{"as_of":"2026-08-17T16:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:004c96543aec598a7ce42c980a0829ab27455b8fa95f0a115e33669541e68b00","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T02:49:16.884263Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2607.03393/citation-record","integrity":"/paper/2607.03393/integrity","json":"/paper/2607.03393/citation-record.json","paper":"/paper/2607.03393"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T02:49:16.884263Z","title":"An overview of gradient descent optimization algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:ab65e9bfd84c1255b17eb18a011395b0454894f345125343339db357bc5f0bd4","observation_id":"916fc5ec-be97-4c74-9622-522b115416a5","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"A lyapunov analysis for accelerated gra- dient methods: From deterministic to stochastic case,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:1a26eec34399871a14ee6994022417c96a2977da78517753ff49fea3fb5312c7","observation_id":"a7a12a0a-7e6c-4422-a61b-a58fa693b720","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"New insights and perspectives on the natural gradient method,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:4c7ab48dfa0e8e9ab4c82f5527618202b850580fd32fff85deac2cb501e7dc1b","observation_id":"8a426a69-074e-4516-b1f5-022314dd4c41","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Defining and characterizing reward gaming,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:dde6afcdf56239bb5c5432902f7fb2dff740fd487e141697f8147fd29aadb239","observation_id":"5551a5c0-790a-4666-816e-31909972a957","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Opti- mization algorithms as robust feedback controllers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:ed56dc0d9dce358ab5b1ab312d92f62570018cf654547ddb7cf918ebe516ebd6","observation_id":"b03ba784-51a0-442d-96c6-6783971f4327","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Analysis and design of opti- mization algorithms via integral quadratic constraints,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:01dc3313ecbc9f3d68b55e9e3f837809005df5d48b7e1066e91ea689d3da80da","observation_id":"d583bc6b-431d-4611-90a5-a41286184405","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Analysis of gradient descent with vary- ing step sizes using integral quadratic constraints,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:00e6d803e11858f925816d85b91317757b7a44da94f0c8918d5c2bc4c5875827","observation_id":"9912c0dc-3252-4eea-b37c-7ef221ced2d4","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.10674","last_updated":"2022-11-19T11:57:25Z","snapshot_observed_at":"2026-08-16T16:14:54.727190Z","submitted_at":"2022-11-19T11:57:25Z","title":"Passivity and Immersion based-modified gradient estimator: A control perspective in parameter estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.10674","snapshot_observed_at":"2026-07-12T02:49:16.884263Z","title":"Passivity and immersion based-modified gradient estimator: A control perspective in parameter estimation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"cited_paper":"/paper/2211.10674","citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:ffce2269017426af9ff735699676928fb9fc7aad1afd127e5e68d92274120836","observation_id":"436080d4-653f-47d1-831f-1d852d506cec","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Trajectory-oriented control using gradient descent: An unconventional approach,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:e2d18de2fd428c693f5047dede1805014db78b9859c3fd7f4aa636109b807c33","observation_id":"18b4c094-08be-4210-a637-3dbdba7c4dfb","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Natural gradient descent for control,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:c654c31bbc40bd618c14dbeda0570c0257e05a864b8ecf2912e6e22816e2dcb1","observation_id":"1729cd0d-0cb8-4744-a931-dbef2d189e44","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Low-complexity learning of linear quadratic regulators from noisy data,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:bc1b6a4b0dc70ce12cde4ac4a9a2d06c2bd475ad226a6212dea8b3a2c3a164dc","observation_id":"db11677a-85d5-4a60-b390-8393d9ed961f","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Bridging direct and indirect data-driven control formulations via regularizations and relaxations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:0d7a308c4010f0e0dcd120695b0c2eab5e936d6b449caf99414ab72c34562b85","observation_id":"967dfa89-6258-4c28-a96a-1fbf5b0ca248","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Direct data-driven discounted infinite hori- zon linear quadratic regulator with robustness guarantees,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:df78b9768d6545dca9f7ade39709b4f160f4d203389ed17f929edd8f7099e5f6","observation_id":"ab07ce93-ffc0-4830-af95-0d1653d72850","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Natural