{"as_of":"2026-08-15T01:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:23fb9c03d48a91760b0130666fd21941472fc5767947daea0fdc3c0b868b4aa2","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":"2026-08-14T06:32:32.682623+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":"2026-08-11T04:32:51.546755Z","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":"2026-07-04T13:59:52.030379Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.04369","last_updated":"2021-10-08T20:25:48Z","snapshot_observed_at":"2026-08-13T17:56:57.796433Z","submitted_at":"2021-10-08T20:25:48Z","title":"A Loss Curvature Perspective on Training Instability in Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04369","snapshot_observed_at":"2026-08-11T04:32:51.546755Z","title":"A loss curvature perspective on training instability in deep learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.18790","last_updated":"2024-12-25T05:58:07Z","snapshot_observed_at":"2026-08-12T06:39:00.033987Z","submitted_at":"2024-12-25T05:58:07Z","title":"Torque-Aware Momentum","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T04:32:51.546755Z"},"links":{"cited_paper":"/paper/2110.04369","citing_paper":"/paper/2412.18790"},"observation_digest":"sha256:6c2cb49309610060045599f5157fb7e7a846992824e8366f2479045910a72549","observation_id":"4ac4761b-0aab-4904-abf2-3b62158766e0","resolution":{"observed_at":"2026-08-11T04:32:51.546755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04369","last_updated":"2021-10-08T20:25:48Z","snapshot_observed_at":"2026-08-13T17:56:57.796433Z","submitted_at":"2021-10-08T20:25:48Z","title":"A Loss Curvature Perspective on Training Instability in Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04369","snapshot_observed_at":"2026-08-06T13:09:57.185189Z","title":"A loss curvature perspective on training instability in deep learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-15T00:23:28.216000Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.185189Z"},"links":{"cited_paper":"/paper/2110.04369","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:3f9fa5d0538363dd5fc22b361929ee8bae5161c36251a009323c402499aac6fd","observation_id":"b3299cb5-a237-47ce-a2f4-dd24f5142834","resolution":{"observed_at":"2026-08-06T13:09:57.185189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04369","last_updated":"2021-10-08T20:25:48Z","snapshot_observed_at":"2026-08-13T17:56:57.796433Z","submitted_at":"2021-10-08T20:25:48Z","title":"A Loss Curvature Perspective on Training Instability in Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04369","snapshot_observed_at":"2026-08-04T12:38:55.058339Z","title":"A loss curvature perspective on training instability in deep learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.03164","last_updated":"2026-06-28T16:14:54Z","snapshot_observed_at":"2026-08-14T12:29:49.923863Z","submitted_at":"2025-10-03T16:35:56Z","title":"Why Do We Need Warm-up? A Theoretical Perspective","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T12:38:55.058339Z"},"links":{"cited_paper":"/paper/2110.04369","citing_paper":"/paper/2510.03164"},"observation_digest":"sha256:8a87843ca31d23a2b0c3551562cd0bf9ecf30775cf0b122ed6432da75a3f13fa","observation_id":"f3373c31-9333-445c-982e-05503cf50e41","resolution":{"observed_at":"2026-08-04T12:38:55.058339Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04369","last_updated":"2021-10-08T20:25:48Z","snapshot_observed_at":"2026-08-13T17:56:57.796433Z","submitted_at":"2021-10-08T20:25:48Z","title":"A Loss Curvature Perspective on Training Instability in Deep Learning","version":1},"cited_work":{"arxiv_id":"2110.04369","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.04369","snapshot_observed_at":"2026-07-04T13:59:52.030379Z","title":"A loss curvature perspective on training instability in deep learning,","venue":null,"work_id":"fb096c52-6fe0-4123-9820-9253c2d03633","year":2021},"citing_paper":{"arxiv_id":"2606.26492","last_updated":"2026-06-25T00:52:22Z","snapshot_observed_at":"2026-08-07T21:59:39.734700Z","submitted_at":"2026-06-25T00:52:22Z","title":"Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-26T04:45:46.785605Z"},"links":{"cited_paper":"/paper/2110.04369","citing_paper":"/paper/2606.26492"},"observation_digest":"sha256:d0b6948c28395a8807c23cccd00af6c7c8a825ce66437d22de4c22440c0911a1","observation_id":"c75d0a5c-6bb6-4895-a9e2-7e63564ac2df","resolution":{"observed_at":"2026-07-04T13:59:52.032131Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2110.04369/citation-record","integrity":"/paper/2110.04369/integrity","json":"/paper/2110.04369/citation-record.json","paper":"/paper/2110.04369"},"outbound":[],"paper":{"arxiv_id":"2110.04369","last_updated":"2021-10-08T20:25:48Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T17:56:57.796433Z","submitted_at":"2021-10-08T20:25:48Z","title":"A Loss Curvature Perspective on Training Instability in Deep Learning"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2110.04369."}