{"as_of":"2026-08-22T02:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5c8a94d4cab69c46ca0fa77c13339ef0d0b48a39e8bebe67e21fde8c800c58d1","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T19:18:41.639508Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2603.03017/citation-record","integrity":"/paper/2603.03017/integrity","json":"/paper/2603.03017/citation-record.json","paper":"/paper/2603.03017"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:18:36.504423Z","title":"Alvarado, D","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:36.504423Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:0f57a52d658983e8f0ee689fadd23298a27085e15fb7d846cd3bfa9d7ee6aa8e","observation_id":"74e0f269-ebea-496f-b645-7828c784b127","resolution":{"observed_at":"2026-08-02T19:18:36.504423Z","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":"2026-08-02T19:18:36.550099Z","title":"Discrete-time Incremental ISS: A framework for Ro- bust NMPC","venue":null,"work_id":null,"year":2068},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:36.550099Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:e35010bca572910ee1ae965aaa528885cd9944c2a30cad503c658111be8c18e2","observation_id":"46eac17e-afc2-4782-83b1-2fb71c16b2ee","resolution":{"observed_at":"2026-08-02T19:18:36.550099Z","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":"2026-08-02T19:18:36.629675Z","title":"On the stability properties of Gated Recurrent Units neural networks.Syst","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:36.629675Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:2c2f2822e64428f1551904a9e9b131466b2e8a063577cf159f901692dbc3ad0d","observation_id":"507d74ab-0a6c-4cef-b19c-618a00462cbf","resolution":{"observed_at":"2026-08-02T19:18:36.629675Z","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":"2026-08-02T19:18:36.683083Z","title":"On Recurrent Neural Networks for learning- based control.J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:36.683083Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:6496891527afebdc0762cc38dc354eda3d7190e009fac9a0b173c79d72afba75","observation_id":"8939823a-1271-4f3f-99a5-26fb429987b0","resolution":{"observed_at":"2026-08-02T19:18:36.683083Z","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":"2026-08-02T19:18:36.753999Z","title":"Cambridge University Press, Cambridge, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:36.753999Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:36ae1903390014e000621cca3209a0df19ee8246cbd26c781cb43f4b9f67c16c","observation_id":"ca27ec91-1fea-477b-b232-853093b7d76d","resolution":{"observed_at":"2026-08-02T19:18:36.753999Z","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":"2026-08-02T19:18:36.825780Z","title":"Boyd and Lieven Vandenberghe.Convex optimization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:36.825780Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:c17accb4a6a34a01407cfc8fef4d1a9c48345d591eec6c597a6f77a34fad0019","observation_id":"56991918-1273-42f6-9fc6-718e0ccee58c","resolution":{"observed_at":"2026-08-02T19:18:36.825780Z","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":"2026-08-02T19:18:36.903155Z","title":"Convergence of Gra- dient Descent for Recurrent Neural Networks.SIAM J","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:36.903155Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:55ae35e97dfb84f5ec904a04b853dbe255121991498efda29af6a6c46d9973ce","observation_id":"62f77de2-617f-41d6-acda-de9263c0deba","resolution":{"observed_at":"2026-08-02T19:18:36.903155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.10779","last_updated":"2024-08-27T09:28:35Z","snapshot_observed_at":"2026-08-16T13:51:51.994035Z","submitted_at":"2024-05-17T13:40:59Z","title":"Baseline Results for Selected Nonlinear System Identification Benchmarks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.10779","snapshot_observed_at":"2026-08-02T19:18:37.019429Z","title":"Champneys, Gerben I","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:37.019429Z"},"links":{"cited_paper":"/paper/2405.10779","citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:c302fcc5dbfc0801bc01b973e20fffada40bec48f87e833bb765b3d75ad2d7a7","observation_id":"bd2fb57e-40b2-4bfc-9c46-efa1d65ab04b","resolution":{"observed_at":"2026-08-02T19:18:37.019429Z","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":"2026-08-02T19:18:37.243742Z","title":"Fast projection onto the simplex and the l1 ball.Math","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:37.243742Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:dd336bb55bb3ab3afc88b541fad036efc4ff1e7d012efcef60cbd9cfc11693dc","observation_id":"7a649388-88f4-4fab-9d33-1ba052abe307","resolution":{"observed_at":"2026-08-02T19:18:37.243742Z","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":"2026-08-02T19:18:37.354743Z","title":"MATLAB