{"as_of":"2026-08-20T08:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d5934dea65b9f8dd395bdc8507c7fe14a4cb929952b21057c083b14a02af365c","coverage":[{"denominator":18,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":18,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:59:14.621322Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2505.11347/citation-record","integrity":"/paper/2505.11347/integrity","json":"/paper/2505.11347/citation-record.json","paper":"/paper/2505.11347"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1910.01663","last_updated":"2019-10-27T17:53:30Z","snapshot_observed_at":"2026-08-17T18:02:49.006775Z","submitted_at":"2019-10-03T18:04:17Z","title":"Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01663","snapshot_observed_at":"2026-08-15T20:59:14.522120Z","title":"Toward large kernel models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.522120Z"},"links":{"cited_paper":"/paper/1910.01663","citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:998e9f7e2ba3b63b83c6155554b3aa922731d19fc91e7f44c11ec8e51b035ac7","observation_id":"54b713fb-c200-40ce-98c4-df117f642e1b","resolution":{"observed_at":"2026-08-15T20:59:14.522120Z","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":"2026-08-15T20:59:15.029056Z","title":"Smoothing noisy data with spline functions: estimating the cor- rect degree of smoothing by the method of generalized cross-validation,","venue":null,"work_id":"c2e99ec8-17ae-497c-a01a-58cb3eeba724","year":1978},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.541623Z"},"links":{"citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:7dd8fa93c06dd55b822c714e4cdba86a0cc98c74025efa5ff99662e6212cbed7","observation_id":"109571fd-4425-47bc-9c53-ad762ab37a71","resolution":{"observed_at":"2026-08-15T20:59:15.033535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T20:59:14.981645Z","title":"Ker- nel alignment risk estimator: Risk prediction from training data,","venue":null,"work_id":"6ab320f8-d379-4841-885a-8fc809265a71","year":2020},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.567128Z"},"links":{"citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:cd3d1c68e1f654c0440a7210c35ef36cda98da89203d08caa324bb2cad318d17","observation_id":"3dd28630-17dd-45e8-9a59-b1ba199c1267","resolution":{"observed_at":"2026-08-15T20:59:14.986807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08938","last_updated":"2024-03-13T20:12:03Z","snapshot_observed_at":"2026-08-20T06:40:14.578575Z","submitted_at":"2024-03-13T20:12:03Z","title":"A non-asymptotic theory of Kernel Ridge Regression: deterministic equivalents, test error, and GCV estimator","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08938","snapshot_observed_at":"2026-08-15T20:59:14.589412Z","title":"Kernel machines that adapt to GPUs for effective large batch training,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.589412Z"},"links":{"cited_paper":"/paper/2403.08938","citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:1c02e06d583a5733cab6b6857b0e3a08136b5091ff226e6e299ee3a5b5bc151b","observation_id":"75fe4303-d842-4c81-93a0-60992ed131cb","resolution":{"observed_at":"2026-08-15T20:59:14.589412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.14646","last_updated":"2024-05-15T23:46:41Z","snapshot_observed_at":"2026-08-17T15:59:03.754792Z","submitted_at":"2023-11-24T18:27:41Z","title":"More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.14646","snapshot_observed_at":"2026-08-15T20:59:14.600954Z","title":"More is better in modern machine learning: when infinite overparameterization is optimal and overfitting is obligatory,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.600954Z"},"links":{"cited_paper":"/paper/2311.14646","citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:31e68787a8840cd93165d5b1f1e154d98b736367417b0a2d801cbd5f2e069e04","observation_id":"a1d9903f-9fa4-4e3c-b8d9-beb9e4ae4cdb","resolution":{"observed_at":"2026-08-15T20:59:14.600954Z","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":"2026-08-15T20:59:14.888234Z","title":"For datasets with fewer than 100 observations, we standardize the data using RobustScaler() from