d246ac3","observation_id":"aa35053a-7732-436d-8019-e676551c6d13","resolution":{"observed_at":"2026-08-12T04:23:00.349426Z","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":"2026-08-12T04:23:00.919052Z","title":"Image-to-image translation with conditional adversarial net- works","venue":null,"work_id":"14fb6979-f96b-430c-9e60-3ae38f544493","year":2017},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.354348Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:4b8865c49982870df2c8d4c670fcf1c93c592052c1ee9815353cbf833c68c7f4","observation_id":"dd3e8514-a778-431c-9e91-df727ce0b973","resolution":{"observed_at":"2026-08-12T04:23:00.923099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.908297Z","title":"Adversar- ial adaptation of synthetic or stale data","venue":null,"work_id":"9e076d59-f269-4810-9d8d-016e5d56968c","year":2017},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.358616Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:548e8a2e4d2f06984bcacac7868aa452c4c3428b0a9e2fa1be57d37fa79ac043","observation_id":"74cd1f3d-0a90-4b13-86ab-a90b6ee93c81","resolution":{"observed_at":"2026-08-12T04:23:00.911925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.363300Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.363300Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:0150aeb6006a396f44df5c2cc8543cdebdf4c7f531bfd5967221dbe7dcc58430","observation_id":"483f4431-b4b9-4938-b882-3af2b6b0d059","resolution":{"observed_at":"2026-08-12T04:23:00.363300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10686","last_updated":"2017-10-29T20:27:51Z","snapshot_observed_at":"2026-08-14T20:19:11.294774Z","submitted_at":"2017-10-29T20:27:51Z","title":"Regularization for Deep Learning: A Taxonomy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10686","snapshot_observed_at":"2026-08-12T04:23:00.366800Z","title":"Reg- ularization for deep learning: A taxonomy","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.366800Z"},"links":{"cited_paper":"/paper/1710.10686","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:5f2144f0241af1d53f0aa15dcf4470a1d6227f9dedab1ef922fff13e9ef16e9c","observation_id":"fb583f0b-ee01-41b7-91ae-904b92af501d","resolution":{"observed_at":"2026-08-12T04:23:00.366800Z","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":"2026-08-12T04:23:00.892910Z","title":"Generalization and network design strategies","venue":null,"work_id":"fbd667f8-526f-4eb3-803c-0d2031c8d4ef","year":1989},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.370213Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:bc8228521b4d0a5ebf590f75acc34740eb0605fc24f1a0d9781607d87213993d","observation_id":"ff901887-23be-4ede-a616-c5a18273e135","resolution":{"observed_at":"2026-08-12T04:23:00.896584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.883199Z","title":"Layer normalization","venue":null,"work_id":"101ca642-2672-496e-bd39-b76adce01d8d","year":2016},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.372963Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:fd20dd917cddb7edf223d55136ef86c98c11ac4f6cdfd4cd5f8b7305f44e994f","observation_id":"42d8b9bc-9f67-45ef-aedb-c9318a36b626","resolution":{"observed_at":"2026-08-12T04:23:00.886198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.07394","last_updated":"2020-02-18T06:20:06Z","snapshot_observed_at":"2026-08-17T14:10:48.435331Z","submitted_at":"2020-02-18T06:20:06Z","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.07394","snapshot_observed_at":"2026-08-12T04:23:00.376508Z","title":"Dividemix: Learning with noisy labels as semi-supervised learning","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.376508Z"},"links":{"cited_paper":"/paper/2002.07394","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:06e61b683fe0282772062194132e8936a79dacf70e1178aa34f6b0881be399e9","observation_id":"e55022b1-f5b4-4317-b8b4-430940ecda82","resolution":{"observed_at":"2026-08-12T04:23:00.376508Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.02862","last_updated":"2017-08-09T14:59:30Z","snapshot_observed_at":"2026-08-14T20:42:20.095725Z","submitted_at":"2017-08-09T14:59:30Z","title":"WebVision Database: Visual Learning and Understanding from Web Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.02862","snapshot_observed_at":"2026-08-12T04:23:00.380243Z","title":"Webvision database: Visual learning and under- standing from web