code for the pro- posed training methodologies for MGU networks","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:37.354743Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:6a375d2639f4b6684fb547041cfd7cad83a38eb0a99b07169be045a41faaf4fc","observation_id":"5c90344d-7dc3-4dd1-8d37-8ddb7f635c51","resolution":{"observed_at":"2026-08-02T19:18:37.354743Z","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":"2026-08-02T19:18:37.500668Z","title":"Infinity-norm-based Input-to-State-Stable Long 15 Short-Term Memory networks","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:37.500668Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:5c9e24c0033a9e892e0c9c47efaad2d39986f4e9c93824b000c0ea829b4459df","observation_id":"07b4e746-b701-4560-9f95-65c4f2338d87","resolution":{"observed_at":"2026-08-02T19:18:37.500668Z","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":"2026-08-02T19:18:37.652149Z","title":"Deep Learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:37.652149Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:66841a9bfdf094dbcafc7d74af07e0d53027664546905ab7f6bd3435532127bb","observation_id":"e22f7659-99b3-4cf0-8bb0-f4a5d0849fd9","resolution":{"observed_at":"2026-08-02T19:18:37.652149Z","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":"2026-08-02T19:18:37.815611Z","title":"Input-to-state sta- bility for discrete-time nonlinear systems.Automatica, 37(6):857–869, 2001","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:37.815611Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:e94e9e087131c77aae46bb4c51e23bdcb6c39c947ae55df08e8971a92927b07d","observation_id":"15edde87-2ddf-4bd4-8496-483e7e0a1095","resolution":{"observed_at":"2026-08-02T19:18:37.815611Z","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":"2026-08-02T19:18:38.044339Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:38.044339Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:f5ce9a27cced2044b8426e62bb9820849d685b72f38af208cd4b1b4d32c8fbf7","observation_id":"25c7dadd-8dc5-4854-b66d-fe3ba5b99be1","resolution":{"observed_at":"2026-08-02T19:18:38.044339Z","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":"2026-08-02T19:18:38.205503Z","title":"LSTM and GRU type recurrent neural networks in model predictive control: A Review.Neurocomputing, 632:129712, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:38.205503Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:5ecb8172b87ee05095088aae9cee0d395e9c2aab5a6847ce48e18402e81b1de6","observation_id":"24fe8fbe-6d69-4419-a35f-fc172be03e7b","resolution":{"observed_at":"2026-08-02T19:18:38.205503Z","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":"2026-08-02T19:18:38.372312Z","title":"Integral-Input-to-State Stability of Switched Nonlinear Systems Under Slow Switch- ing.IEEE Trans","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:38.372312Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:1b7c999efb5d0c6f8f5ffb9d408b21f27c0320f488ae0ab1b96a2942b3737989","observation_id":"feb1cf82-bb3f-4fbf-995a-2e84dd9fee06","resolution":{"observed_at":"2026-08-02T19:18:38.372312Z","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":"2026-08-02T19:18:38.568902Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:38.568902Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:e78d00cd392de9cecbf801acd52f5509b4078ed478745e4062b2f67124f78e6f","observation_id":"8b7082d5-43c4-44c9-8fd9-eff7e1a74e13","resolution":{"observed_at":"2026-08-02T19:18:38.568902Z","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":"2026-08-02T19:18:38.761284Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:38.761284Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:4347888681cc481c5c99fb6acdbb6223ca74757f5c3ba60260ebb68dfe8a2304","observation_id":"8c2935d1-0539-4a36-a955-da0ccf029902","resolution":{"observed_at":"2026-08-02T19:18:38.761284Z","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":"2026-08-02T19:18:38.941823Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:38.941823Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:26bb7215eb4e4cd6c0b33731deee5c064b709f910d237ad2ea85262e364be56a","observation_id":"29c67054-0be3-48f3-b0cb-0980dd552162","resolution":{"observed_at":"2026-08-02T19:18:38.941823Z","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":"2026-08-02T19:18:39.077396Z","title":"SIAM, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:39.077396Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:971a0cd66aecde16d5858a1a685333810d0f34496128f5122dee25709ad408d0","observation_id":"d0fe8ca0-b1c1-4a54-9621-b9e07e175ba0","resolution":{"observed_at":"2026-08-02T19:18:39.077396Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.10369","last_updated":"2019-03-02T00:55:07Z","snapshot_observed_at":"2026-08-14T19:10:56.566148Z","submitted_at":"2018-05-25T21:37:35Z","title":"Stable