{"as_of":"2026-08-13T04:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fa9c48702ebd95a451f52ad5a45019339f98a2e36564ae2853b6ae1d2f22421a","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T04:36:32.204110Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-30T15:56:46.678986Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-18T14:01:28.074283Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"cited_work":{"arxiv_id":"2412.18756","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.18756","snapshot_observed_at":"2026-07-29T01:25:26.226530Z","title":"Zhang, J","venue":null,"work_id":"7ff4b6a4-1d5c-48a8-9019-3e3612a3bf40","year":2024},"citing_paper":{"arxiv_id":"2509.20294","last_updated":"2026-05-11T15:07:04Z","snapshot_observed_at":"2026-08-13T04:21:10.824467Z","submitted_at":"2025-09-24T16:28:08Z","title":"Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels","version":4},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-18T13:56:28.965345Z"},"links":{"cited_paper":"/paper/2412.18756","citing_paper":"/paper/2509.20294"},"observation_digest":"sha256:4d75cdb72b0593826773bd73dbbe1eba9045e2deb88a63d30ba9bae88e051326","observation_id":"f6a3ed5b-8500-4037-b498-41f376941199","resolution":{"observed_at":"2026-07-29T01:25:26.226530Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"cited_work":{"arxiv_id":"2412.18756","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.18756","snapshot_observed_at":"2026-07-29T01:25:26.226530Z","title":"Zhang, J","venue":null,"work_id":"7ff4b6a4-1d5c-48a8-9019-3e3612a3bf40","year":2024},"citing_paper":{"arxiv_id":"2511.09425","last_updated":"2026-04-07T11:19:48Z","snapshot_observed_at":"2026-07-06T22:35:37.039024Z","submitted_at":"2025-11-12T15:39:28Z","title":"Supporting Evidence for the Adaptive Feature Program across Diverse Models","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-17T23:08:21.701195Z"},"links":{"cited_paper":"/paper/2412.18756","citing_paper":"/paper/2511.09425"},"observation_digest":"sha256:1641e30b880adfe47cf750e33e4c4b28df29c75c29b1dcc5d38cd81becaca6cc","observation_id":"1b7d53aa-7687-43f9-ad99-d5d00d15c24d","resolution":{"observed_at":"2026-07-29T01:25:26.226530Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18756","snapshot_observed_at":"2026-07-30T15:56:46.678986Z","title":"arXiv preprint arXiv:2412.18756 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26955","last_updated":"2026-07-29T14:21:39Z","snapshot_observed_at":"2026-08-06T21:10:17.072894Z","submitted_at":"2026-07-29T14:21:39Z","title":"Breaking the Curse with BAND: Nonparametric Distribution Estimation in High Dimensions","version":1},"reference_index":204,"source":"arxiv_source","source_observed_at":"2026-07-30T15:56:46.678986Z"},"links":{"cited_paper":"/paper/2412.18756","citing_paper":"/paper/2607.26955"},"observation_digest":"sha256:7e1a94f14935b285b6054ad4b5459202861f3f4d3a15864780cb29f32fe70b10","observation_id":"a8d5c886-82c7-430e-bf16-f63866706bea","resolution":{"observed_at":"2026-07-30T15:56:46.678986Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.18756/citation-record","integrity":"/paper/2412.18756/integrity","json":"/paper/2412.18756/citation-record.json","paper":"/paper/2412.18756"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.04980","last_updated":"2024-06-04T08:28:52Z","snapshot_observed_at":"2026-08-13T04:24:09.225455Z","submitted_at":"2024-02-07T15:57:30Z","title":"Asymptotics of feature learning in two-layer networks after one gradient-step","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04980","snapshot_observed_at":"2026-08-11T04:36:32.038109Z","title":"Asymptotics of feature learning in two-layer networks after one gradient-step","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.038109Z"},"links":{"cited_paper":"/paper/2402.04980","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:dfa688d449ef6b263e02b1458ccb66f75d14fe7513877dc4293b627a05b345d3","observation_id":"3517b08a-6313-4d32-8b1c-26d7ae5548c7","resolution":{"observed_at":"2026-08-11T04:36:32.038109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07709","last_updated":"2024-10-08T11:21:33Z","snapshot_observed_at":"2026-08-13T04:10:16.400639Z","submitted_at":"2024-04-11T12:53:23Z","title":"A Geometrical Analysis of Kernel Ridge Regression and its Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07709","snapshot_observed_at":"2026-08-11T04:36:32.058227Z","title":"A geometrical analysis of kernel ridge regression and its applications","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.058227Z"},"links":{"cited_paper":"/paper/2404.07709","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:73082ff08b72ee2340bb9a86bd3fca9c6507d43c589eb506824a2964974c9eef","observation_id":"d8de97ac-3092-40da-9c7e-8ab2417c7805","resolution":{"observed_at":"2026-08-11T04:36:32.058227Z","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":"2026-08-11T04:36:32.877531Z","title":"Disentangling