{"as_of":"2026-08-18T13:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5ec0768c14a5b648e070ab18c25a8b2a183c93d7cb2b81f63fad228ca2d83c79","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":9,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":9,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":9,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T06:03:00.601341Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":48,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","snapshot_observed_at":"2026-08-14T16:39:49.310730Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double Descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.01897","snapshot_observed_at":"2026-08-11T18:53:10.365287Z","title":"Optimal regu- larization can mitigate double descent","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-14T05:01:05.739672Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.365287Z"},"links":{"cited_paper":"/paper/2003.01897","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:05d58dbe0eb4f5551aaf188c05e2a6089017a351965c8c2d160b4605cbd46048","observation_id":"2f6ef4e8-bd5f-4d7c-ae12-595303d66d7a","resolution":{"observed_at":"2026-08-11T18:53:10.365287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","snapshot_observed_at":"2026-08-14T16:39:49.310730Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double Descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.01897","snapshot_observed_at":"2026-08-16T06:03:00.601341Z","title":"and Ma, T","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.19351","last_updated":"2025-04-27T20:29:24Z","snapshot_observed_at":"2026-08-16T05:52:26.569968Z","submitted_at":"2025-04-27T20:29:24Z","title":"The Double Descent Behavior in Two Layer Neural Network for Binary Classification","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T06:03:00.601341Z"},"links":{"cited_paper":"/paper/2003.01897","citing_paper":"/paper/2504.19351"},"observation_digest":"sha256:f481357c7fc60b5b3711c62c2d4fa5e80bb8f0a800bb911091c6f0dcead4fa2b","observation_id":"ab2b6936-ca4d-4deb-8f71-96921cb459f2","resolution":{"observed_at":"2026-08-16T06:03:00.601341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","snapshot_observed_at":"2026-08-14T16:39:49.310730Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double Descent","version":2},"cited_work":{"arxiv_id":"2003.01897","doi":"10.48550/arxiv.2003.01897","metadata_source":"arxiv_reference","pith_arxiv_id":"2003.01897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Optimal regularization can mitigate double descent","venue":"arXiv (Cornell University)","work_id":"2e21a9b3-1f50-4bc3-97c0-569582aa8d3a","year":2003},"citing_paper":{"arxiv_id":"2506.07298","last_updated":"2026-04-24T00:35:40Z","snapshot_observed_at":"2026-08-11T18:19:18.277777Z","submitted_at":"2025-06-08T21:49:38Z","title":"Pre-trained Large Language Models Learn Hidden Markov Models In-context","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-19T10:34:40.987583Z"},"links":{"cited_paper":"/paper/2003.01897","citing_paper":"/paper/2506.07298"},"observation_digest":"sha256:d1e84263c3d5d69c0442593e13eaab107deef949bfb1d755661115ed0052e784","observation_id":"b4979844-d73d-4a96-abf7-481c6f40a148","resolution":{"observed_at":"2026-05-19T10:37:15.052151Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","snapshot_observed_at":"2026-08-14T16:39:49.310730Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double Descent","version":2},"cited_work":{"arxiv_id":"2003.01897","doi":"10.48550/arxiv.2003.01897","metadata_source":"arxiv_reference","pith_arxiv_id":"2003.01897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Optimal regularization can mitigate double descent","venue":"arXiv (Cornell University)","work_id":"2e21a9b3-1f50-4bc3-97c0-569582aa8d3a","year":2003},"citing_paper":{"arxiv_id":"2508.17412","last_updated":"2026-04-18T06:49:55Z","snapshot_observed_at":"2026-07-06T22:17:21.314143Z","submitted_at":"2025-08-24T15:34:17Z","title":"A Ridge Too Far: Correcting Over-Shrinkage via Negative Regularization","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-18T21:01:34.347413Z"},"links":{"cited_paper":"/paper/2003.01897","citing_paper":"/paper/2508.17412"},"observation_digest":"sha256:a4a5dcf1856c88a823d21d5c19810b5062ee1bb4ebed38e383bf879ab86bf86a","observation_id":"c849ba4f-fc9c-4505-ac4c-57efd31bdf55","resolution":{"observed_at":"2026-05-18T21:01:50.908680Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","snapshot_observed_at":"2026-08-14T16:39:49.310730Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double Descent","version":2},"cited_work":{"arxiv_id":"2003.01897","doi":"10.48550/arxiv.2003.01897","metadata_source":"arxiv_reference","pith_arxiv_id":"2003.01897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Optimal regularization can mitigate double descent","venue":"arXiv (Cornell University)","work_id":"2e21a9b3-1f50-4bc3-97c0-569582aa8d3a","year":2003},"citing_paper":{"arxiv_id":"2604.17202","last_updated":"2026-04-19T02:09:37Z","snapshot_observed_at":"2026-08-13T16:50:05.278380Z","submitted_at":"2026-04-19T02:09:37Z","title":"Double Descent in Quantum Kernel Ridge