sklearn","venue":null,"work_id":"b02f703c-bc9e-4e2f-bed4-9f0b5c9b1b72","year":2014},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.621322Z"},"links":{"citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:e40a28394a1a2c377ed3cd039f08ab51b8c9f3273d35935c599eb5d7a5e94b55","observation_id":"4ccbe9f5-5439-4fed-a6d7-2a56f560714f","resolution":{"observed_at":"2026-08-15T20:59:14.894508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T20:59:14.905609Z","title":"A.2 Details For the MNIST Dataset","venue":null,"work_id":"21270e85-fd4f-41dc-9aff-a7f1edd41c28","year":2024},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.616753Z"},"links":{"citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:dc437c88e36290163702fc4814cf743def6820c00db848c4ab608ded252d2f7b","observation_id":"08b3f3b7-1f65-428c-b20d-7314c9d074cd","resolution":{"observed_at":"2026-08-15T20:59:14.910284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T20:59:14.996610Z","title":"Gradient descent finds global minima of deep neural networks,","venue":null,"work_id":"8f633215-90ff-4142-9828-fda9da9e5003","year":2019},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.554586Z"},"links":{"citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:e612c7a874ae0e22167e04686842088ed79ece34736114674240f5f7edf151ea","observation_id":"7e70f9b2-adb2-4fb9-81ea-d838ce9aed72","resolution":{"observed_at":"2026-08-15T20:59:15.001702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T20:59:15.012544Z","title":"Toward deeper understanding of neural networks: The power of initialization and a dual view on expressivity,","venue":null,"work_id":"93f5b1bb-5098-4ab3-bbe7-e804e9b1b45e","year":2016},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.548937Z"},"links":{"citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:013f814745e8037c1f8383c2414da0ab5d4d5934975a334deef4e583d82388d6","observation_id":"3f9c8025-0c31-44c5-9f4a-18e9cded01c8","resolution":{"observed_at":"2026-08-15T20:59:15.017782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.07998","last_updated":"2025-09-10T18:21:17Z","snapshot_observed_at":"2026-08-19T06:46:30.813240Z","submitted_at":"2025-02-11T22:34:49Z","title":"Adaptive kernel predictors from feature-learning infinite limits of neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.07998","snapshot_observed_at":"2026-08-15T20:59:14.572606Z","title":"The virtue of complexity in return prediction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.572606Z"},"links":{"cited_paper":"/paper/2502.07998","citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:956104ac6afe83b9d100e99e65d38285f9bf30d3956e3f2dd386a3ca75459eca","observation_id":"f3c1814f-c73c-4136-b25a-0a878640e987","resolution":{"observed_at":"2026-08-15T20:59:14.572606Z","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":"2026-08-15T20:59:14.950489Z","title":"Diving into the shallows: a computational perspective on large- scale shallow learning,","venue":null,"work_id":"28f0c9df-edb2-4590-80a1-e4864d329085","year":2017},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.583681Z"},"links":{"citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:54805725f82d9363d84a1d9bcebf8aa5c6a046852777c80c9cd3820bd86c2e37","observation_id":"86758e25-3e42-48b0-85e3-167513aab967","resolution":{"observed_at":"2026-08-15T20:59:14.954854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.08560","last_updated":"2020-12-07T17:59:02Z","snapshot_observed_at":"2026-08-18T15:40:56.072162Z","submitted_at":"2019-03-19T16:53:11Z","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.08560","snapshot_observed_at":"2026-08-15T20:59:14.560837Z","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the neural tangent kernel,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.560837Z"},"links":{"cited_paper":"/paper/1903.08560","citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:88d20cc3f631fb2b0c00cb7767500b3032df99454ca9759f829ebaaaf73e9f91","observation_id":"d97925e8-f7aa-459a-bf43-3824cd2ce676","resolution":{"observed_at":"2026-08-15T20:59:14.560837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.07956","last_updated":"2020-01-07T16:11:56Z","snapshot_observed_at":"2026-08-18T14:04:42.281348Z","submitted_at":"2018-12-19T14:11:20Z","title":"On