{"as_of":"2026-08-09T12:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c213e23d4b420a6148bdf3e0a74fd5f666856c521a70da0c3337ceef17a42d97","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":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:48:45.281153Z","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":"2026-05-25T05:40:24.297793Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.01878","last_updated":"2019-09-26T06:53:59Z","snapshot_observed_at":"2026-08-04T16:48:43.945005Z","submitted_at":"2019-08-05T21:56:41Z","title":"How Does Learning Rate Decay Help Modern Neural Networks?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.01878","snapshot_observed_at":"2026-08-07T12:48:45.281153Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.23489","last_updated":"2025-05-29T14:40:24Z","snapshot_observed_at":"2026-08-09T07:26:40.760979Z","submitted_at":"2025-05-29T14:40:24Z","title":"SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T12:48:45.281153Z"},"links":{"cited_paper":"/paper/1908.01878","citing_paper":"/paper/2505.23489"},"observation_digest":"sha256:b45ff13a81a511068f984f1a5b9fd8ac8092522b4225e714fc13dac44e22f19a","observation_id":"faf4f39e-dd6a-4079-a3d0-c9e1dd180e17","resolution":{"observed_at":"2026-08-07T12:48:45.281153Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.01878","last_updated":"2019-09-26T06:53:59Z","snapshot_observed_at":"2026-08-04T16:48:43.945005Z","submitted_at":"2019-08-05T21:56:41Z","title":"How Does Learning Rate Decay Help Modern Neural Networks?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.01878","snapshot_observed_at":"2026-08-07T04:26:54.041063Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.10620","last_updated":"2025-06-12T12:06:05Z","snapshot_observed_at":"2026-08-07T04:19:10.066017Z","submitted_at":"2025-06-12T12:06:05Z","title":"Assessing the Resilience of Automotive Intrusion Detection Systems to Adversarial Manipulation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T04:26:54.041063Z"},"links":{"cited_paper":"/paper/1908.01878","citing_paper":"/paper/2506.10620"},"observation_digest":"sha256:361f3538529db76318aef37dac7b7f9ec87104ea8d428fddae3d87bf0b4cc20a","observation_id":"41315ccb-2f77-488b-a766-2528d8610d77","resolution":{"observed_at":"2026-08-07T04:26:54.041063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.01878","last_updated":"2019-09-26T06:53:59Z","snapshot_observed_at":"2026-08-04T16:48:43.945005Z","submitted_at":"2019-08-05T21:56:41Z","title":"How Does Learning Rate Decay Help Modern Neural Networks?","version":2},"cited_work":{"arxiv_id":"1908.01878","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1908.01878","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anytime Training with Schedule-Free Spectral Optimization","venue":null,"work_id":"026b8b15-298f-404b-a94f-781cda43102e","year":2019},"citing_paper":{"arxiv_id":"2604.23362","last_updated":"2026-04-25T16:05:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-25T16:05:32Z","title":"UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-08T07:53:59.293260Z"},"links":{"cited_paper":"/paper/1908.01878","citing_paper":"/paper/2604.23362"},"observation_digest":"sha256:b4d38532bda4ebd1cca264ddb8eef937bde72b4a9ce4b8ac99dff2ab2b4e2fbd","observation_id":"17e733de-2682-4d03-b49f-1d228acacc83","resolution":{"observed_at":"2026-05-11T20:51:08.901040Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"1908.01878","last_updated":"2019-09-26T06:53:59Z","snapshot_observed_at":"2026-08-04T16:48:43.945005Z","submitted_at":"2019-08-05T21:56:41Z","title":"How Does Learning Rate Decay Help Modern Neural Networks?","version":2},"cited_work":{"arxiv_id":"1908.01878","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1908.01878","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Anytime Training with Schedule-Free Spectral Optimization","venue":null,"work_id":"026b8b15-298f-404b-a94f-781cda43102e","year":2019},"citing_paper":{"arxiv_id":"2605.23061","last_updated":"2026-05-21T21:50:22Z","snapshot_observed_at":"2026-08-02T04:10:09.683333Z","submitted_at":"2026-05-21T21:50:22Z","title":"Anytime Training with Schedule-Free Spectral Optimization","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-05-25T05:38:16.958574Z"},"links":{"cited_paper":"/paper/1908.01878","citing_paper":"/paper/2605.23061"},"observation_digest":"sha256:3b885dd2219960e34b0c3283b6df5b3f10fe8eb17b1586291d9c74fd3b47bab9","observation_id":"dfd38cb2-6973-46bd-adf8-f44cc189dfc8","resolution":{"observed_at":"2026-05-25T05:40:24.300674Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"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":"1908.01878","last_updated":"2019-09-26T06:53:59Z","snapshot_observed_at":"2026-08-04T16:48:43.945005Z","submitted_at":"2019-08-05T21:56:41Z","title":"How Does Learning Rate Decay Help Modern Neural Networks?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.01878","snapshot_observed_at":"2026-08-01T00:54:33.061955Z","title":null,"venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2607.26014","last_updated":"2026-07-28T17:27:36Z","snapshot_observed_at":"2026-08-04T17:32:44.956215Z","submitted_at":"2026-07-28T17:27:36Z","title":"Automated Solar Radio Burst Detection Using Deep Learning on Augmented e-Callisto Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T00:54:33.061955Z"},"links":{"cited_paper":"/paper/1908.01878","citing_paper":"/paper/2607.26014"},"observation_digest":"sha256:ba93e732cc4edaf7ac32455b25c531820f7e7debdb406893c9789c349b16dad8","observation_id":"339cfd79-b8ae-4809-bec7-edbbe738c39b","resolution":{"observed_at":"2026-08-01T00:54:33.061955Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1908.01878/citation-record","integrity":"/paper/1908.01878/integrity","json":"/paper/1908.01878/citation-record.json","paper":"/paper/1908.01878"},"outbound":[],"paper":{"arxiv_id":"1908.01878","last_updated":"2019-09-26T06:53:59Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T16:48:43.945005Z","submitted_at":"2019-08-05T21:56:41Z","title":"How Does Learning Rate Decay Help Modern Neural Networks?"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:1908.01878."}