feature and lazy training in deep neural networks","venue":null,"work_id":"4703f730-6e09-4b3d-a458-c84d78610936","year":2020},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.064400Z"},"links":{"citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:b32fe60c4134acc3e0a0a3ff4143b8c1578ec05e55656c99c32c751ffe7c6584","observation_id":"51a1b87e-d6a6-4969-84e8-019b34317a65","resolution":{"observed_at":"2026-08-11T04:36:32.886390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T04:36:32.072125Z","title":"URL https: //doi.org/10.1214/20-AOS1990","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.072125Z"},"links":{"citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:ba04067697acc57495d26e28c169ed39ad058373ae13adc240990337f1351d7e","observation_id":"455e7fe4-ec85-4d39-ad7d-52a1eb6ae3f9","resolution":{"observed_at":"2026-08-11T04:36:32.072125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.05989","last_updated":"2019-09-13T00:21:53Z","snapshot_observed_at":"2026-08-09T04:32:29.065400Z","submitted_at":"2019-09-13T00:21:53Z","title":"Finite Depth and Width Corrections to the Neural Tangent Kernel","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.05989","snapshot_observed_at":"2026-08-11T04:36:32.078516Z","title":"Finite depth and width corrections to the neural tangent kernel","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.078516Z"},"links":{"cited_paper":"/paper/1909.05989","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:67b779dfa8f2ec0fb927b0b726f90b66f918011f863cf69f560ce61dbf2e18da","observation_id":"a76c8b3f-b5e7-4c17-bdec-c7268fddd0ed","resolution":{"observed_at":"2026-08-11T04:36:32.078516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.06798","last_updated":"2022-05-13T17:50:54Z","snapshot_observed_at":"2026-07-06T13:09:47.622920Z","submitted_at":"2022-05-13T17:50:54Z","title":"Sharp Asymptotics of Kernel Ridge Regression Beyond the Linear Regime","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.06798","snapshot_observed_at":"2026-08-11T04:36:32.085843Z","title":"URL https://doi.org/10.1214/21-AOS2133","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.085843Z"},"links":{"cited_paper":"/paper/2205.06798","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:5a12d3f5b08aaf39fc6d24f1cfa30811045548a1074245c7b33353bdd029cc1d","observation_id":"927b3043-1263-4899-b646-59bd3e24f388","resolution":{"observed_at":"2026-08-11T04:36:32.085843Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00894","last_updated":"2024-10-31T13:05:24Z","snapshot_observed_at":"2026-08-12T22:58:36.753222Z","submitted_at":"2024-09-02T02:11:52Z","title":"Improving Adaptivity via Over-Parameterization in Sequence Models","version":2},"cited_work":{"arxiv_id":"2409.00894","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.00894","snapshot_observed_at":"2026-08-11T04:36:32.603575Z","title":"Improving Adaptivity via Over-Parameterization in Sequence Models","venue":"cs.LG","work_id":"122ccb55-8ae5-44b6-9743-0466edb9c713","year":2024},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.114211Z"},"links":{"cited_paper":"/paper/2409.00894","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:b00ba785e6ef4de97aeee6b2f4afb785828867a50a2c559363a78f1d4ede3576","observation_id":"e11575a8-093a-45bd-bc69-41e7d01d4a6e","resolution":{"observed_at":"2026-08-11T04:36:32.612085Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T04:36:32.130490Z","title":"URL https://doi.org/10.1214/19-AOS1849","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.130490Z"},"links":{"citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:ea7c4f789a07d8d4e7630904dacc132305c750a746f1f499b183f60f7dbaa902","observation_id":"e668b5ee-8579-441a-8206-767e9b2db9f2","resolution":{"observed_at":"2026-08-11T04:36:32.130490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.04268","last_updated":"2024-06-28T09:59:08Z","snapshot_observed_at":"2026-07-06T16:16:07.182657Z","submitted_at":"2023-09-08T11:29:05Z","title":"Optimal Rate of Kernel Regression in Large Dimensions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.04268","snapshot_observed_at":"2026-08-11T04:36:32.137166Z","title":"Optimal rate of kernel regression in large dimensions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.137166Z"},"links":{"cited_paper":"/paper/2309.04268","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:8529cd4aa89cc56bf32db7cbc85d961c3f799d8580e21557926f45bd7fd07fc2","observation_id":"79c64076-8102-4815-b074-e339ee1137e8","resolution":{"observed_at":"2026-08-11T04:36:32.137166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.06569","last_updated":"2024-07-15T21:54:26Z","snapshot_observed_at":"2026-08-10T12:42:18.970962Z","submitted_at":"2022-07-14T00:23:01Z","title":"Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.06569","snapshot_observed_at":"2026-08-11T04:36:32.143811Z","title":"Benign, tempered, or