Recurrent Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.10369","snapshot_observed_at":"2026-08-02T19:18:39.241199Z","title":"Stable Recurrent Mod- els","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:39.241199Z"},"links":{"cited_paper":"/paper/1805.10369","citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:9b5cb9d15ade0fdf4d57a2249ec9f893e7c98b539c2993faa6f564425a6d9616","observation_id":"c32594e8-6a0a-4d31-9971-78f3a1ee87aa","resolution":{"observed_at":"2026-08-02T19:18:39.241199Z","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":"2026-08-02T19:18:39.435713Z","title":"Criteria for Input-to-State Practi- cal Stability.IEEE Trans","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:39.435713Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:1798f7c0be8d3fa2c1835ea41a5d60aa434c079d00fb836b8f710a9e4082fcb2","observation_id":"eb942cf0-ad95-43ab-9cc0-3b9d884052f7","resolution":{"observed_at":"2026-08-02T19:18:39.435713Z","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":"2026-08-02T19:18:39.567867Z","title":"Murphy.Probabilistic Machine Learning: An Introduction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:39.567867Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:968ac11724ca3f75e4038bbe4c9a54fc3175769927fc66fca07b484ca2e68af1","observation_id":"f909816e-5757-475c-b1a8-23dd01fe77ac","resolution":{"observed_at":"2026-08-02T19:18:39.567867Z","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":"2026-08-02T19:18:39.712657Z","title":"Wright.Numerical Op- timization","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:39.712657Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:741d75ae0fadd2803a33d29135b6cbc5f4ea73fe2a47f1d6d0465b10372d04b8","observation_id":"2a23d570-f8e8-4990-a5f6-8e080b2f0031","resolution":{"observed_at":"2026-08-02T19:18:39.712657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6026","last_updated":"2014-04-24T15:17:07Z","snapshot_observed_at":"2026-08-19T20:40:45.710513Z","submitted_at":"2013-12-20T16:39:39Z","title":"How to Construct Deep Recurrent Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6026","snapshot_observed_at":"2026-08-02T19:18:39.795972Z","title":"How to Construct Deep Recur- rent Neural Networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:39.795972Z"},"links":{"cited_paper":"/paper/1312.6026","citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:f0ce74a3cfe337d0ed0e414c24c878acb36851b580ed031f58f0782e05b0caaa","observation_id":"b556e7fe-7e72-45cf-b7d0-92059283e452","resolution":{"observed_at":"2026-08-02T19:18:39.795972Z","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":"2026-08-02T19:18:39.863206Z","title":"Ribeiro, and Thomas B","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:39.863206Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:9ffcb0595e565a2284740c9df4beb85d2048ca4fe6a7ebfefe96bd274349c559","observation_id":"de5044cb-ad56-4d88-ab7c-b430b42dd357","resolution":{"observed_at":"2026-08-02T19:18:39.863206Z","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":"2026-08-02T19:18:39.958481Z","title":"Kernel-Based Identification of Incremen- tally Input-to-State Stable Nonlinear Systems.IFAC- PapersOnLine, 56(2):5127–5132, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:39.958481Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:93c01a3175f13fc1c5e1a9593549329a5cc9a9b088cf43162b151932552756b9","observation_id":"0ae32080-74d2-404d-8e2d-95c249d2d84c","resolution":{"observed_at":"2026-08-02T19:18:39.958481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.10212","last_updated":"2025-03-17T10:44:13Z","snapshot_observed_at":"2026-08-16T17:18:51.951417Z","submitted_at":"2024-09-16T12:03:23Z","title":"Kernel-Based Learning of Stable Nonlinear Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.10212","snapshot_observed_at":"2026-08-02T19:18:40.108978Z","title":"Kernel-Based Learning of Stable Nonlinear Systems","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:40.108978Z"},"links":{"cited_paper":"/paper/2409.10212","citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:1fa72aa14206d9b0df54bf4267eb07e01b1701ffdd77ff06e3a674bf32558cda","observation_id":"3518d0c0-2369-4de7-bb72-5cc7af24a2bd","resolution":{"observed_at":"2026-08-02T19:18:40.108978Z","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":"2026-08-02T19:18:40.256110Z","title":"Robust