Lazy Training in Differentiable Programming","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.07956","snapshot_observed_at":"2026-08-15T20:59:14.535822Z","title":"To understand deep learning we need to understand kernel learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.535822Z"},"links":{"cited_paper":"/paper/1812.07956","citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:9b5d6757447afa58cc291f65e1dcf8e85291d919612e676073fb70143d35bf29","observation_id":"14009e15-5dd0-4d55-8939-d535ddeb3f8f","resolution":{"observed_at":"2026-08-15T20:59:14.535822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.00034","last_updated":"2021-12-02T21:06:20Z","snapshot_observed_at":"2026-08-18T12:54:55.683816Z","submitted_at":"2021-10-29T18:22:46Z","title":"Neural Networks as Kernel Learners: The Silent Alignment Effect","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.00034","snapshot_observed_at":"2026-08-15T20:59:14.528968Z","title":"Neural networks as kernel learners: The silent alignment effect,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.528968Z"},"links":{"cited_paper":"/paper/2111.00034","citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:281cadb932e8065d64ccc2041e373697ef35b1029447328d9a36a5edf1cf7591","observation_id":"3b99484f-94d0-4f61-b1f8-a342c256831c","resolution":{"observed_at":"2026-08-15T20:59:14.528968Z","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":"2026-08-15T20:59:14.920902Z","title":"More than a toy: Random matrix models predict how real-world neural representations generalize,","venue":null,"work_id":"e6d5acec-a589-47d2-bd66-758042fdbeec","year":2022},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.611829Z"},"links":{"citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:9752ac5d36c5c87e5d88a1187f7e25c9e09ed94b30e01da3f68e985d4e7f1d01","observation_id":"6261556c-0289-4fa3-9e6a-789f6a53cc78","resolution":{"observed_at":"2026-08-15T20:59:14.925084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-08-16T16:51:39.151684Z","submitted_at":"2022-06-20T21:23:28Z","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.10012","snapshot_observed_at":"2026-08-15T20:59:14.606693Z","title":"Limitations of the NTK for understanding generalization in deep learning,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.606693Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:2ef17414f2bdc5d490a42484ae776553be8c77984c8e1c6f0b82a98ff71f7bfc","observation_id":"544d55d1-a440-4509-9a2b-d77b70c25011","resolution":{"observed_at":"2026-08-15T20:59:14.606693Z","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":"2026-08-15T20:59:14.935751Z","title":"Uniform consistency of cross-validation estimators for high-dimensional ridge regression,","venue":null,"work_id":"56dfe456-da03-45e4-9bce-dc1786fc819a","year":2021},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.595003Z"},"links":{"citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:16401769c8bdfb3ce034a43eb2b9c9efd095174cd3dca1bc5837b2ddd22ed51b","observation_id":"cb5f46b9-41e6-44ed-aba5-623066c53ae7","resolution":{"observed_at":"2026-08-15T20:59:14.940136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T20:59:14.965677Z","title":"Wide neural networks of any depth evolve as linear models under gradient descent,","venue":null,"work_id":"ac108328-f54f-42ed-a75f-f373b981ff7d","year":2019},"citing_paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T20:59:14.578878Z"},"links":{"citing_paper":"/paper/2505.11347"},"observation_digest":"sha256:838b00b9d6debe94c022a7e7ea7a0eff7074562603740a01573c082f10c7e586","observation_id":"81fee9a2-5b6e-4b01-b0be-8b0e48e6442a","resolution":{"observed_at":"2026-08-15T20:59:14.971025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.11347","last_updated":"2025-05-21T09:58:43Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T17:24:31.629931Z","submitted_at":"2025-05-16T15:13:30Z","title":"Training NTK to Generalize with KARE"},"reference_resolution":{"displayed":18,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":10},"total_outbound_references":18},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2505.11347."}