catastrophic: A taxonomy of overfitting","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.143811Z"},"links":{"cited_paper":"/paper/2207.06569","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:fabfcb3f0061457f8f5502cf3d533cea25ef35c09d3c8ef1da745530bdbe77c8","observation_id":"da59c207-ceab-4d6d-a9b2-c6a78528353d","resolution":{"observed_at":"2026-08-11T04:36:32.143811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.10425","last_updated":"2022-04-21T22:20:52Z","snapshot_observed_at":"2026-07-06T13:02:38.535183Z","submitted_at":"2022-04-21T22:20:52Z","title":"Spectrum of inner-product kernel matrices in the polynomial regime and multiple descent phenomenon in kernel ridge regression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.10425","snapshot_observed_at":"2026-08-11T04:36:32.150378Z","title":"doi: https://doi.org/10.1016/j.acha.2021.12.003","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.150378Z"},"links":{"cited_paper":"/paper/2204.10425","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:978b3f399b02228b7fa99c055994804f5405f4fdf681dbc855eafc6f2a3a7b98","observation_id":"ffe35d1e-8857-44d1-b7b0-c2dde4ccb93b","resolution":{"observed_at":"2026-08-11T04:36:32.150378Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08938","last_updated":"2024-03-13T20:12:03Z","snapshot_observed_at":"2026-08-13T00:54:48.263699Z","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":"2026-08-11T04:36:32.156934Z","title":"A non-asymptotic theory of kernel ridge regression: deterministic equivalents, test error, and gcv estimator","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.156934Z"},"links":{"cited_paper":"/paper/2403.08938","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:6bd7beac3463faf921d6df7ac65bdd0b573dea4ac0a1a6d36987e7f3b4eb3109","observation_id":"32c08120-e198-4a27-9861-ff60026728a2","resolution":{"observed_at":"2026-08-11T04:36:32.156934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.07891","last_updated":"2025-04-10T04:26:24Z","snapshot_observed_at":"2026-08-07T19:20:45.700824Z","submitted_at":"2023-10-11T20:55:02Z","title":"A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.07891","snapshot_observed_at":"2026-08-11T04:36:32.163578Z","title":"A theory of non-linear feature learning with one gradient step in two-layer neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.163578Z"},"links":{"cited_paper":"/paper/2310.07891","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:ed9b00aae887cbe58dec6ed95ba3a8c1c16fbfa24cf88030b6382b777875ac00","observation_id":"75330558-2d30-44df-a8b6-0b709fc034cb","resolution":{"observed_at":"2026-08-11T04:36:32.163578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.05392","last_updated":"2019-07-04T00:17:07Z","snapshot_observed_at":"2026-07-06T07:59:57.219458Z","submitted_at":"2019-06-12T21:39:06Z","title":"Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.05392","snapshot_observed_at":"2026-08-11T04:36:32.169879Z","title":"Generalization guarantees for neural networks via harnessing the low-rank structure of the jacobian","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.169879Z"},"links":{"cited_paper":"/paper/1906.05392","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:e1de03683298911e6cbe19c66ec5ebeedefeefa7aead5bb791db988f423dcc05","observation_id":"06f2fd3a-d4e8-4d7f-a0a9-44c3ee3a9911","resolution":{"observed_at":"2026-08-11T04:36:32.169879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.14301","last_updated":"2022-02-10T01:39:58Z","snapshot_observed_at":"2026-08-11T09:58:53.693954Z","submitted_at":"2021-05-29T13:50:03Z","title":"A Theory of Neural Tangent Kernel Alignment and Its Influence on Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.14301","snapshot_observed_at":"2026-08-11T04:36:32.183489Z","title":"A theory of neural tangent kernel alignment and its influence on training","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.183489Z"},"links":{"cited_paper":"/paper/2105.14301","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:ae4a331ecdda81059a4f0725e682e3eb03573a97b036239adf9491366c27f3e8","observation_id":"3b4d5e54-3474-4ad6-82b2-69a0bd4010d6","resolution":{"observed_at":"2026-08-11T04:36:32.183489Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.14522","last_updated":"2022-07-15T17:04:24Z","snapshot_observed_at":"2026-08-10T23:48:51.698481Z","submitted_at":"2020-11-30T03:21:05Z","title":"Feature Learning in Infinite-Width Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.14522","snapshot_observed_at":"2026-08-11T04:36:32.197212Z","title":"Feature learning in infinite-width neural