{"as_of":"2026-08-20T18:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fa01b14f6ef7284379afe06053a1a1cf1cf0c38df91cf8d9d98c2b9e4fdc4282","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":"2026-08-20T06:33:59.587034+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":"2026-08-10T23:08:28.123888Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":3,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.11215","last_updated":"2024-05-28T05:40:38Z","snapshot_observed_at":"2026-08-16T14:17:47.090256Z","submitted_at":"2024-02-17T07:49:50Z","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11215","snapshot_observed_at":"2026-08-10T23:08:28.123888Z","title":"arXiv preprint arXiv:2402.11215, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.21124","last_updated":"2025-03-16T21:10:15Z","snapshot_observed_at":"2026-08-17T20:30:23.005028Z","submitted_at":"2024-12-30T17:55:28Z","title":"Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T23:08:28.123888Z"},"links":{"cited_paper":"/paper/2402.11215","citing_paper":"/paper/2412.21124"},"observation_digest":"sha256:fa3efc3193ca5ac67b8f81ac785af4e77a70508fb33487ee18af3c6f29a93502","observation_id":"2928c122-0501-4787-9a67-f490766b7b7a","resolution":{"observed_at":"2026-08-10T23:08:28.123888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11215","last_updated":"2024-05-28T05:40:38Z","snapshot_observed_at":"2026-08-16T14:17:47.090256Z","submitted_at":"2024-02-17T07:49:50Z","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11215","snapshot_observed_at":"2026-08-06T19:55:45.867498Z","title":"arXiv preprint arXiv:2402.11215 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04269","last_updated":"2025-07-06T07:02:04Z","snapshot_observed_at":"2026-08-20T07:30:13.774201Z","submitted_at":"2025-07-06T07:02:04Z","title":"Efficient Training of Deep Networks using Guided Spectral Data Selection: A Step Toward Learning What You Need","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:45.867498Z"},"links":{"cited_paper":"/paper/2402.11215","citing_paper":"/paper/2507.04269"},"observation_digest":"sha256:22f2f67c728f0f1ce0f55db1f6be0ea967d295506a73844818c68b54b87bab15","observation_id":"437df03d-b11d-4460-a96d-ffa0d01fe23d","resolution":{"observed_at":"2026-08-06T19:55:45.867498Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11215","last_updated":"2024-05-28T05:40:38Z","snapshot_observed_at":"2026-08-16T14:17:47.090256Z","submitted_at":"2024-02-17T07:49:50Z","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11215","snapshot_observed_at":"2026-08-05T16:36:50.522929Z","title":"Adadagrad: Adaptive batch size schemes for adaptive gradient methods, 2024 b","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18182","last_updated":"2025-08-25T16:35:57Z","snapshot_observed_at":"2026-08-12T07:25:47.527315Z","submitted_at":"2025-08-25T16:35:57Z","title":"AdLoCo: adaptive batching significantly improves communications efficiency and convergence for Large Language Models","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-05T16:36:50.522929Z"},"links":{"cited_paper":"/paper/2402.11215","citing_paper":"/paper/2508.18182"},"observation_digest":"sha256:a0a9d825d8ee1909f173716e9d7be7ffe614b81f407bd99403297a478c3b2582","observation_id":"d73c9710-d506-4114-b18f-8aad88581f0c","resolution":{"observed_at":"2026-08-05T16:36:50.522929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11215","last_updated":"2024-05-28T05:40:38Z","snapshot_observed_at":"2026-08-16T14:17:47.090256Z","submitted_at":"2024-02-17T07:49:50Z","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","version":3},"cited_work":{"arxiv_id":"2402.11215","doi":"10.48550/arxiv.2402.11215","metadata_source":"arxiv_reference","pith_arxiv_id":"2402.11215","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"arXiv (Cornell University)","work_id":"e4652852-3a93-4674-90b4-a03fa5ee1c04","year":2024},"citing_paper":{"arxiv_id":"2604.26687","last_updated":"2026-04-29T13:52:38Z","snapshot_observed_at":"2026-08-15T11:14:11.808420Z","submitted_at":"2026-04-29T13:52:38Z","title":"COPUS: Co-adaptive Parallelism and Batch Size Selection in Large Language Model Training","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-07T11:25:24.079444Z"},"links":{"cited_paper":"/paper/2402.11215","citing_paper":"/paper/2604.26687"},"observation_digest":"sha256:604cd49a5900921ee8c40d82a77aba2fa4212d5a00cf1ed9bcfd15eb69dd9a9d","observation_id":"35e3f6af-612e-4efe-b773-e499fead9acf","resolution":{"observed_at":"2026-05-09T03:55:07.660974Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.11215/citation-record","integrity":"/paper/2402.11215/integrity","json":"/paper/2402.11215/citation-record.json","paper":"/paper/2402.11215"},"outbound":[],"paper":{"arxiv_id":"2402.11215","last_updated":"2024-05-28T05:40:38Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T14:17:47.090256Z","submitted_at":"2024-02-17T07:49:50Z","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2402.11215."}