data","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.380243Z"},"links":{"cited_paper":"/paper/1708.02862","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:704065151938d8ae410104eaeb08a8c830874288de6785f304aa33aeec9d4c12","observation_id":"a87d2b2b-65c7-449f-bc7a-93c1dc5b31d5","resolution":{"observed_at":"2026-08-12T04:23:00.380243Z","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":"2026-08-12T04:23:00.384091Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.384091Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:9d9233f1497cb6506b98baf2e3377ec23d2f1db5899ca7d459c6777da6f34038","observation_id":"ce56fa87-ff0d-4bd3-9e13-8937cb0c1dd2","resolution":{"observed_at":"2026-08-12T04:23:00.384091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.01009","last_updated":"2017-08-03T05:53:53Z","snapshot_observed_at":"2026-08-14T20:43:30.970495Z","submitted_at":"2017-08-03T05:53:53Z","title":"Revisiting Activation Regularization for Language RNNs","version":1},"cited_work":{"arxiv_id":"1708.01009","doi":null,"metadata_source":"pith","pith_arxiv_id":"1708.01009","snapshot_observed_at":"2026-08-12T04:23:00.610521Z","title":"Revisiting Activation Regularization for Language RNNs","venue":"cs.CL","work_id":"4ca0d117-fb80-498c-8878-d9424444b0bb","year":2017},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.387691Z"},"links":{"cited_paper":"/paper/1708.01009","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:9aec8dc7129fcb4c9d13b6cee952a97ef872de6ee9ba23b1a928cebcc83aa7bd","observation_id":"dbc631fb-dfc2-4b7a-9b54-d82b71676818","resolution":{"observed_at":"2026-08-12T04:23:00.615082Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.391354Z","title":"Which training methods for gans do actually converge? In International conference on machine learning, pages 3481–","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.391354Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:952bdf3b557ea6e3a3f006e8d7a23171df3f6f9a2c144a50b291a5a7170f05c5","observation_id":"25d9e110-569a-447a-9466-9223eb26ae47","resolution":{"observed_at":"2026-08-12T04:23:00.391354Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.02163","last_updated":"2017-05-12T23:52:12Z","snapshot_observed_at":"2026-08-14T21:31:35.579054Z","submitted_at":"2016-11-07T16:42:09Z","title":"Unrolled Generative Adversarial Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.02163","snapshot_observed_at":"2026-08-12T04:23:00.395175Z","title":"Unrolled generative adversarial networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.395175Z"},"links":{"cited_paper":"/paper/1611.02163","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:21452f711c368811b944192088bb9a6234ad00feaf0f1b95f564887c700bee99","observation_id":"1d4e33f3-a346-4d09-93af-3c5123f2201c","resolution":{"observed_at":"2026-08-12T04:23:00.395175Z","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":"2026-08-12T04:23:00.398874Z","title":"When does label smoothing help? Advances in neural in- formation processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.398874Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:4d10b6505a7e9c43919345c1e1bb2245c6bbbd21040e798578ad0f046731ffe0","observation_id":"4b365c0d-cea7-410c-ba60-b9e0089097c3","resolution":{"observed_at":"2026-08-12T04:23:00.398874Z","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":"2026-08-12T04:23:00.402587Z","title":"Automated flower classification over a large number of classes","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.402587Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:d2e6b6f15f463c5c6302a211735814a743499396806e1136b9e4777d730795fc","observation_id":"cb284c42-3bd7-41a4-95d0-1c00bd7300f3","resolution":{"observed_at":"2026-08-12T04:23:00.402587Z","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":"2026-08-12T04:23:00.820073Z","title":"Wasser- stein distance guided representation learning for domain adap- tation","venue":null,"work_id":"7318fed0-17b4-4d69-a229-9079580fdd8d","year":2018},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.406360Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:a32f59aa85efc62663be7d6b06aa51477bf3407da7c9c933ae3f584171dc7426","observation_id":"b28129e7-5b0a-48e6-96ca-b552735a904a","resolution":{"observed_at":"2026-08-12T04:23:00.823806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.809634Z","title":"Domain adaptation: challenges, methods, datasets, and applications","venue":null,"work_id":"d46aea95-0b12-4c22-9325-f8439c7162a2","year":2023},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.409643Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:68142a3adf92d1eda0acea1c91ea489dc1e5cc6ef2d7753f31e17d1df2b91ae1","observation_id":"ae0ecfdb-55f9-4870-8fad-f6930c04b1be","resolution":{"observed_at":"2026-08-12T04:23:00.812613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.12176","last_updated":"2021-01-28T18:32:14Z","snapshot_observed_at":"2026-08-16T18:49:16.822507Z","submitted_at":"2021-01-28T18:32:14Z","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.12176","snapshot_observed_at":"2026-08-12T04:23:00.414541Z","title":"On