{"as_of":"2026-08-08T21:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:20b842bf245ea1295f9a12ed511968e301e7d12ed778ec204867d8379e821993","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T10:27:48.555525Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T18:56:16.182901Z","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":"2026-05-10T23:40:53.086156Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"cited_work":{"arxiv_id":"2601.10222","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2601.10222","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Introduction to optimization methods for training sciml models","venue":null,"work_id":"3e783787-ec74-4fc2-8226-75ca7599b2e0","year":2026},"citing_paper":{"arxiv_id":"2604.05230","last_updated":"2026-04-06T22:52:34Z","snapshot_observed_at":"2026-07-06T22:54:00.211106Z","submitted_at":"2026-04-06T22:52:34Z","title":"Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-10T18:56:16.182901Z"},"links":{"cited_paper":"/paper/2601.10222","citing_paper":"/paper/2604.05230"},"observation_digest":"sha256:70997147a259b7995348fb7dc0ec4d69a614afa38bbc63e2e4ae43fce325127f","observation_id":"2aafa969-9ce3-4d1d-8106-6921052fc3a5","resolution":{"observed_at":"2026-06-03T02:05:44.900480Z","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/2601.10222/citation-record","integrity":"/paper/2601.10222/integrity","json":"/paper/2601.10222/citation-record.json","paper":"/paper/2601.10222"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:27:47.459165Z","title":"Ahamed, N","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:47.459165Z"},"links":{"citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:ed1acdb8f0e3124786151f6fd8228cb6ecb997a866483054ac13b152fa41dbe8","observation_id":"f32d3552-3b27-4cb8-b4de-b3a000e80cf2","resolution":{"observed_at":"2026-08-03T10:27:47.459165Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:27:48.025576Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:48.025576Z"},"links":{"citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:f31cce01057bc9f7ce03f3152bd0366cbe58b7399707ffb31554087b551fe933","observation_id":"379cad92-07eb-42e4-9a24-8becf3e459fd","resolution":{"observed_at":"2026-08-03T10:27:48.025576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:27:48.234471Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:48.234471Z"},"links":{"citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:e68f4248a43fa2413277b20f20a9c1a70cd22433a86b6082e42cafb6552ef23e","observation_id":"10c04fe9-335c-4939-86dc-3f3ff90b22be","resolution":{"observed_at":"2026-08-03T10:27:48.234471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:27:47.859351Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:47.859351Z"},"links":{"citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:715c2a16c116b394cd43b86a3cc94299993baa5ebdc1dcbafd85f7d18bc00b92","observation_id":"e9d9cf16-9927-4b34-96a6-96f26456b3a1","resolution":{"observed_at":"2026-08-03T10:27:47.859351Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:27:48.298988Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:48.298988Z"},"links":{"citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:85828f8da97603fb2afa854154aff59391d6faddd3823802b437ca94364ed69e","observation_id":"5732e4e7-4836-4b8b-bafe-9ce8c72c730a","resolution":{"observed_at":"2026-08-03T10:27:48.298988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11321","last_updated":"2025-01-31T18:52:42Z","snapshot_observed_at":"2026-07-06T19:16:51.512681Z","submitted_at":"2024-09-17T16:18:05Z","title":"SOAP: Improving and Stabilizing Shampoo using Adam","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11321","snapshot_observed_at":"2026-08-03T10:27:48.555525Z","title":"Verfürth,A posteriori error estimation and adaptive mesh-refinement techniques, Journal of Computational and Applied Mathematics, 50 (1994), pp","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":1998,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:48.555525Z"},"links":{"cited_paper":"/paper/2409.11321","citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:6971cedc359f2fd584f6fe68e14544f88be6c837deacb00854673d2726853781","observation_id":"02b8b6f0-d3bf-4dd7-a0ba-ca640d819341","resolution":{"observed_at":"2026-08-03T10:27:48.555525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.18708","last_updated":"2025-04-02T18:37:59Z","snapshot_observed_at":"2026-07-06T20:28:38.345613Z","submitted_at":"2025-01-30T19:09:38Z","title":"Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.18708","snapshot_observed_at":"2026-08-03T10:27:48.355455Z","title":"Ponce, R","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":2006,