{"as_of":"2026-08-10T01:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:51b78534f01900d71368ce68ea382bb2104e5204aae78ccd5f3d5150f940345a","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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":"2026-08-03T23:39:20.921704Z","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":"2026-07-02T16:47:10.316436Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2002.10376","last_updated":"2020-02-24T17:08:24Z","snapshot_observed_at":"2026-08-09T20:05:00.942919Z","submitted_at":"2020-02-24T17:08:24Z","title":"The Two Regimes of Deep Network Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.10376","snapshot_observed_at":"2026-08-03T23:39:20.921704Z","title":"Sparse upcycling: Training mixture-of-experts from dense checkpoints","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2511.04981","last_updated":"2026-06-01T03:01:47Z","snapshot_observed_at":"2026-08-03T23:39:17.439120Z","submitted_at":"2025-11-07T04:56:45Z","title":"Scaling depth capacity via zero/one-layer model expansion","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-03T23:39:20.921704Z"},"links":{"cited_paper":"/paper/2002.10376","citing_paper":"/paper/2511.04981"},"observation_digest":"sha256:cc765b34c9068c832ad47b99b5b120c80b58bf6e3c7fc2296fbdaa4258a44a8e","observation_id":"fb70ff31-cc98-45f8-b3e6-9251e85f40ad","resolution":{"observed_at":"2026-08-03T23:39:20.921704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.10376","last_updated":"2020-02-24T17:08:24Z","snapshot_observed_at":"2026-08-09T20:05:00.942919Z","submitted_at":"2020-02-24T17:08:24Z","title":"The Two Regimes of Deep Network Training","version":1},"cited_work":{"arxiv_id":"2002.10376","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.10376","snapshot_observed_at":"2026-07-02T16:47:10.316436Z","title":"The two regimes of deep network training","venue":null,"work_id":"400bc077-aad3-422c-abcc-77c5ffa1915c","year":2002},"citing_paper":{"arxiv_id":"2603.10079","last_updated":"2026-04-13T13:15:13Z","snapshot_observed_at":"2026-08-02T23:21:16.952968Z","submitted_at":"2026-03-10T09:27:17Z","title":"Large Spikes in Stochastic Gradient Descent: A Large-Deviations View","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-15T13:30:04.366752Z"},"links":{"cited_paper":"/paper/2002.10376","citing_paper":"/paper/2603.10079"},"observation_digest":"sha256:603e6cd91838e194af1c17ed4a5fb98842d752eba573135e991a1b5dc065d416","observation_id":"af4ae74f-eb05-4c89-b61c-2aa611e68bdf","resolution":{"observed_at":"2026-05-15T13:30:51.012421Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.10376","last_updated":"2020-02-24T17:08:24Z","snapshot_observed_at":"2026-08-09T20:05:00.942919Z","submitted_at":"2020-02-24T17:08:24Z","title":"The Two Regimes of Deep Network Training","version":1},"cited_work":{"arxiv_id":"2002.10376","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.10376","snapshot_observed_at":"2026-07-02T16:47:10.316436Z","title":"The two regimes of deep network training","venue":null,"work_id":"400bc077-aad3-422c-abcc-77c5ffa1915c","year":2002},"citing_paper":{"arxiv_id":"2606.07495","last_updated":"2026-06-05T17:49:19Z","snapshot_observed_at":"2026-08-05T16:38:31.972892Z","submitted_at":"2026-06-05T17:49:19Z","title":"Second-Order Path Kernel Interpolation Formulas in Machine Learning","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-06-27T22:20:15.074286Z"},"links":{"cited_paper":"/paper/2002.10376","citing_paper":"/paper/2606.07495"},"observation_digest":"sha256:834f3a8d0aa4a70c088fe1bbb9e9961c74019c2d7be2eb3285678e2cbc7ea454","observation_id":"0edbd5d2-92bf-425f-9cde-d1198c528388","resolution":{"observed_at":"2026-07-02T16:47:10.317683Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2002.10376/citation-record","integrity":"/paper/2002.10376/integrity","json":"/paper/2002.10376/citation-record.json","paper":"/paper/2002.10376"},"outbound":[],"paper":{"arxiv_id":"2002.10376","last_updated":"2020-02-24T17:08:24Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T20:05:00.942919Z","submitted_at":"2020-02-24T17:08:24Z","title":"The Two Regimes of Deep Network Training"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2002.10376."}