networks","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.197212Z"},"links":{"cited_paper":"/paper/2011.14522","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:160463dbaf5367a12884a9e1706bf4fb3de7143a00c75245d095b9491fdb65bd","observation_id":"7a3fd1b7-7519-4197-a38b-e3201a7fd318","resolution":{"observed_at":"2026-08-11T04:36:32.197212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.01270","last_updated":"2024-01-02T16:14:35Z","snapshot_observed_at":"2026-08-09T13:37:16.584189Z","submitted_at":"2024-01-02T16:14:35Z","title":"Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.01270","snapshot_observed_at":"2026-08-11T04:36:32.204110Z","title":"On the optimality of misspecified spectral algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.204110Z"},"links":{"cited_paper":"/paper/2401.01270","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:78496ece413cd7bf10cec1eb97201a9309d6e39882af622d4b15a1b93542a81a","observation_id":"5f901e5c-b664-47a5-a86a-c9e5ce0cbf36","resolution":{"observed_at":"2026-08-11T04:36:32.204110Z","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":"10.1017/cbo9780511662201","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T04:36:32.302251Z","title":"Jianqing Fan, Cong Ma, and Yiqiao Zhong","venue":null,"work_id":"068ea2f4-3085-43e1-9c93-6fa550cbc455","year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":1996,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.051607Z"},"links":{"citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:433aedc8aceb50dadc889b3dbad78e75ac12fd801be657df1740aaee77a812f4","observation_id":"313196ee-4a9b-4bdd-ac2a-98750b100e9e","resolution":{"observed_at":"2026-08-11T04:36:32.308777Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T04:36:32.855948Z","title":"Neural spectrum alignment: Empirical study","venue":null,"work_id":"128a6268-6b83-4d6e-82d0-4bc90e873d8e","year":2020},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":2001,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.101464Z"},"links":{"citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:cdf9f5b1187c08f8bf800aecad7537b49bd2179340b282f1a258d1804241124e","observation_id":"2c253b90-0ee0-45df-9dbe-61c1d762e605","resolution":{"observed_at":"2026-08-11T04:36:32.862589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.00570","last_updated":"2023-09-01T16:30:02Z","snapshot_observed_at":"2026-08-09T20:28:46.796888Z","submitted_at":"2023-09-01T16:30:02Z","title":"Mechanism of feature learning in convolutional neural networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.00570","snapshot_observed_at":"2026-08-11T04:36:32.019182Z","title":"On the inconsistency of kernel ridgeless regression in fixed dimensions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":2007,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.019182Z"},"links":{"cited_paper":"/paper/2309.00570","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:f6015cb0e4e9d55f66edf1b1fd29b895f0aebfe33f5f8f6087625425686ebfc0","observation_id":"2d90223a-b4d2-4ccb-9699-e8c4a52fd406","resolution":{"observed_at":"2026-08-11T04:36:32.019182Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.07187","last_updated":"2024-09-16T09:57:35Z","snapshot_observed_at":"2026-07-06T17:15:14.689584Z","submitted_at":"2024-01-14T02:30:19Z","title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","version":3},"cited_work":{"arxiv_id":"2401.07187","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.07187","snapshot_observed_at":"2026-08-11T04:36:32.371697Z","title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","venue":"stat.ML","work_id":"0e0c7b55-e309-4e59-9a40-1a4b1f482e0e","year":2024},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.190161Z"},"links":{"cited_paper":"/paper/2401.07187","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:33dc98767de10f096dfaf6635de743f7333cf1147bace085a1fdda29d3b5c8a2","observation_id":"7a3d8938-e178-4a9c-ab4f-328ac75b4f38","resolution":{"observed_at":"2026-08-11T04:36:32.378779Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1214/08-aos648","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T04:36:32.267978Z","title":"URL https://doi.org/10.1214/08-AOS648","venue":null,"work_id":"ef1d1aba-9083-4572-a5eb-60466c31708b","year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":2010,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.094269Z"},"links":{"citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:bd28fec17d363070e458899a4f0c9260e28da2b8d45cda4830532222307e336c","observation_id":"77b057d3-dfab-4c25-9296-d963e76baaa5","resolution":{"observed_at":"2026-08-11T04:36:32.275175Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.13881","last_updated":"2023-05-09T14:29:35Z","snapshot_observed_at":"2026-07-06T14:35:33.623257Z","submitted_at":"2022-12-28T15:50:58Z","title":"Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.13881","snapshot_observed_at":"2026-08-11T04:36:32.176405Z","title":"Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.176405Z"},"links":{"cited_paper":"/paper/2212.13881","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:67b99c406e81a47e28124a49b60d96773091c67f97279bbb692e6210d604af69","observation_id":"58152eb7-328a-496c-b6d5-77e4c8be3215","resolution":{"observed_at":"2026-08-11T04:36:32.176405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.05933","last_updated":"2023-02-12T15:07:27Z","snapshot_observed_at":"2026-08-10T10:12:15.991515Z","submitted_at":"2023-02-12T15:07:27Z","title":"Generalization