{"as_of":"2026-08-22T08:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2f13821a344724679131d76481f1331bb510a27883491a06a644130eb4583194","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T06:04:09.675097Z","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":"2026-08-10T14:10:55.748563Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.10533","last_updated":"2025-02-15T04:17:23Z","snapshot_observed_at":"2026-08-21T02:47:24.737232Z","submitted_at":"2024-10-14T14:11:37Z","title":"Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation","version":2},"cited_work":{"arxiv_id":"2410.10533","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.10533","snapshot_observed_at":"2026-08-10T14:10:55.748563Z","title":"Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation","venue":"cs.LG","work_id":"8c0916f3-08aa-4adb-a531-f651568abf44","year":2024},"citing_paper":{"arxiv_id":"2501.15646","last_updated":"2025-01-26T19:11:57Z","snapshot_observed_at":"2026-08-14T12:46:39.320894Z","submitted_at":"2025-01-26T19:11:57Z","title":"Mathematical analysis of the gradients in deep learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T14:10:55.171951Z"},"links":{"cited_paper":"/paper/2410.10533","citing_paper":"/paper/2501.15646"},"observation_digest":"sha256:fe38df5b0060ee0efdd917559b2ef0cb9baa85ac6aaf9eb4791979cde77ba4ff","observation_id":"7d58f89a-2b2c-4fde-92c0-aca6e4701d44","resolution":{"observed_at":"2026-08-10T14:10:55.752584Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10533","last_updated":"2025-02-15T04:17:23Z","snapshot_observed_at":"2026-08-21T02:47:24.737232Z","submitted_at":"2024-10-14T14:11:37Z","title":"Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10533","snapshot_observed_at":"2026-08-16T06:04:09.675097Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.19426","last_updated":"2025-04-28T02:17:50Z","snapshot_observed_at":"2026-08-21T02:46:31.820451Z","submitted_at":"2025-04-28T02:17:50Z","title":"Sharp higher order convergence rates for the Adam optimizer","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T06:04:09.675097Z"},"links":{"cited_paper":"/paper/2410.10533","citing_paper":"/paper/2504.19426"},"observation_digest":"sha256:3e12822096e56296ece74fe4a2eaf02e6024d6cd6c1f6c7a66ce307545ced32d","observation_id":"4838e261-417c-4152-be2f-a0ab65616662","resolution":{"observed_at":"2026-08-16T06:04:09.675097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10533","last_updated":"2025-02-15T04:17:23Z","snapshot_observed_at":"2026-08-21T02:47:24.737232Z","submitted_at":"2024-10-14T14:11:37Z","title":"Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10533","snapshot_observed_at":"2026-08-02T00:02:19.592530Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15173","last_updated":"2026-07-16T16:22:16Z","snapshot_observed_at":"2026-08-20T21:35:15.679712Z","submitted_at":"2026-07-16T16:22:16Z","title":"Landscape analysis for shallow neural networks: Complete classification of critical points for cubic activation and affine target functions","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-02T00:02:19.592530Z"},"links":{"cited_paper":"/paper/2410.10533","citing_paper":"/paper/2607.15173"},"observation_digest":"sha256:c14e5148d3abba66b2316f1442bc021973e8811a93fb4836e439a0ecbb07b395","observation_id":"c9ff34c5-c8c5-4d4b-8996-47251815b10f","resolution":{"observed_at":"2026-08-02T00:02:19.592530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2410.10533/citation-record","integrity":"/paper/2410.10533/integrity","json":"/paper/2410.10533/citation-record.json","paper":"/paper/2410.10533"},"outbound":[],"paper":{"arxiv_id":"2410.10533","last_updated":"2025-02-15T04:17:23Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-21T02:47:24.737232Z","submitted_at":"2024-10-14T14:11:37Z","title":"Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent optimization provably fail to converge to global minimizers in the training of deep neural networks with ReLU activation"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2410.10533."}