{"as_of":"2026-08-08T15:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d804df12d12496d0f795e7cbbcbeca990679b3c4901514bc09ceb06c97590070","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T13:20:49.539468Z","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":"2026-05-20T12:23:16.782786Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2301.02312","last_updated":"2023-02-01T07:08:58Z","snapshot_observed_at":"2026-07-06T14:37:56.945127Z","submitted_at":"2023-01-05T21:58:46Z","title":"Training trajectories, mini-batch losses and the curious role of the learning rate","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.02312","snapshot_observed_at":"2026-08-07T13:20:49.539468Z","title":"Training tra- jectories, mini-batch losses and the curious role of the learning rate","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22085","last_updated":"2025-05-28T08:07:34Z","snapshot_observed_at":"2026-08-07T13:13:06.021383Z","submitted_at":"2025-05-28T08:07:34Z","title":"PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T13:20:49.539468Z"},"links":{"cited_paper":"/paper/2301.02312","citing_paper":"/paper/2505.22085"},"observation_digest":"sha256:231b3c218559b96593e2993b569eb35e42d2ed12247101b102642c621ec8bb36","observation_id":"59a99ae4-2b76-4bb0-ad7f-ecea03b0c639","resolution":{"observed_at":"2026-08-07T13:20:49.539468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.02312","last_updated":"2023-02-01T07:08:58Z","snapshot_observed_at":"2026-07-06T14:37:56.945127Z","submitted_at":"2023-01-05T21:58:46Z","title":"Training trajectories, mini-batch losses and the curious role of the learning rate","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.02312","snapshot_observed_at":"2026-08-06T14:49:40.322544Z","title":"Training trajectories, mini-batch losses and the curious role of the learning rate","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.17634","last_updated":"2025-08-11T08:36:31Z","snapshot_observed_at":"2026-08-06T19:16:35.269127Z","submitted_at":"2025-07-23T16:02:06Z","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-06T14:49:40.322544Z"},"links":{"cited_paper":"/paper/2301.02312","citing_paper":"/paper/2507.17634"},"observation_digest":"sha256:3fa9566b0ef34ea821b9312dd5a598610184a788f2ab5c49fdcf11da01589a38","observation_id":"9f1d570c-bd0e-43dd-801f-db8643107920","resolution":{"observed_at":"2026-08-06T14:49:40.322544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.02312","last_updated":"2023-02-01T07:08:58Z","snapshot_observed_at":"2026-07-06T14:37:56.945127Z","submitted_at":"2023-01-05T21:58:46Z","title":"Training trajectories, mini-batch losses and the curious role of the learning rate","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.02312","snapshot_observed_at":"2026-08-06T10:23:51.923341Z","title":"Training trajectories, mini-batch losses and the curious role of the learning rate","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.00180","last_updated":"2025-07-31T21:49:20Z","snapshot_observed_at":"2026-08-06T10:23:40.957414Z","submitted_at":"2025-07-31T21:49:20Z","title":"EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-06T10:23:51.923341Z"},"links":{"cited_paper":"/paper/2301.02312","citing_paper":"/paper/2508.00180"},"observation_digest":"sha256:e89e797bd6cc29e551f0d94b00d6ae9d8cb6fc19473865340bca16e1c5f88dc3","observation_id":"8a87a096-54f8-4fa8-9708-00f1012e76a9","resolution":{"observed_at":"2026-08-06T10:23:51.923341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.02312","last_updated":"2023-02-01T07:08:58Z","snapshot_observed_at":"2026-07-06T14:37:56.945127Z","submitted_at":"2023-01-05T21:58:46Z","title":"Training trajectories, mini-batch losses and the curious role of the learning rate","version":2},"cited_work":{"arxiv_id":"2301.02312","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2301.02312","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"439ae8bd-7e78-46c2-9547-75d68c69514b","year":2023},"citing_paper":{"arxiv_id":"2605.19095","last_updated":"2026-05-18T20:31:49Z","snapshot_observed_at":"2026-07-06T23:29:52.061489Z","submitted_at":"2026-05-18T20:31:49Z","title":"ScheduleFree+: Scaling Learning-Rate-Free & Schedule-Free Learning to Large Language Models","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-05-20T12:22:30.263086Z"},"links":{"cited_paper":"/paper/2301.02312","citing_paper":"/paper/2605.19095"},"observation_digest":"sha256:57aeef4d29f03e06e4770510fc72df4c67c42cabcd5a2abe372834e8bd3277b5","observation_id":"8bf73e49-b023-47a1-b2f6-0d8210f4ed28","resolution":{"observed_at":"2026-05-20T12:23:16.784243Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2301.02312/citation-record","integrity":"/paper/2301.02312/integrity","json":"/paper/2301.02312/citation-record.json","paper":"/paper/2301.02312"},"outbound":[],"paper":{"arxiv_id":"2301.02312","last_updated":"2023-02-01T07:08:58Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T14:37:56.945127Z","submitted_at":"2023-01-05T21:58:46Z","title":"Training trajectories, mini-batch losses and the curious role of the learning rate"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2301.02312."}