{"as_of":"2026-08-18T05:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f3a89241fbe85a94fc143172d6fca81800291393a3fdcc64aec133372ea1c8d0","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":"2026-08-16T10:30:08.782584Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2504.18207/citation-record","integrity":"/paper/2504.18207/integrity","json":"/paper/2504.18207/citation-record.json","paper":"/paper/2504.18207"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.231904Z","title":"Stability and generalization of learning algorithms that converge to global 8 optima","venue":null,"work_id":"0b3b2b2d-08bf-4833-a743-e6725beb89fc","year":2018},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.654722Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:96bc227ae2fbab6d08d5ab0c19a662f0419b51bd1cb20d0ff64f8094da113c27","observation_id":"a64816cf-7d4e-49ae-ae0d-fff2602b06f0","resolution":{"observed_at":"2026-08-16T10:30:09.237777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.215639Z","title":"Approximation by superpositions of a sig- moidal function","venue":null,"work_id":"b6304d5c-5921-481f-8996-c72ef77f9102","year":1989},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.659871Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:f5a581d7dadbb2325e9bdc8ecdd68cea190de4daf197085aed6c1d493fd16917","observation_id":"7e62e6ee-df9d-4423-8370-5fb33fda475b","resolution":{"observed_at":"2026-08-16T10:30:09.220842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.200854Z","title":null,"venue":null,"work_id":"772a734c-ff7a-45b2-b27a-b356041cb5f2","year":2009},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.664746Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:9185347bc10e91809d74f17039d5f346a335c7c5fbe4a3bed17597037bb4402f","observation_id":"3f17f610-b158-4711-87cc-70b803b83544","resolution":{"observed_at":"2026-08-16T10:30:09.205413Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.186412Z","title":"Spectral bias in practice: The role of function fre- quency in generalization","venue":null,"work_id":"4435caa2-e891-463e-9f73-362eddf314e3","year":2022},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.669329Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:c532281c071a9fe620c6c2bdd1d2307fcf1bf760eaa7074bf11dd143f4f7c1c1","observation_id":"275765a5-b62b-49fa-950a-045e3250449f","resolution":{"observed_at":"2026-08-16T10:30:09.191065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.171448Z","title":"Optimal shrinkage of singular values","venue":null,"work_id":"c89f23a3-461c-43f5-9649-d976da1efd30","year":2017},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.674868Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:8c5fac2d6d8018acd2234d2cfeced44163b9d4b8381bf7f06582938f903f62d7","observation_id":"03b91e58-7d81-4335-b7de-8c20535fb7ed","resolution":{"observed_at":"2026-08-16T10:30:09.176075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.156406Z","title":"Stochastic training is not nec- essary for generalization","venue":null,"work_id":"cefa7b8c-25aa-4584-9d04-fe38a3cf60ba","year":2022},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.679709Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:df1078f4f8eb657f57e07de066fe05a4ff995d40f829db6b538778223c7fa3ec","observation_id":"d6e3c413-3e88-4406-af69-ec5a6682718d","resolution":{"observed_at":"2026-08-16T10:30:09.161443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:08.685172Z","title":"Train faster, generalize better: Stability of stochastic gradient descent","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.685172Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:f66545b298b22b5142a605121c77a0570b2e316a26f47ffa282bfbd7573bf200","observation_id":"e7827710-4ece-4925-b0d4-cf1aaf6ee72c","resolution":{"observed_at":"2026-08-16T10:30:08.685172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.02903","last_updated":"2023-10-04T15:07:57Z","snapshot_observed_at":"2026-07-06T08:35:23.114586Z","submitted_at":"2019-11-07T13:48:15Z","title":"How Implicit Regularization of ReLU Neural Networks Characterizes the Learned Function -- Part I: the 1-D Case of Two Layers with Random First Layer","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.02903","snapshot_observed_at":"2026-08-16T10:30:08.689978Z","title":"How im- plicit regularization of relu neural networks characterizes the learned function–part i: the 1-d case of two layers with ran- dom first layer","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.689978Z"},"links":{"cited_paper":"/paper/1911.02903","citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:242c535851432fe872d06d4303e977df02ec639d66892f9e54fc2020813b297d","observation_id":"7c064db6-6c01-4510-83e2-93626671bc41","resolution":{"observed_at":"2026-08-16T10:30:08.689978Z","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":"2026-08-16T10:30:09.131005Z","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","venue":null,"work_id":"18a6957b-91b7-4802-8c90-128e674d87b0","year":2017},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.695000Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:b08c848321388793f1e8f4abaa9cbf93e21a093822459b4700e1ed38907e1e76","observation_id":"7085e4ef-69a3-4ef5-9041-8a152ec5b8b6","resolution":{"observed_at":"2026-08-16T10:30:09.135875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.116129Z","title":"Neu- ral tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":"23a46df2-9940-47d0-8502-adbe37e0e126","year":2018},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.699894Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:bbab990e3fe65bd49166b5d241b8d240496da6674b010b4f6596fabd122a1469","observation_id":"804cee8c-df77-4973-82e2-40e620a4951c","resolution":{"observed_at":"2026-08-16T10:30:09.120819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.100425Z","title":"A note on the use of principal components in regression","venue":null,"work_id":"cd26323b-054d-4fda-90de-8af139627138","year":1982},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.704604Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:d7bdcccdf14ba602fba1788dbf9948721527f24cf6b3d765d739b5f524839c6c","observation_id":"246ead73-152f-4e3e-a526-06accb66910e","resolution":{"observed_at":"2026-08-16T10:30:09.105496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.085741Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":"e424b855-7fa1-4946-8fed-98783b1c251f","year":2012},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.709247Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:c7d62b87cfe0e4577f6d71f5ce8216f2f282a408d3c14bb090b39d00cc465b1a","observation_id":"4b8a08c5-a0ac-435e-8c07-64521ec4d58d","resolution":{"observed_at":"2026-08-16T10:30:09.090388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.070456Z","title":"Beyond lipschitz: Sharp generalization and excess risk bounds for full-batch gd","venue":null,"work_id":"9bcc7656-0dd1-4f04-bc2c-a685122f81b9","year":null},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.713510Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:e538ee85b6c7f553a54bf774d4c1ddc5002764f1298b2ebb31fad94b41b6fe81","observation_id":"16de50e3-24f9-4134-9008-f151f952bf4d","resolution":{"observed_at":"2026-08-16T10:30:09.075503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.054971Z","title":"Beyond periodicity: Towards a unifying framework for activations in coordinate- mlps","venue":null,"work_id":"a02f2191-1e08-4a4c-90e2-fe92cfc2e11a","year":2022},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.718410Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:81d2887c3a184105e65e43b754d94d607f5f66eb0430a685e890cf2dab3e5cbd","observation_id":"8899c65a-dd3a-4ed3-874d-83e74c68e2ff","resolution":{"observed_at":"2026-08-16T10:30:09.059660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.039043Z","title":"Smoothing by spline functions","venue":null,"work_id":"e231f7ff-e5ec-4a62-99e2-1f6ae7ce0023","year":1967},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.722922Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:610517169863e51e40ce93f0ef963e6ff043a282ca30aae1b78745a7c99167ec","observation_id":"6d80c98c-c76a-480b-8b7b-879c89d3bcd3","resolution":{"observed_at":"2026-08-16T10:30:09.044344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.023673Z","title":"A sam- pling theory perspective on activations for implicit neural representations","venue":null,"work_id":"2ac10f23-08e9-4cb7-af08-6be81bf015a3","year":null},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.727191Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:648bd57de57a181ef5d5ac209708b5e309bb3b1a15ae48f5b4506d5376c8b133","observation_id":"ebf585bc-e064-4ba7-851c-4c43f7732367","resolution":{"observed_at":"2026-08-16T10:30:09.028413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:09.008038Z","title":"Communication in the presence of noise","venue":null,"work_id":"d35cab66-3eef-4717-a338-335282613fcf","year":1949},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.731767Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:9c40fd4b3271b755d6503b90c88eba7cba1e497265620eee2704aea3b049087a","observation_id":"bf5cbe57-aca4-476f-b1e7-20a4388b8456","resolution":{"observed_at":"2026-08-16T10:30:09.012544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:08.993098Z","title":"Implicit neural representa- tions with periodic activation functions","venue":null,"work_id":"21cdde5c-9f42-4221-a1bb-f19f0aa2e495","year":2020},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.736243Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:a2ca12d7ce006e3bd9b02b9662f1cf2406a7a97bdc64aa5e20b83366f67d38bb","observation_id":"f3818ca9-db27-4abb-8594-1e18f17e0c60","resolution":{"observed_at":"2026-08-16T10:30:08.997872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:08.977290Z","title":"The implicit bias of gradi- ent descent on separable data","venue":null,"work_id":"0b75cb44-b9ae-4098-b7d8-a0a051c6293d","year":2018},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.740694Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:9722374d0c7b455b9abf5b93f55140feb11124a6997758137b28bf6256c655be","observation_id":"0f1ca6ee-a80f-4cca-acdd-874e94b1e2c3","resolution":{"observed_at":"2026-08-16T10:30:08.982521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:08.961543Z","title":"Fourier