{"as_of":"2026-08-10T06:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b5466977ced6c3416a5b228139f458a9fd898e59755e0d431d79ee5aa08b84ff","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:35:00.591858Z","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":"2026-05-21T10:30:58.903033Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1912.03194","last_updated":"2020-10-23T08:07:04Z","snapshot_observed_at":"2026-08-02T08:10:10.416307Z","submitted_at":"2019-12-06T15:58:29Z","title":"Why are Adaptive Methods Good for Attention Models?","version":2},"cited_work":{"arxiv_id":"1912.03194","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1912.03194","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reddi, Sanjiv Kumar, and Suvrit Sra","venue":null,"work_id":"d83f1ea2-f71c-4f2f-a01b-45c5f7b78451","year":1912},"citing_paper":{"arxiv_id":"2003.00295","last_updated":"2021-09-08T23:37:17Z","snapshot_observed_at":"2026-07-06T09:01:12.515300Z","submitted_at":"2020-02-29T16:37:29Z","title":"Adaptive Federated Optimization","version":5},"reference_index":245,"source":"arxiv_source","source_observed_at":"2026-05-21T10:30:58.601351Z"},"links":{"cited_paper":"/paper/1912.03194","citing_paper":"/paper/2003.00295"},"observation_digest":"sha256:b838ae872e0acb6b305716cce1e3f5e7a2b6454a919b032527f48b4368af6dd5","observation_id":"aa39e3b4-8d9a-4070-8706-99af43b1858e","resolution":{"observed_at":"2026-05-21T10:30:58.904776Z","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":"1912.03194","last_updated":"2020-10-23T08:07:04Z","snapshot_observed_at":"2026-08-02T08:10:10.416307Z","submitted_at":"2019-12-06T15:58:29Z","title":"Why are Adaptive Methods Good for Attention Models?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.03194","snapshot_observed_at":"2026-08-06T17:35:00.591858Z","title":"Why are adaptive methods good for attention models?, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.10536","last_updated":"2025-07-14T17:57:08Z","snapshot_observed_at":"2026-08-10T00:25:46.079436Z","submitted_at":"2025-07-14T17:57:08Z","title":"On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T17:35:00.591858Z"},"links":{"cited_paper":"/paper/1912.03194","citing_paper":"/paper/2507.10536"},"observation_digest":"sha256:3b6ade2c5897125f590ec63a32f2852923c107f7b39b8497743999bd2bbce6cf","observation_id":"0351a6d9-9cd4-48a8-8d70-89e37877fdaf","resolution":{"observed_at":"2026-08-06T17:35:00.591858Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.03194","last_updated":"2020-10-23T08:07:04Z","snapshot_observed_at":"2026-08-02T08:10:10.416307Z","submitted_at":"2019-12-06T15:58:29Z","title":"Why are Adaptive Methods Good for Attention Models?","version":2},"cited_work":{"arxiv_id":"1912.03194","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1912.03194","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reddi, Sanjiv Kumar, and Suvrit Sra","venue":null,"work_id":"d83f1ea2-f71c-4f2f-a01b-45c5f7b78451","year":1912},"citing_paper":{"arxiv_id":"2605.11838","last_updated":"2026-05-12T09:24:59Z","snapshot_observed_at":"2026-07-06T23:23:34.924221Z","submitted_at":"2026-05-12T09:24:59Z","title":"Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-13T07:01:37.086159Z"},"links":{"cited_paper":"/paper/1912.03194","citing_paper":"/paper/2605.11838"},"observation_digest":"sha256:f914876f0ca0e1dbc80b6795a7bc9bc3362bca9231e6b01babe5e6c038378d5f","observation_id":"4991c1e8-4429-4396-a665-f0c73e69f7f0","resolution":{"observed_at":"2026-05-13T07:02:27.452595Z","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":"1912.03194","last_updated":"2020-10-23T08:07:04Z","snapshot_observed_at":"2026-08-02T08:10:10.416307Z","submitted_at":"2019-12-06T15:58:29Z","title":"Why are Adaptive Methods Good for Attention Models?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.03194","snapshot_observed_at":"2026-08-06T00:33:17.824749Z","title":null,"venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2608.01223","last_updated":"2026-08-02T13:12:16Z","snapshot_observed_at":"2026-08-10T04:55:14.792489Z","submitted_at":"2026-08-02T13:12:16Z","title":"Perspectives on Tsallis Statistics for Artificial Intelligence","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T00:33:17.824749Z"},"links":{"cited_paper":"/paper/1912.03194","citing_paper":"/paper/2608.01223"},"observation_digest":"sha256:9f4b0a9d1917e2ab2c07fee1795b2e012b29c4e78bac6a74cce3b12570dd0244","observation_id":"2cb0968c-b162-4856-bb1f-8958827466ae","resolution":{"observed_at":"2026-08-06T00:33:17.824749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1912.03194/citation-record","integrity":"/paper/1912.03194/integrity","json":"/paper/1912.03194/citation-record.json","paper":"/paper/1912.03194"},"outbound":[],"paper":{"arxiv_id":"1912.03194","last_updated":"2020-10-23T08:07:04Z","latest_version":2,"primary_category":"math.OC","snapshot_observed_at":"2026-08-02T08:10:10.416307Z","submitted_at":"2019-12-06T15:58:29Z","title":"Why are Adaptive Methods Good for Attention Models?"},"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 4 inbound Pith citation observations for arXiv:1912.03194."}