Ability of Wide Neural Networks on $\\mathbb{R}$","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.05933","snapshot_observed_at":"2026-08-11T04:36:32.107556Z","title":"Generalization ability of wide neural networks on R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.107556Z"},"links":{"cited_paper":"/paper/2302.05933","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:c8deb5be8dff93ee5dc1f16d9c417571a20fcbf7dc5b5fae89d61c5da219b6a8","observation_id":"ec8b3515-b5d3-43e0-bce9-9b050a8ddd7c","resolution":{"observed_at":"2026-08-11T04:36:32.107556Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.15995","last_updated":"2024-02-20T07:53:38Z","snapshot_observed_at":"2026-08-13T00:18:33.829853Z","submitted_at":"2023-12-26T10:55:20Z","title":"Generalization in Kernel Regression Under Realistic Assumptions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.15995","snapshot_observed_at":"2026-08-11T04:36:32.011823Z","title":"Generalization in kernel regression under realistic assumptions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.011823Z"},"links":{"cited_paper":"/paper/2312.15995","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:05aa43ea178cc961fedbb2e7bb9cf86b8c456fd28f4209577a082c02bd63c70a","observation_id":"22b7ea4f-e69c-460f-8d72-a714a21fe878","resolution":{"observed_at":"2026-08-11T04:36:32.011823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18270","last_updated":"2025-06-03T19:12:56Z","snapshot_observed_at":"2026-08-13T03:08:08.630221Z","submitted_at":"2023-05-29T17:43:44Z","title":"How Two-Layer Neural Networks Learn, One (Giant) Step at a Time","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18270","snapshot_observed_at":"2026-08-11T04:36:32.044680Z","title":"Learning two-layer neural networks, one (giant) step at a time","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.044680Z"},"links":{"cited_paper":"/paper/2305.18270","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:98fb2f64cf738a0badefb582ce3cc971ebcb11d9753e3572c32322be978c5592","observation_id":"fa86431a-df41-4314-9fb5-a8535fcabfaf","resolution":{"observed_at":"2026-08-11T04:36:32.044680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.01599","last_updated":"2026-06-08T12:50:51Z","snapshot_observed_at":"2026-07-06T17:11:09.611305Z","submitted_at":"2024-01-03T08:00:50Z","title":"Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.01599","snapshot_observed_at":"2026-08-11T04:36:32.122676Z","title":"Ridgeless","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.122676Z"},"links":{"cited_paper":"/paper/2401.01599","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:8504889799797e6697fae617f2a6a34d58a916a9967a4775d6f7ee31fc89e350","observation_id":"12f8b6ac-69a9-4f2c-8d37-1318bee47e9a","resolution":{"observed_at":"2026-08-11T04:36:32.122676Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05626","last_updated":"2024-10-08T02:22:50Z","snapshot_observed_at":"2026-08-12T22:28:37.042795Z","submitted_at":"2024-10-08T02:22:50Z","title":"On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory","version":1},"cited_work":{"arxiv_id":"2410.05626","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.05626","snapshot_observed_at":"2026-08-11T04:36:32.775496Z","title":"On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory","venue":"stat.ML","work_id":"93333c2a-cdf4-4e36-97fb-d84cad2f0386","year":2024},"citing_paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-11T04:36:32.032238Z"},"links":{"cited_paper":"/paper/2410.05626","citing_paper":"/paper/2412.18756"},"observation_digest":"sha256:210407e3d73763ff7d361d2634a1a0c20762fd93e8bb376a4e49a54e5c66d053","observation_id":"658ed5a2-dde8-4994-bd04-a024d0cd8e33","resolution":{"observed_at":"2026-08-11T04:36:32.782867Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.18756","last_updated":"2024-12-25T03:03:58Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T19:52:15.938751Z","submitted_at":"2024-12-25T03:03:58Z","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":21,"verified_exact":4,"verified_fuzzy":2},"total_outbound_references":28},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 3 inbound Pith citation observations for arXiv:2412.18756."}