{"as_of":"2026-08-09T06:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1ed59693b8a34594a15b2226dc475781224eada61f3a19ecf500e8dbd30e5ebe","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":14,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T11:19:07.021901Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T16:47:10.307161Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","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":"2026-08-08T11:19:07.021901Z","title":"Limitations of the ntk for understanding generalization in deep learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.07998","last_updated":"2025-09-10T18:21:17Z","snapshot_observed_at":"2026-08-08T11:09:21.022136Z","submitted_at":"2025-02-11T22:34:49Z","title":"Adaptive kernel predictors from feature-learning infinite limits of neural networks","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-08T11:19:07.021901Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2502.07998"},"observation_digest":"sha256:d675e5981d7acecd51adbe67baafd05952d3e6a5b531857cc18a898307d81ce9","observation_id":"8da687c9-9cfd-4ea6-a967-0d71f2b75040","resolution":{"observed_at":"2026-08-08T11:19:07.021901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","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":"2026-08-06T14:17:37.234144Z","title":"Limitations of the ntk for understanding generalization in deep learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.19680","last_updated":"2025-07-25T21:19:37Z","snapshot_observed_at":"2026-08-07T16:14:29.307306Z","submitted_at":"2025-07-25T21:19:37Z","title":"Feature learning is decoupled from generalization in high capacity neural networks","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-06T14:17:37.234144Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2507.19680"},"observation_digest":"sha256:091d7420eef4d95cb826dd4c9c86d80420592fb96bf271cf62d6154a6e9c6c3d","observation_id":"2bdd98f0-9d2a-4d3b-956b-480b6a9697d8","resolution":{"observed_at":"2026-08-06T14:17:37.234144Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","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":"2026-08-04T17:03:17.184315Z","title":"Limitations of the ntk for understanding generalization in deep learning.arXiv preprint arXiv:2206.10012, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.11167","last_updated":"2025-09-14T08:59:53Z","snapshot_observed_at":"2026-08-08T02:46:15.330994Z","submitted_at":"2025-09-14T08:59:53Z","title":"Harnessing Optimization Dynamics for Curvature-Informed Model Merging","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T17:03:17.184315Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2509.11167"},"observation_digest":"sha256:9c8e3972d440e700b95b31fa3e2cb544c9b608f5e865d5c9b38ccdb1e03b0a5b","observation_id":"3f7a2778-c414-4f50-b860-aaa24c6be19e","resolution":{"observed_at":"2026-08-04T17:03:17.184315Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","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":"2026-08-02T21:30:53.974565Z","title":"Limitations of the ntk for understanding generalization in deep learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.20062","last_updated":"2026-06-30T08:25:25Z","snapshot_observed_at":"2026-08-06T03:53:38.456812Z","submitted_at":"2026-02-23T17:19:33Z","title":"A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-02T21:30:53.974565Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2602.20062"},"observation_digest":"sha256:fbb89b19514db14ced9ff9e25c8c100cda3d07ab407acd5a173965615330c6b5","observation_id":"e20161cf-43e6-4be2-8c21-a002f48ac39d","resolution":{"observed_at":"2026-08-02T21:30:53.974565Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","submitted_at":"2022-06-20T21:23:28Z","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","version":1},"cited_work":{"arxiv_id":"2206.10012","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.10012","snapshot_observed_at":"2026-07-02T16:47:10.307161Z","title":"arXiv preprint arXiv:2206.10012 , year=","venue":null,"work_id":"541e81e6-eb10-4975-b5a2-0d7edae536b3","year":2022},"citing_paper":{"arxiv_id":"2604.21691","last_updated":"2026-04-23T13:58:12Z","snapshot_observed_at":"2026-08-02T12:48:50.592713Z","submitted_at":"2026-04-23T13:58:12Z","title":"There Will Be a Scientific Theory of Deep Learning","version":1},"reference_index":183,"source":"arxiv_source","source_observed_at":"2026-05-09T20:11:17.616190Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2604.21691"},"observation_digest":"sha256:35d0b92ea2b4d905f1aa69590d26dd3f507c1603ae0b98e26ce46e8d9f81b90c","observation_id":"848d2f75-143d-4b81-90f0-6f18cd14dd81","resolution":{"observed_at":"2026-05-11T15:21:08.617679Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","submitted_at":"2022-06-20T21:23:28Z","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","version":1},"cited_work":{"arxiv_id":"2206.10012","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.10012","snapshot_observed_at":"2026-07-02T16:47:10.307161Z","title":"arXiv