{"as_of":"2026-08-15T00:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fff8eafb729e41aabc76aabd44e44c3f8b143c5c50585f6fbfa2d4863364792b","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":"2026-08-14T06:32:32.682623+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":"2026-08-11T13:28:28.959819Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-08T11:46:48.196141Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.03496","last_updated":"2024-10-04T18:49:17Z","snapshot_observed_at":"2026-08-13T16:35:02.854755Z","submitted_at":"2024-02-05T20:15:19Z","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","version":10},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03496","snapshot_observed_at":"2026-08-11T13:28:28.959819Z","title":"Can we remove the square-root in adaptive gradient methods? a second-order perspective","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13148","last_updated":"2025-02-21T18:59:37Z","snapshot_observed_at":"2026-08-14T17:31:00.554747Z","submitted_at":"2024-12-17T18:13:18Z","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-11T13:28:28.959819Z"},"links":{"cited_paper":"/paper/2402.03496","citing_paper":"/paper/2412.13148"},"observation_digest":"sha256:c2f1480f1e8a294710688406efb78876953cbb9d8c2c551c5ea43dca18cdf895","observation_id":"b1c10969-318b-4b0e-9838-ba034372db6e","resolution":{"observed_at":"2026-08-11T13:28:28.959819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03496","last_updated":"2024-10-04T18:49:17Z","snapshot_observed_at":"2026-08-13T16:35:02.854755Z","submitted_at":"2024-02-05T20:15:19Z","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","version":10},"cited_work":{"arxiv_id":"2402.03496","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.03496","snapshot_observed_at":"2026-08-08T11:46:48.196141Z","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective","venue":"cs.LG","work_id":"d412d6ae-5455-422b-8e10-bd29ba3b7dba","year":2024},"citing_paper":{"arxiv_id":"2502.07752","last_updated":"2025-02-20T18:48:58Z","snapshot_observed_at":"2026-08-14T22:25:07.493744Z","submitted_at":"2025-02-11T18:27:19Z","title":"Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-08T11:46:47.689130Z"},"links":{"cited_paper":"/paper/2402.03496","citing_paper":"/paper/2502.07752"},"observation_digest":"sha256:675d501168c0717085f59500e9e63fc3f0ce810b869c4915eb9fe0faa40bd4d5","observation_id":"98d71768-a389-41a1-9b93-9794e8b2545b","resolution":{"observed_at":"2026-08-08T11:46:48.200943Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.03496/citation-record","integrity":"/paper/2402.03496/integrity","json":"/paper/2402.03496/citation-record.json","paper":"/paper/2402.03496"},"outbound":[],"paper":{"arxiv_id":"2402.03496","last_updated":"2024-10-04T18:49:17Z","latest_version":10,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T16:35:02.854755Z","submitted_at":"2024-02-05T20:15:19Z","title":"Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2402.03496."}