{"as_of":"2026-08-10T03:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d237809180970486e3902945384e0c4b9d60f0fa2a5aa88e73e4972bafe7ad66","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":"2026-08-08T05:44:07.620866Z","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":"2026-07-03T12:28:07.393013Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1803.02865","last_updated":"2020-11-19T20:31:14Z","snapshot_observed_at":"2026-08-10T03:16:47.943859Z","submitted_at":"2018-03-07T20:30:35Z","title":"WNGrad: Learn the Learning Rate in Gradient Descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.02865","snapshot_observed_at":"2026-08-08T05:44:07.620866Z","title":"Wngrad: Learn the learnin g rate in gradient descent,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.08308","last_updated":"2025-02-12T11:22:23Z","snapshot_observed_at":"2026-08-09T19:44:45.202487Z","submitted_at":"2025-02-12T11:22:23Z","title":"prunAdag: an adaptive pruning-aware gradient method","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-08T05:44:07.620866Z"},"links":{"cited_paper":"/paper/1803.02865","citing_paper":"/paper/2502.08308"},"observation_digest":"sha256:15fae1ed5bec7d5fd0193913260165322939f6633669f25f9b80de5053272622","observation_id":"fce8ebf8-de76-4af6-adb5-88c91bea043c","resolution":{"observed_at":"2026-08-08T05:44:07.620866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.02865","last_updated":"2020-11-19T20:31:14Z","snapshot_observed_at":"2026-08-10T03:16:47.943859Z","submitted_at":"2018-03-07T20:30:35Z","title":"WNGrad: Learn the Learning Rate in Gradient Descent","version":2},"cited_work":{"arxiv_id":"1803.02865","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1803.02865","snapshot_observed_at":"2026-07-03T12:28:07.393013Z","title":"WNGrad: Lear n the learning rate in gradient descent","venue":null,"work_id":"4e0abca1-a7b4-4af2-87a2-1f6972080a3a","year":2018},"citing_paper":{"arxiv_id":"2604.17423","last_updated":"2026-05-01T14:46:49Z","snapshot_observed_at":"2026-08-02T20:20:49.115675Z","submitted_at":"2026-04-19T13:07:51Z","title":"A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad, Shampoo and Muo","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-10T07:19:59.335184Z"},"links":{"cited_paper":"/paper/1803.02865","citing_paper":"/paper/2604.17423"},"observation_digest":"sha256:5805b79ba17df0dc38bf23e176b5a64dc55254f3ed1ea1cf6ecd8f3c549b4654","observation_id":"da049918-e738-43d5-8bbc-15a76c6ed5e2","resolution":{"observed_at":"2026-05-10T07:26:59.865849Z","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":"1803.02865","last_updated":"2020-11-19T20:31:14Z","snapshot_observed_at":"2026-08-10T03:16:47.943859Z","submitted_at":"2018-03-07T20:30:35Z","title":"WNGrad: Learn the Learning Rate in Gradient Descent","version":2},"cited_work":{"arxiv_id":"1803.02865","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1803.02865","snapshot_observed_at":"2026-07-03T12:28:07.393013Z","title":"WNGrad: Lear n the learning rate in gradient descent","venue":null,"work_id":"4e0abca1-a7b4-4af2-87a2-1f6972080a3a","year":2018},"citing_paper":{"arxiv_id":"2606.11791","last_updated":"2026-06-10T08:23:37Z","snapshot_observed_at":"2026-08-09T06:32:13.556505Z","submitted_at":"2026-06-10T08:23:37Z","title":"bAdag: an adaptive block coordinate gradient method for smooth nonconvex functions","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-06-27T09:00:34.960719Z"},"links":{"cited_paper":"/paper/1803.02865","citing_paper":"/paper/2606.11791"},"observation_digest":"sha256:dab7a3c24f0a4b7fec4e5f8a72fa564811c04c22ae49a76d64a8c5140abee5b6","observation_id":"09ee4e5a-1fa8-4f94-8e12-79989842b1f8","resolution":{"observed_at":"2026-07-03T12:28:07.409844Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/1803.02865/citation-record","integrity":"/paper/1803.02865/integrity","json":"/paper/1803.02865/citation-record.json","paper":"/paper/1803.02865"},"outbound":[],"paper":{"arxiv_id":"1803.02865","last_updated":"2020-11-19T20:31:14Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-10T03:16:47.943859Z","submitted_at":"2018-03-07T20:30:35Z","title":"WNGrad: Learn the Learning Rate in 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":"2026-08-09T06:31:02.800959+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:1803.02865."}