{"as_of":"2026-08-17T22:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f47b0fc7cedebe0b97082a8fe109de5704977b4c78dbb3eac34eb817cabc09db","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":13,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":13,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":13,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":13,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T11:02:29.363232Z","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":"2026-07-02T22:47:26.170047Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":"1902.06720","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-07-02T22:47:26.170047Z","title":"Wide neural networks of any depth evolv e as linear models under gradient descent","venue":null,"work_id":"c89ee0d8-2737-411e-bfc6-57db871c9acf","year":2020},"citing_paper":{"arxiv_id":"1906.08654","last_updated":"2019-06-20T14:17:33Z","snapshot_observed_at":"2026-08-16T06:22:28.549984Z","submitted_at":"2019-06-20T14:17:33Z","title":"ID3 Learns Juntas for Smoothed Product Distributions","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-25T19:41:47.309669Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/1906.08654"},"observation_digest":"sha256:ab1cb98193b6c8f3ff4e1fa8ddceea948b26eaafa99d792f17ad77d2a9152291","observation_id":"594230e1-80ae-49d6-b302-f918a27c482b","resolution":{"observed_at":"2026-05-25T19:46:10.453628Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":"1902.06720","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-07-02T22:47:26.170047Z","title":"Wide neural networks of any depth evolv e as linear models under gradient descent","venue":null,"work_id":"c89ee0d8-2737-411e-bfc6-57db871c9acf","year":2020},"citing_paper":{"arxiv_id":"1906.08899","last_updated":"2019-06-21T00:29:54Z","snapshot_observed_at":"2026-08-13T07:24:15.845572Z","submitted_at":"2019-06-21T00:29:54Z","title":"Limitations of Lazy Training of Two-layers Neural Networks","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-05-25T19:11:02.369698Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/1906.08899"},"observation_digest":"sha256:26544e0f4b5ec35c3494de7ed929267d7b9a02d41cd040678a026ff18d2caf41","observation_id":"120cf4a5-a5ff-41d6-9330-e56ced565a45","resolution":{"observed_at":"2026-05-25T19:11:09.720890Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-08-14T11:02:29.363232Z","title":"S., Bahri, Y ., Sohl- Dickstein, J., and Pennington, J","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"1908.10030","last_updated":"2019-08-27T04:49:23Z","snapshot_observed_at":"2026-08-17T21:15:40.397289Z","submitted_at":"2019-08-27T04:49:23Z","title":"Finite size corrections for neural network Gaussian processes","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-14T11:02:29.363232Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/1908.10030"},"observation_digest":"sha256:1b305ae4c68fd157d679b376fd5b9624674d7f5acb6b6bb5018b92b992057e6d","observation_id":"a451b1ed-81d9-4611-bc66-04cc96959125","resolution":{"observed_at":"2026-08-14T11:02:29.363232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-08-14T10:27:42.116640Z","title":", Xiao, L","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1909.01150","last_updated":"2019-11-12T21:42:43Z","snapshot_observed_at":"2026-08-15T10:56:00.207708Z","submitted_at":"2019-08-29T15:38:19Z","title":"Neural Policy Gradient Methods: Global Optimality and Rates of Convergence","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-14T10:27:42.116640Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/1909.01150"},"observation_digest":"sha256:a2b712aff4a0496529d3d55e7fd8dc45e33fa83bda67b04457f8bd94a4ddeb7a","observation_id":"b664bb50-65b6-4ce9-b454-a87a21a16496","resolution":{"observed_at":"2026-08-14T10:27:42.116640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":"1902.06720","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-07-02T22:47:26.170047Z","title":"Wide neural networks of any depth evolv e as linear models under gradient descent","venue":null,"work_id":"c89ee0d8-2737-411e-bfc6-57db871c9acf","year":2020},"citing_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-08-13T17:41:53.092611Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-24T15:31:29.677449Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/2001.08361"},"observation_digest":"sha256:4a5f2dcd880903fbb8ef4bdefd016799fea60c08bc84cdd5231cf199b8bac797","observation_id":"129bb48c-afea-4464-bd2f-fc7a6a007143","resolution":{"observed_at":"2026-05-09T04:51:47.655093Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":"1902.06720","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-07-02T22:47:26.170047Z","title":"Wide neural networks of any depth evolv e as linear models under gradient descent","venue":null,"work_id":"c89ee0d8-2737-411e-bfc6-57db871c9acf","year":2020},"citing_paper":{"arxiv_id":"2010.14701","last_updated":"2020-11-06T04:16:36Z","snapshot_observed_at":"2026-07-06T10:09:17.078776Z","submitted_at":"2020-10-28T02:17:24Z","title":"Scaling Laws for Autoregressive Generative Modeling","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-05-13T07:49:43.711653Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/2010.14701"},"observation_digest":"sha256:968d75ff6902c3bdbbfb5004c82106384a3e683c9f897b391e262cea91f9d9a1","observation_id":"f93b6da1-2f8b-48a5-be69-5411989a108a","resolution":{"observed_at":"2026-05-13T07:49:43.845507Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-08-07T13:15:36.947914Z","title":"Schoenholz, Yasaman Bahri, Roman Novak, Jascha Sohl-Dickstein, and Jeffrey