the origin of implicit regularization in stochastic gradient descent","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.414541Z"},"links":{"cited_paper":"/paper/2101.12176","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:3397e257418bb1621f501d2b70f1e49c75a62e21564f0aa77c92c2d54f7ff278","observation_id":"e82c2006-771c-4225-873b-0e03eddb9ee9","resolution":{"observed_at":"2026-08-12T04:23:00.414541Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.08059","last_updated":"2020-09-08T06:23:48Z","snapshot_observed_at":"2026-08-15T17:03:56.929116Z","submitted_at":"2019-11-19T02:51:15Z","title":"How does Early Stopping Help Generalization against Label Noise?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.08059","snapshot_observed_at":"2026-08-12T04:23:00.418997Z","title":"How does early stopping help generalization against label noise? arXiv preprint arXiv:1911.08059, 2019","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.418997Z"},"links":{"cited_paper":"/paper/1911.08059","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:53a2340ec105960c6b2c6702dcefbcb466453f49bdd67dd98b105fed8fd898e8","observation_id":"4e88e56a-21e4-461e-bc3a-07d4eff22f76","resolution":{"observed_at":"2026-08-12T04:23:00.418997Z","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":"2026-08-12T04:23:00.800540Z","title":"Dropout: A simple way to prevent neural networks from overfitting","venue":null,"work_id":"f6fe3e42-3f48-48d6-aa33-67489ec6a7c4","year":1929},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.423643Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:57c0eabcf7873978eedde4067849fcebedc255906eb145f87a067b8d872ffe0f","observation_id":"5d4d2119-f3c5-456a-ae05-adf7a278d7dc","resolution":{"observed_at":"2026-08-12T04:23:00.803561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.788827Z","title":"Rethinking the inception ar- chitecture for computer vision","venue":null,"work_id":"fe1b22c8-fe10-4416-9dc2-2f2a31b8eed1","year":2016},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.428296Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:c6ac767d0a8335830af37b9ad996dba29ec2b31b7e63b9aea5cf0b2a93dbdeba","observation_id":"b151c7b4-d318-4317-a2ec-77d711cf3825","resolution":{"observed_at":"2026-08-12T04:23:00.793751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07030","last_updated":"2024-03-18T02:45:04Z","snapshot_observed_at":"2026-08-16T14:11:08.394966Z","submitted_at":"2024-03-11T03:34:14Z","title":"AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07030","snapshot_observed_at":"2026-08-12T04:23:00.433248Z","title":"Aug-kd: Anchor-based mixup generation for out-of-domain knowledge distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.433248Z"},"links":{"cited_paper":"/paper/2403.07030","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:78b78e48ee0d05aabca93f8bb82dcb1fbb3e13917e735e26a86681372b37e71c","observation_id":"c4e08df1-17d8-403b-ac49-0a43463b86d2","resolution":{"observed_at":"2026-08-12T04:23:00.433248Z","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":"2026-08-12T04:23:00.775453Z","title":"A comprehensive survey on regularization strategies in machine learning","venue":null,"work_id":"3e38e409-378d-4c83-8163-ab37cd5b0921","year":2022},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.437894Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:50f047859209f3d5ddef79d0634199a5566a37b4a3a9ae567678a92c96eeadf2","observation_id":"24f71351-e395-4e57-bdc3-d8432f4b1a72","resolution":{"observed_at":"2026-08-12T04:23:00.779952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.760623Z","title":"Efficient object localization using con- volutional networks","venue":null,"work_id":"d1bd9bc8-42fb-4132-aebf-87182fb96df1","year":null},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.442360Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:1c2db776a263eb7841cd93c5f946abc309a058a592669fafd4d54b7f3ffc4f83","observation_id":"60fda121-4bce-4088-a08e-3206d798a9fa","resolution":{"observed_at":"2026-08-12T04:23:00.766244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.3474","last_updated":"2014-12-10T21:20:54Z","snapshot_observed_at":"2026-08-14T23:08:06.157493Z","submitted_at":"2014-12-10T21:20:54Z","title":"Deep Domain Confusion: Maximizing for Domain Invariance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.3474","snapshot_observed_at":"2026-08-12T04:23:00.446450Z","title":"Deep domain confusion: Maximizing for domain