preprint arXiv:2206.10012 , year=","venue":null,"work_id":"541e81e6-eb10-4975-b5a2-0d7edae536b3","year":2022},"citing_paper":{"arxiv_id":"2605.07870","last_updated":"2026-05-21T16:56:03Z","snapshot_observed_at":"2026-07-06T23:20:11.042952Z","submitted_at":"2026-05-08T15:28:01Z","title":"Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-11T03:02:52.833353Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2605.07870"},"observation_digest":"sha256:e191abfee66ed6f4eeb7a012922dd27e5c1c1b4e946c11438cfc79db06447738","observation_id":"79b371c7-0cbf-4893-a2ac-e4e881bb6e05","resolution":{"observed_at":"2026-05-11T03:05:53.374387Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","submitted_at":"2022-06-20T21:23:28Z","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","version":1},"cited_work":{"arxiv_id":"2206.10012","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.10012","snapshot_observed_at":"2026-07-02T16:47:10.307161Z","title":"arXiv preprint arXiv:2206.10012 , year=","venue":null,"work_id":"541e81e6-eb10-4975-b5a2-0d7edae536b3","year":2022},"citing_paper":{"arxiv_id":"2605.07870","last_updated":"2026-05-21T16:56:03Z","snapshot_observed_at":"2026-07-06T23:20:11.042952Z","submitted_at":"2026-05-08T15:28:01Z","title":"Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-22T10:25:54.649302Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2605.07870"},"observation_digest":"sha256:b997d5e245e50f88b7ad5fe5ebccb2117fa59face82571f298985b0e807cbec3","observation_id":"b1d58a01-2497-415d-a906-e8cc58f9cd1c","resolution":{"observed_at":"2026-05-22T10:26:24.239292Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","submitted_at":"2022-06-20T21:23:28Z","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","version":1},"cited_work":{"arxiv_id":"2206.10012","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.10012","snapshot_observed_at":"2026-07-02T16:47:10.307161Z","title":"arXiv preprint arXiv:2206.10012 , year=","venue":null,"work_id":"541e81e6-eb10-4975-b5a2-0d7edae536b3","year":2022},"citing_paper":{"arxiv_id":"2605.14200","last_updated":"2026-05-13T23:32:00Z","snapshot_observed_at":"2026-07-06T23:25:39.415637Z","submitted_at":"2026-05-13T23:32:00Z","title":"How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-05-15T04:45:20.091598Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2605.14200"},"observation_digest":"sha256:0f5a67c59da457a9d56428d3cf5bfd9b7999e553362ad4eb3644279facc0e75a","observation_id":"491e39fc-3f96-4bf2-afbd-279dc765d3c5","resolution":{"observed_at":"2026-05-15T04:49:44.889107Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","submitted_at":"2022-06-20T21:23:28Z","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","version":1},"cited_work":{"arxiv_id":"2206.10012","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.10012","snapshot_observed_at":"2026-07-02T16:47:10.307161Z","title":"arXiv preprint arXiv:2206.10012 , year=","venue":null,"work_id":"541e81e6-eb10-4975-b5a2-0d7edae536b3","year":2022},"citing_paper":{"arxiv_id":"2605.17767","last_updated":"2026-05-21T20:45:44Z","snapshot_observed_at":"2026-08-04T06:32:13.198687Z","submitted_at":"2026-05-18T02:37:50Z","title":"Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent","version":1},"reference_index":232,"source":"arxiv_source","source_observed_at":"2026-05-20T01:29:14.555216Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2605.17767"},"observation_digest":"sha256:6fd4c22955a5e2cd4e53deb7b08889743b868aec4802d7f56e67a86ea7e85180","observation_id":"ce7d5c1a-edbc-48fd-b6e5-c14272b2710a","resolution":{"observed_at":"2026-05-20T01:32:56.168233Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","submitted_at":"2022-06-20T21:23:28Z","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","version":1},"cited_work":{"arxiv_id":"2206.10012","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.10012","snapshot_observed_at":"2026-07-02T16:47:10.307161Z","title":"arXiv preprint arXiv:2206.10012 , year=","venue":null,"work_id":"541e81e6-eb10-4975-b5a2-0d7edae536b3","year":2022},"citing_paper":{"arxiv_id":"2605.17767","last_updated":"2026-05-21T20:45:44Z","snapshot_observed_at":"2026-08-04T06:32:13.198687Z","submitted_at":"2026-05-18T02:37:50Z","title":"Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent","version":2},"reference_index":232,"source":"arxiv_source","source_observed_at":"2026-05-25T06:39:16.246591Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2605.17767"},"observation_digest":"sha256:cb4161e6da6c48abe77ba092ee5febf9e0239de4e9808e89fd0fee08bd1b215e","observation_id":"0d3f3449-c7c6-43a3-84f0-6ea06f6ddc78","resolution":{"observed_at":"2026-05-25T06:40:24.900864Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","submitted_at":"2022-06-20T21:23:28Z","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","version":1},"cited_work":{"arxiv_id":"2206.10012","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.10012","snapshot_observed_at":"2026-07-02T16:47:10.307161Z","title":"arXiv preprint arXiv:2206.10012 , year=","venue":null,"work_id":"541e81e6-eb10-4975-b5a2-0d7edae536b3","year":2022},"citing_paper":{"arxiv_id":"2605.18598","last_updated":"2026-05-18T16:09:06Z","snapshot_observed_at":"2026-07-06T23:29:29.105126Z","submitted_at":"2026-05-18T16:09:06Z","title":"Pointwise Generalization in Deep Neural Networks","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-05-20T12:34:28.962887Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2605.18598"},"observation_digest":"sha256:19b4155fdf14b07f716afbed7d66066530b0d613f9a17551fa17094a32694912","observation_id":"daa0ee55-38c7-4c2f-a657-a1f7e9b7c271","resolution":{"observed_at":"2026-05-20T12:38:16.908806Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","submitted_at":"2022-06-20T21:23:28Z","title":"Limitations of the NTK for Understanding Generalization in Deep Learning","version":1},"cited_work":{"arxiv_id":"2206.10012","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.10012","snapshot_observed_at":"2026-07-02T16:47:10.307161Z","title":"arXiv preprint arXiv:2206.10012 , year=","venue":null,"work_id":"541e81e6-eb10-4975-b5a2-0d7edae536b3","year":2022},"citing_paper":{"arxiv_id":"2606.07495","last_updated":"2026-06-05T17:49:19Z","snapshot_observed_at":"2026-08-05T16:38:31.972892Z","submitted_at":"2026-06-05T17:49:19Z","title":"Second-Order Path Kernel Interpolation Formulas in Machine Learning","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-06-27T22:20:15.074286Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2606.07495"},"observation_digest":"sha256:476dafd14943db88d3f8a5d2966709881d58383dc85e002a409525c0ebc317bb","observation_id":"2909d9f0-f5df-40dd-bb3f-6f48530048b9","resolution":{"observed_at":"2026-07-02T16:47:10.308432Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","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":"2026-07-13T03:41:36.654380Z","title":"Limitations of the","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.09350","last_updated":"2026-07-10T12:29:58Z","snapshot_observed_at":"2026-08-02T18:48:52.800985Z","submitted_at":"2026-07-10T12:29:58Z","title":"The Cost of Discretization in Functional Linear Regression: Minimax Rates and Adaptation","version":1},"reference_index":119,"source":"arxiv_source","source_observed_at":"2026-07-13T03:41:36.654380Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2607.09350"},"observation_digest":"sha256:5e7b747cfbca0d48203dce6b3c1fa8b83849b849498ba0f0767eddd64a02a6de","observation_id":"c89ad082-364c-452e-878e-88727cd65d5f","resolution":{"observed_at":"2026-07-13T03:41:36.654380Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","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":"2026-08-01T06:58:10.426306Z","title":"Limitations of the ntk for understanding generalization in deep learning.arXiv preprint arXiv:2206.10012,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21716","last_updated":"2026-07-23T18:02:03Z","snapshot_observed_at":"2026-08-07T15:18:52.757558Z","submitted_at":"2026-07-23T18:02:03Z","title":"A Defense of the Quadratic Model","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T06:58:10.426306Z"},"links":{"cited_paper":"/paper/2206.10012","citing_paper":"/paper/2607.21716"},"observation_digest":"sha256:b1264dace2e1298e51b00121efd36380ca2c654a77dcb515a79b423bbf5554d5","observation_id":"c8bc3caf-7b71-4841-ac08-c92468b05caf","resolution":{"observed_at":"2026-08-01T06:58:10.426306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2206.10012/citation-record","integrity":"/paper/2206.10012/integrity","json":"/paper/2206.10012/citation-record.json","paper":"/paper/2206.10012"},"outbound":[],"paper":{"arxiv_id":"2206.10012","last_updated":"2022-06-20T21:23:28Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T13:22:50.125014Z","submitted_at":"2022-06-20T21:23:28Z","title":"Limitations of the NTK for Understanding Generalization in Deep Learning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 14 inbound Pith citation observations for arXiv:2206.10012."}