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:48.355455Z"},"links":{"cited_paper":"/paper/2501.18708","citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:fb456c46458b71b963577baf8dea56c58d22a40329240fa6aeeb81f759e19e59","observation_id":"1eb619d4-b094-4fec-9401-6c2a9ddc675a","resolution":{"observed_at":"2026-08-03T10:27:48.355455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:27:47.741150Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:47.741150Z"},"links":{"citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:93101eb9b97047d269c0499cb017027561dedcbf73b2d4b9d5856edec92aa0de","observation_id":"fda221b4-a947-4519-960e-e3a6a68ad328","resolution":{"observed_at":"2026-08-03T10:27:47.741150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:27:48.439563Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:48.439563Z"},"links":{"citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:aba7a986c2ef4f76eab472faa1cdc7086b891d9d09826769011df6a676bba5e6","observation_id":"949b8118-e31f-4a1a-ad8f-8c3a32689ab8","resolution":{"observed_at":"2026-08-03T10:27:48.439563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:27:47.957535Z","title":"Kiyani, K","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:47.957535Z"},"links":{"citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:86359dde18f0ea1115e66f387a970dea199c29b63561b6a11648e0d92193a60c","observation_id":"e5b17f6e-26ca-475b-9019-d9c11cda9f26","resolution":{"observed_at":"2026-08-03T10:27:47.957535Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.08932","last_updated":"2021-12-08T08:30:55Z","snapshot_observed_at":"2026-07-06T10:34:33.181329Z","submitted_at":"2021-01-22T03:35:42Z","title":"Sobolev Training for Physics Informed Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.08932","snapshot_observed_at":"2026-08-03T10:27:48.487293Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:48.487293Z"},"links":{"cited_paper":"/paper/2101.08932","citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:e1f19b0bf417a949446ce31e04d1ef58e3dfe30106c7c0d61e4a570a4f065090","observation_id":"6931992d-bcfb-4ab2-adbc-45a421ceca26","resolution":{"observed_at":"2026-08-03T10:27:48.487293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T10:27:48.158107Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:48.158107Z"},"links":{"citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:29fe1cc3d2ba90fee1e1c932e12b4ded8d925a82b59403f7c932475446813c56","observation_id":"50231933-6090-46fc-a852-ee9f5de450a5","resolution":{"observed_at":"2026-08-03T10:27:48.158107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.11235","last_updated":"2024-03-09T13:28:29Z","snapshot_observed_at":"2026-07-06T14:44:56.245065Z","submitted_at":"2023-01-26T17:18:36Z","title":"Handbook of Convergence Theorems for (Stochastic) Gradient Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.11235","snapshot_observed_at":"2026-08-03T10:27:47.638277Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:47.638277Z"},"links":{"cited_paper":"/paper/2301.11235","citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:d4b14f9067521b4fcec2105e70f67109b89a94e1751eeb6a427388df0c1bab6f","observation_id":"66b29a9f-f37e-48db-803f-1a75f369b3f7","resolution":{"observed_at":"2026-08-03T10:27:47.638277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10348","last_updated":"2018-02-01T23:25:10Z","snapshot_observed_at":"2026-07-06T06:06:30.935200Z","submitted_at":"2017-10-27T22:06:58Z","title":"Multi-level Residual Networks from Dynamical Systems View","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10348","snapshot_observed_at":"2026-08-03T10:27:47.544382Z","title":"Amari,Natural gradient works efficiently in learning, Neural Com- putation, 10 (1998), pp","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models","version":2},"reference_index":2501,"source":"pdf_text","source_observed_at":"2026-08-03T10:27:47.544382Z"},"links":{"cited_paper":"/paper/1710.10348","citing_paper":"/paper/2601.10222"},"observation_digest":"sha256:5ef3da8dd2caeb76965b03ef417897db8ff9124daa6945e30333471135713a59","observation_id":"0db96c88-29d9-47e9-9490-22bd37d1e638","resolution":{"observed_at":"2026-08-03T10:27:47.544382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2601.10222","last_updated":"2026-06-02T13:23:42Z","latest_version":2,"primary_category":"math.NA","snapshot_observed_at":"2026-08-03T21:23:39.674231Z","submitted_at":"2026-01-15T09:36:15Z","title":"Introduction to optimization methods for training SciML models"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":14},"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 14 of 14 outbound references and 1 inbound Pith citation observation for arXiv:2601.10222."}