invariance","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.446450Z"},"links":{"cited_paper":"/paper/1412.3474","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:4e39fd8d58a3d4e52bab68db450cd936391dcb1e4cb89f14968f62623dad3f38","observation_id":"e08278c6-934e-47c2-861a-3115b1205b91","resolution":{"observed_at":"2026-08-12T04:23:00.446450Z","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":"2026-08-12T04:23:00.451292Z","title":"Adversarial discriminative domain adaptation","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.451292Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:420c72d9299406b349f67e169dbf35f5a27bd5d5046a535a66297fe581f4c658","observation_id":"c4702bd8-9440-4310-b68a-77a38739f325","resolution":{"observed_at":"2026-08-12T04:23:00.451292Z","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":"2026-08-12T04:23:00.741667Z","title":"On the uniform convergence of relative frequencies of events to their prob- abilities","venue":null,"work_id":"e05d9db3-5f6a-43b3-9c93-d041fbe38683","year":2015},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.455251Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:13e61fb07fb94327c28d40a030fa250dc6464fa25ef5de0299b40491d14ae2ab","observation_id":"3ea03c33-d6a4-4078-a5f0-cf65983dcf3e","resolution":{"observed_at":"2026-08-12T04:23:00.745759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.459089Z","title":"Bayesian learning via stochas- tic gradient langevin dynamics","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.459089Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:4bc5b086713de2fcfd5eaae96b2cccf43fb162087c9b015e100895f9087d3829","observation_id":"e5ba0ba5-8739-415b-b7d4-d1965eacfd3c","resolution":{"observed_at":"2026-08-12T04:23:00.459089Z","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":"2026-08-12T04:23:00.722132Z","title":"Group normalization","venue":null,"work_id":"beb8e805-dff7-4c66-a6b2-272cce064b6f","year":2018},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.464267Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:6da71b0c7b2bd1a365f6fbb78534b2730f4e4afb37239748bf32b609afee54e4","observation_id":"e61b96ea-70ed-4b3d-a72d-b808d38a94e5","resolution":{"observed_at":"2026-08-12T04:23:00.725770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.02401","last_updated":"2019-02-06T21:17:57Z","snapshot_observed_at":"2026-08-14T17:19:59.875632Z","submitted_at":"2019-02-06T21:17:57Z","title":"Adversarial Domain Adaptation for Stance Detection","version":1},"cited_work":{"arxiv_id":"1902.02401","doi":null,"metadata_source":"pith","pith_arxiv_id":"1902.02401","snapshot_observed_at":"2026-08-12T04:23:00.529312Z","title":"Adversarial Domain Adaptation for Stance Detection","venue":"cs.LG","work_id":"c750d817-06aa-4dba-af16-9b0061505aa6","year":2019},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.469252Z"},"links":{"cited_paper":"/paper/1902.02401","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:1a64870ee931839af6c104303ed8b8fef9abad1226ae94d6502bcd1895b6415a","observation_id":"6c8e1797-dd61-45e4-9e25-ba422eb6ab96","resolution":{"observed_at":"2026-08-12T04:23:00.534572Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:23:00.710239Z","title":"Understanding deep learning (still) re- quires rethinking generalization","venue":null,"work_id":"e0d75700-7f4a-4cb3-af4a-8d68dde96c5a","year":2021},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.472964Z"},"links":{"citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:36bce2e10cffbf66cd236d1a57c93cb661f9bf035272b3007f91fda8a6e43465","observation_id":"45ee6134-71bf-4440-8753-d2d730ebbada","resolution":{"observed_at":"2026-08-12T04:23:00.714349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"cited_work":{"arxiv_id":"2412.01476","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.01476","snapshot_observed_at":"2026-08-12T04:23:00.508923Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","venue":"cs.LG","work_id":"b40096c1-c3cf-4124-aff8-edf1c750471b","year":2024},"citing_paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T04:23:00.476134Z"},"links":{"cited_paper":"/paper/2412.01476","citing_paper":"/paper/2412.01476"},"observation_digest":"sha256:e7b901d36a184bfdbe0d7cd46da837900a66f4502004e275ed0e14c3df89b91f","observation_id":"c52ddac5-a0f2-4074-b3da-e1c70aa11030","resolution":{"observed_at":"2026-08-12T04:23:00.515259Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.01476","last_updated":"2025-01-24T14:16:46Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T08:26:22.755778Z","submitted_at":"2024-12-02T13:21:31Z","title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":20,"verified_exact":2,"verified_fuzzy":26},"total_outbound_references":49},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 1 inbound Pith citation observation for arXiv:2412.01476."}