{"as_of":"2026-08-19T12:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ebb78e645dfc0e8c19feaca279afebf6444d6c044bc9c4e0de2eb4f6d6257b29","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T14:17:37.064891Z","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":"2026-05-21T17:34:17.263009Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2206.15144","last_updated":"2022-06-30T09:24:02Z","snapshot_observed_at":"2026-08-16T16:49:18.035166Z","submitted_at":"2022-06-30T09:24:02Z","title":"Neural Networks can Learn Representations with Gradient Descent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.15144","snapshot_observed_at":"2026-08-06T14:17:37.064891Z","title":"Lee, and Mahdi Soltanolkotabi","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.19680","last_updated":"2025-07-25T21:19:37Z","snapshot_observed_at":"2026-08-16T06:57:12.804004Z","submitted_at":"2025-07-25T21:19:37Z","title":"Feature learning is decoupled from generalization in high capacity neural networks","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T14:17:37.064891Z"},"links":{"cited_paper":"/paper/2206.15144","citing_paper":"/paper/2507.19680"},"observation_digest":"sha256:e4382b13bc2805b9d49fbcb6f3e7aa0ef29061db8ee96c6fe856c58030f5a91b","observation_id":"a8fea7c1-cb6b-4a1d-a376-59941a79baec","resolution":{"observed_at":"2026-08-06T14:17:37.064891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.15144","last_updated":"2022-06-30T09:24:02Z","snapshot_observed_at":"2026-08-16T16:49:18.035166Z","submitted_at":"2022-06-30T09:24:02Z","title":"Neural Networks can Learn Representations with Gradient Descent","version":1},"cited_work":{"arxiv_id":"2206.15144","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.15144","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"[EHN96] Heinz Werner Engl, Martin Hanke, and Andreas Neubauer.Regularization of Inverse Problems, volume 375 ofMathematics and Its Applications","venue":null,"work_id":"0499f534-6174-4632-a5e2-ee91b87a8023","year":null},"citing_paper":{"arxiv_id":"2512.14473","last_updated":"2026-05-15T17:46:33Z","snapshot_observed_at":"2026-08-13T04:20:21.706578Z","submitted_at":"2025-12-16T15:01:51Z","title":"Sharp convergence rates for Spectral methods via the feature space decomposition method","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-21T17:33:12.942867Z"},"links":{"cited_paper":"/paper/2206.15144","citing_paper":"/paper/2512.14473"},"observation_digest":"sha256:7f365b2edcb48d91da9af6409a90dafd91240b911694b1dd740a877c83434826","observation_id":"90365dae-d0a8-4edd-b6c5-871e3cd46f8d","resolution":{"observed_at":"2026-05-21T17:34:17.265176Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2206.15144/citation-record","integrity":"/paper/2206.15144/integrity","json":"/paper/2206.15144/citation-record.json","paper":"/paper/2206.15144"},"outbound":[],"paper":{"arxiv_id":"2206.15144","last_updated":"2022-06-30T09:24:02Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T16:49:18.035166Z","submitted_at":"2022-06-30T09:24:02Z","title":"Neural Networks can Learn Representations with 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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2206.15144."}