Pennington","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.22502","last_updated":"2025-07-03T11:27:35Z","snapshot_observed_at":"2026-08-15T07:57:20.724684Z","submitted_at":"2025-05-28T15:50:56Z","title":"Assessing Quantum Advantage for Gaussian Process Regression","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:15:36.947914Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/2505.22502"},"observation_digest":"sha256:d41d0773890ba7e680b0727c32cf69b7e5ea09ecd22fce21701860acbf3ddd0b","observation_id":"211ee424-5b2c-40b0-a697-b066df62bbae","resolution":{"observed_at":"2026-08-07T13:15:36.947914Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-08-03T13:34:53.578576Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.24116","last_updated":"2026-07-01T15:57:21Z","snapshot_observed_at":"2026-08-14T15:28:10.430366Z","submitted_at":"2025-12-30T09:53:02Z","title":"Quantitative Understanding of PDF Fits and their Uncertainties","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T13:34:53.578576Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/2512.24116"},"observation_digest":"sha256:2c09a3ab95d565657c0fa4d5dad57f28d7f278cb8a33deb24681d368f1ae63c6","observation_id":"6b702e3d-ed15-450d-82e6-2ad9ceb3121d","resolution":{"observed_at":"2026-08-03T13:34:53.578576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":"1902.06720","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-07-02T22:47:26.170047Z","title":"Wide neural networks of any depth evolv e as linear models under gradient descent","venue":null,"work_id":"c89ee0d8-2737-411e-bfc6-57db871c9acf","year":2020},"citing_paper":{"arxiv_id":"2605.28585","last_updated":"2026-05-27T15:09:02Z","snapshot_observed_at":"2026-08-07T06:12:39.413721Z","submitted_at":"2026-05-27T15:09:02Z","title":"Outer-Momentum Restarting in High-Dimensional Two-Phase Optimization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-29T13:31:23.664332Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/2605.28585"},"observation_digest":"sha256:6573f742406a43e6ec021aa3d6f5c22c104f4ba823658322641a05ab6b772b93","observation_id":"a58d14a6-3086-4fb1-b4d5-4e1d85ecc7c9","resolution":{"observed_at":"2026-06-29T13:33:27.943370Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":"1902.06720","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-07-02T22:47:26.170047Z","title":"Wide neural networks of any depth evolv e as linear models under gradient descent","venue":null,"work_id":"c89ee0d8-2737-411e-bfc6-57db871c9acf","year":2020},"citing_paper":{"arxiv_id":"2606.08316","last_updated":"2026-06-06T20:01:31Z","snapshot_observed_at":"2026-08-12T06:29:56.649880Z","submitted_at":"2026-06-06T20:01:31Z","title":"Some Inverse Problems in Particle Physics","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-27T18:38:49.963266Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/2606.08316"},"observation_digest":"sha256:66e5955c984b72a59fffa62e9c74870c5867dbc2bbf9ceefbb667e3796dfb969","observation_id":"a73b0343-0c7a-4784-b010-6e2376458c4e","resolution":{"observed_at":"2026-07-02T22:47:26.171522Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":"1902.06720","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-07-02T22:47:26.170047Z","title":"Wide neural networks of any depth evolv e as linear models under gradient descent","venue":null,"work_id":"c89ee0d8-2737-411e-bfc6-57db871c9acf","year":2020},"citing_paper":{"arxiv_id":"2606.30831","last_updated":"2026-07-23T18:53:12Z","snapshot_observed_at":"2026-08-04T02:09:09.481541Z","submitted_at":"2026-06-29T19:01:43Z","title":"Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-01T01:42:14.145227Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/2606.30831"},"observation_digest":"sha256:ff62925e50a0a8796761a8a626e22f3884a93cebf49625de8008ed7a07d8ead5","observation_id":"1d7f499b-3882-4e7a-81e8-47d929529bdc","resolution":{"observed_at":"2026-07-01T12:55:43.888929Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-08-02T09:36:50.510084Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.30831","last_updated":"2026-07-23T18:53:12Z","snapshot_observed_at":"2026-08-04T02:09:09.481541Z","submitted_at":"2026-06-29T19:01:43Z","title":"Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T09:36:50.510084Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/2606.30831"},"observation_digest":"sha256:08b03592bb668599b58297474a3a384ae03816278c14076b178424a5f1f676ba","observation_id":"2d142f73-3175-44f7-b782-48919a9600dd","resolution":{"observed_at":"2026-08-02T09:36:50.510084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.06720","snapshot_observed_at":"2026-07-12T06:14:03.658427Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.02905","last_updated":"2026-07-03T03:04:12Z","snapshot_observed_at":"2026-08-07T12:25:44.783974Z","submitted_at":"2026-07-03T03:04:12Z","title":"Pre-Strings Lectures on Artificial Intelligence","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-12T06:14:03.658427Z"},"links":{"cited_paper":"/paper/1902.06720","citing_paper":"/paper/2607.02905"},"observation_digest":"sha256:0fc02960bfba09431ab9b6d30570c60bd07a9f5ab3f63c805246c32298f60edf","observation_id":"d9b093b9-3943-4bba-846d-131ffef317d6","resolution":{"observed_at":"2026-07-12T06:14:03.658427Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1902.06720/citation-record","integrity":"/paper/1902.06720/integrity","json":"/paper/1902.06720/citation-record.json","paper":"/paper/1902.06720"},"outbound":[],"paper":{"arxiv_id":"1902.06720","last_updated":"2019-12-08T06:02:33Z","latest_version":4,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-14T17:14:47.330773Z","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 13 inbound Pith citation observations for arXiv:1902.06720."}