Regression","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T06:42:30.100063Z"},"links":{"cited_paper":"/paper/2003.01897","citing_paper":"/paper/2604.17202"},"observation_digest":"sha256:84a4918aad973597769c3c7c99eed9a005fd10683ca88c40477fd552bbaaf204","observation_id":"4405f323-b7b7-4708-b1cd-e2b0a1ff6a63","resolution":{"observed_at":"2026-05-10T06:46:37.376896Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","snapshot_observed_at":"2026-08-14T16:39:49.310730Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double Descent","version":2},"cited_work":{"arxiv_id":"2003.01897","doi":"10.48550/arxiv.2003.01897","metadata_source":"arxiv_reference","pith_arxiv_id":"2003.01897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Optimal regularization can mitigate double descent","venue":"arXiv (Cornell University)","work_id":"2e21a9b3-1f50-4bc3-97c0-569582aa8d3a","year":2003},"citing_paper":{"arxiv_id":"2605.18022","last_updated":"2026-05-18T08:12:45Z","snapshot_observed_at":"2026-08-14T17:36:51.826375Z","submitted_at":"2026-05-18T08:12:45Z","title":"Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-20T12:27:56.774581Z"},"links":{"cited_paper":"/paper/2003.01897","citing_paper":"/paper/2605.18022"},"observation_digest":"sha256:9e611800c428838671c2266fcdc7243498436d819af7ade3261a7c4ed1a99b2e","observation_id":"c53bbe3c-16f0-40ae-a679-4f3b2c094fda","resolution":{"observed_at":"2026-05-20T12:28:16.629714Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","snapshot_observed_at":"2026-08-14T16:39:49.310730Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double Descent","version":2},"cited_work":{"arxiv_id":"2003.01897","doi":"10.48550/arxiv.2003.01897","metadata_source":"arxiv_reference","pith_arxiv_id":"2003.01897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Optimal regularization can mitigate double descent","venue":"arXiv (Cornell University)","work_id":"2e21a9b3-1f50-4bc3-97c0-569582aa8d3a","year":2003},"citing_paper":{"arxiv_id":"2606.10089","last_updated":"2026-06-08T19:16:32Z","snapshot_observed_at":"2026-08-12T09:27:24.769295Z","submitted_at":"2026-06-08T19:16:32Z","title":"A Theory on Flow Matching with Neural Networks","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-06-27T16:59:34.084575Z"},"links":{"cited_paper":"/paper/2003.01897","citing_paper":"/paper/2606.10089"},"observation_digest":"sha256:8fc57761ba94277a4cdfcddb0135b2a9c86c9d714ac8ab6842ebeffecfd37492","observation_id":"958f3099-5cf2-482f-b92f-b0eab4984241","resolution":{"observed_at":"2026-07-03T00:47:30.918048Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","snapshot_observed_at":"2026-08-14T16:39:49.310730Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double Descent","version":2},"cited_work":{"arxiv_id":"2003.01897","doi":"10.48550/arxiv.2003.01897","metadata_source":"arxiv_reference","pith_arxiv_id":"2003.01897","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Optimal regularization can mitigate double descent","venue":"arXiv (Cornell University)","work_id":"2e21a9b3-1f50-4bc3-97c0-569582aa8d3a","year":2003},"citing_paper":{"arxiv_id":"2606.31110","last_updated":"2026-06-30T04:15:23Z","snapshot_observed_at":"2026-08-02T08:26:02.836428Z","submitted_at":"2026-06-30T04:15:23Z","title":"Explaining Machine Learning and Memorization with Statistical Mechanics","version":1},"reference_index":162,"source":"pdf_text","source_observed_at":"2026-07-01T06:04:52.621553Z"},"links":{"cited_paper":"/paper/2003.01897","citing_paper":"/paper/2606.31110"},"observation_digest":"sha256:20731e6df9bed02e0707b53dc44816e9bd4bc54cd05b7b97d4dcc0f515de7499","observation_id":"d1670583-2b7c-42f1-84bc-4fd1765230b1","resolution":{"observed_at":"2026-07-01T06:05:28.869760Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","snapshot_observed_at":"2026-08-14T16:39:49.310730Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double Descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.01897","snapshot_observed_at":"2026-08-02T00:50:35.581710Z","title":"arXiv preprint arXiv:2003.01897 , year=","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.14894","last_updated":"2026-07-16T12:11:06Z","snapshot_observed_at":"2026-08-18T00:09:26.004912Z","submitted_at":"2026-07-16T12:11:06Z","title":"Domain Adaptation of Mismatched Proximal Denoiser for Plug-and-Play Image Reconstruction","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-02T00:50:35.581710Z"},"links":{"cited_paper":"/paper/2003.01897","citing_paper":"/paper/2607.14894"},"observation_digest":"sha256:20275cb37095e5416dbbff3a71652009e57c5316acbd0a24a0a73d4e71b2ed73","observation_id":"c050cc65-6988-462d-973b-07f9fe98b947","resolution":{"observed_at":"2026-08-02T00:50:35.581710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2003.01897/citation-record","integrity":"/paper/2003.01897/integrity","json":"/paper/2003.01897/citation-record.json","paper":"/paper/2003.01897"},"outbound":[],"paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T16:39:49.310730Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double 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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 9 inbound Pith citation observations for arXiv:2003.01897."}