constrained nonlinear Model Predictive Control with Gated Recur- rent Unit model.Automatica, 161:111472, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:40.256110Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:de5cd0f432cf68f716c368224fe3553f845b894cc2a3a44e76bc017f6379dc50","observation_id":"b84af47e-73bd-4a46-9792-806ca753aed3","resolution":{"observed_at":"2026-08-02T19:18:40.256110Z","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":"2026-08-02T19:18:40.385937Z","title":"Robust Offset- Free Constrained Model Predictive Control With Long Short-Term Memory Networks.IEEE Trans","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:40.385937Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:861881c7fdb6243146f1cef253d0224c2642fe841467f535d371f7f212140cb9","observation_id":"6311fc95-43a6-49db-ac5f-2f901f003ddc","resolution":{"observed_at":"2026-08-02T19:18:40.385937Z","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":"2026-08-02T19:18:40.528106Z","title":null,"venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:40.528106Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:4b6e38c1ee0f6a078f33da4798c0028e64fd19d12a1810cc53a09900654564f2","observation_id":"8d67e7d3-dcea-48b8-8f20-a5a7b624f0f8","resolution":{"observed_at":"2026-08-02T19:18:40.528106Z","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":"2026-08-02T19:18:40.702950Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":null,"year":1929},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:40.702950Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:e440c1917ac0a4557549227961bc32e8d3b67027014f8456f4eb1a3616eb3e8c","observation_id":"7b7f36c1-a300-4364-97e0-2fcd93f48ab7","resolution":{"observed_at":"2026-08-02T19:18:40.702950Z","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":"10.5281/zenodo.3956066","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"pH reactor dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","work_id":"1519699d-115c-4f9b-9503-c8ed3232d039","year":2020},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:40.852930Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:80c1b5052abba5eef40f81ff26d29ac203fadde5caccba3b0ca9c187de2758ea","observation_id":"348bd163-4288-49b6-b3c5-8e129461a7ff","resolution":{"observed_at":"2026-08-02T19:24:00.155903Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T19:18:41.037559Z","title":"Learning model predictive control with long short-term memory networks.Int","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:41.037559Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:06a50351be7ccbf7fc0f0d0b03cfba805047795261b4a58df058f88a52978aa6","observation_id":"98a2c516-2841-4a0e-9eaf-a722ccc6bd35","resolution":{"observed_at":"2026-08-02T19:18:41.037559Z","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":"2026-08-02T19:18:41.212814Z","title":"Three free data sets for development and benchmarking in nonlinear system identification","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:41.212814Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:a3cf51e97927eaab17f051bc12bbbb7affb6d2d1f48468fe9a9673f313953d49","observation_id":"0fc4ff83-2d00-4e5d-a991-4857a03b9e4f","resolution":{"observed_at":"2026-08-02T19:18:41.212814Z","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":"2026-08-02T19:18:41.439053Z","title":"Gradient centralization: A new optimiza- tion technique for deep neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:41.439053Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:26ad10dd16c5e34b0e9453982993bc45ca54370718541f0b1b58d5de51bb69cd","observation_id":"a0908038-9230-4052-89fa-2491784c5637","resolution":{"observed_at":"2026-08-02T19:18:41.439053Z","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":"2026-08-02T19:18:41.639508Z","title":"Minimal gated unit for recurrent neu- ral networks.Int","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T19:18:41.639508Z"},"links":{"citing_paper":"/paper/2603.03017"},"observation_digest":"sha256:57b3e229d1fa23148b2c6142a5256a1719a012995b8fbc291e79503a57834ba4","observation_id":"00fce168-254e-459b-a4d1-cc9064849f07","resolution":{"observed_at":"2026-08-02T19:18:41.639508Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.03017","last_updated":"2026-06-11T14:26:18Z","latest_version":2,"primary_category":"math.OC","snapshot_observed_at":"2026-08-19T20:43:14.696993Z","submitted_at":"2026-03-03T14:12:55Z","title":"Stability properties of Minimal Gated Unit neural networks"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":37},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2603.03017."}