features let networks learn high frequency functions in low dimen- sional domains","venue":null,"work_id":"7e78ae3a-326a-4cf5-8448-d09bad5be584","year":2020},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.746009Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:a197d1fc1acd744a659b6cecc2da1ae2206a104fdb8d488a298f6668756c2bbf","observation_id":"f40c872c-3abf-42eb-82eb-2013630d03a3","resolution":{"observed_at":"2026-08-16T10:30:08.966584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:08.946213Z","title":"Sampling-50 years after shannon","venue":null,"work_id":"38ac4157-5736-42e1-9ea9-334e05841b59","year":2000},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.750695Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:ad251c6e5eaa097824d6114c5d5fa963c5361e2aa38616d15b2fc86e549e4efe","observation_id":"ce5a93c3-d1f8-49dd-80ba-158bf239b339","resolution":{"observed_at":"2026-08-16T10:30:08.950853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:08.755297Z","title":"Principles of risk minimization for learn- ing theory","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.755297Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:c6aefe2dca026437e72a3f0a38e53186b298c84f9c986a9fa897810994f38c34","observation_id":"293fc9ca-a1a1-476a-a192-e08acdfd1ab9","resolution":{"observed_at":"2026-08-16T10:30:08.755297Z","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":"2026-08-16T10:30:08.917939Z","title":"The “fourier” theory of the cardinal func- tion","venue":null,"work_id":"781f1896-c281-4d9a-828f-f861e3919538","year":1928},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.759536Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:2baaf434f027eca1573ca7973e541f76eefc4b0f2043cb94980001cde63997a5","observation_id":"efac4bde-15b1-4810-b270-3b77ad71aebe","resolution":{"observed_at":"2026-08-16T10:30:08.922909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:08.901981Z","title":"Gradient dynamics of shallow univariate relu networks","venue":null,"work_id":"54251663-ddc9-4828-bb1f-f67ba37fc58b","year":2019},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.764283Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:96f788e0f2cde00a9a8d54b1e25d08a38f8f704a4bb1f022d0e40f8dd635c56a","observation_id":"fcac2a27-0803-4445-96df-3fa10a2f270f","resolution":{"observed_at":"2026-08-16T10:30:08.906664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:08.885543Z","title":"A mathematical analysis of the motion coherence theory","venue":null,"work_id":"581b4071-bf7d-41a8-9fc9-2fc1a2f45270","year":1989},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.768763Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:920ac8fe2669c9761db516aec3f530c7a4881ef36d58e25025056bf2f21c0a50","observation_id":"63c8ab11-0ec2-4135-a43c-222cc543b133","resolution":{"observed_at":"2026-08-16T10:30:08.890784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:30:08.869660Z","title":"Understanding deep learning re- quires rethinking generalization","venue":null,"work_id":"43193e69-c028-4d14-bcad-79748f720828","year":2017},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.773228Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:70c7266190ce48c5dbc6e3d580dea80d561cf92863ff378b1a6cc1bab84c84f2","observation_id":"36d36d9d-051b-4600-8722-3909c3b02f65","resolution":{"observed_at":"2026-08-16T10:30:08.875029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.02561","last_updated":"2021-10-11T22:39:59Z","snapshot_observed_at":"2026-08-17T17:53:34.869661Z","submitted_at":"2021-07-06T12:04:04Z","title":"Rethinking Positional Encoding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.02561","snapshot_observed_at":"2026-08-16T10:30:08.777697Z","title":"Rethinking positional encoding","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.777697Z"},"links":{"cited_paper":"/paper/2107.02561","citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:f668267c708cddf7e3d53a1b2d22c758051d7d420bc73ba245203dca7c0efe2b","observation_id":"f6daf10a-7a06-43a9-9a18-0245d2be46de","resolution":{"observed_at":"2026-08-16T10:30:08.777697Z","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":"2026-08-16T10:30:08.850827Z","title":"Trading positional complexity vs deepness in coordinate networks","venue":null,"work_id":"233659cd-2f39-417a-8b49-7d5b5b92ea58","year":2022},"citing_paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T10:30:08.782584Z"},"links":{"citing_paper":"/paper/2504.18207"},"observation_digest":"sha256:daba8b3c9384e42be3f14a90592f0606fe541fa2477274aa20f258981ab115db","observation_id":"5595c28e-ea9a-4c7d-aec7-ee9ae904f157","resolution":{"observed_at":"2026-08-16T10:30:08.857993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.18207","last_updated":"2025-04-25T09:36:17Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T23:56:35.775907Z","submitted_at":"2025-04-25T09:36:17Z","title":"Gradient Descent as a Shrinkage Operator for Spectral Bias"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":23},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2504.18207."}