gradient works efficiently in learning,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:33ef85a98573c3ac81347a933854f87cd2b4e20a1fd7bd7cdd788d0b7d1829f9","observation_id":"d105f1dc-1822-42e2-bc53-55f51973f6d5","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14871","last_updated":"2024-10-04T07:17:37Z","snapshot_observed_at":"2026-08-16T14:24:14.592669Z","submitted_at":"2024-01-26T13:58:35Z","title":"Data-Enabled Policy Optimization for Direct Adaptive Learning of the LQR","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14871","snapshot_observed_at":"2026-07-12T02:49:16.884263Z","title":"Data-enabled policy optimization for direct adaptive learning of the lqr,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"cited_paper":"/paper/2401.14871","citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:5e09dd52bddbe8132a3810e052359e22b514f874a418fd709b886881caed9fbd","observation_id":"c4bd93a2-145e-4548-ba6f-12eb41c61175","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"A new approach to linear filtering and prediction problems,","venue":null,"work_id":null,"year":1960},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:9121c77576ff7b2b3c200eb4fc7a7688f79c8f3457c1b67e4c41e19343759e86","observation_id":"5a0ceff3-b952-42b7-acd4-3733b12f9fda","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Blanchini and S","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:68c3368cf8b8c217776e1f0ed360ad06e613c120fbb285c075938a1151a37048","observation_id":"3c310d80-c8d2-4521-bb89-f75c9d3c1328","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Covariance control theory,","venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:a16cc1b0e7abe9c7b43017832bd0bec08648a24e7b4bfc12b6eb3d54e1e16ded","observation_id":"26356c0e-86ce-44e1-b2b6-5aa8639098b0","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"A data-driven riccati equation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:64220a87fb2ed34a804ec47faa8fd7fc40e7f9695179fcb6253166e80dcd6475","observation_id":"7c5e2803-e3cc-40b2-b6d0-b68af76aadfb","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Linear quadratic dual control,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:2ab4da2ffe82af3df8561542fa6e916d7f2013e1f7bf42428349b207360d101d","observation_id":"5af2055c-3890-4061-b508-ef369af20b78","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.07937","last_updated":"2020-03-26T17:54:55Z","snapshot_observed_at":"2026-08-17T15:59:35.214844Z","submitted_at":"2020-03-17T20:59:17Z","title":"Finite-time Identification of Stable Linear Systems: Optimality of the Least-Squares Estimator","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.07937","snapshot_observed_at":"2026-07-12T02:49:16.884263Z","title":"Finite-time identification of stable linear systems: Optimality of the least-squares estimator,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"cited_paper":"/paper/2003.07937","citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:49714feb188f09a876ca321625765142606f5ab5af6763a81c763e7dbdecd6f7","observation_id":"296dcdcc-8d62-480e-a682-f844a8fff094","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Learning without mixing: Towards a sharp analysis of linear system identifi- cation,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:5bc8d5fbdd48ff5200950cf59c057fb25f8772c68a27d580f3633b03aee4a758","observation_id":"0204beb7-66f4-4886-97b6-9481e6fae5c7","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"CVXPY: A Python-embedded modeling lan- guage for convex optimization,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:65a7c02498f9db044bb7f35068d14d8c010ea3eab5273213f489b9939aef5a68","observation_id":"5ec75026-d4bc-4ed8-9317-4b3e98bec966","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"A rewriting system for convex optimization problems,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:989529be88474f357e56c8b8c0221386f94bbed48fc1795f7f8702c8f0f84489","observation_id":"23bc8143-3594-4f1f-af25-5adc2d2ffb8b","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"ApS,MOSEK Optimizer API for Python 9.3.22, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:47d7a02921d8decab5a426c629051efbb4f5daa31c4171dd65576af0201b6a4e","observation_id":"826275d0-1cb9-430b-8379-72031119219f","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Finite-time pure pursuit guidance control of a four mecanum wheeled mobile robot with active disturbance rejection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:3c51799faf75fe515d349679d0c3818f4820345590f2cde8f1468f2ad0d41dbe","observation_id":"1b010dfb-e5ee-44d9-9596-d6b606350341","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Path-following control of mecanum-wheels omnidirectional mobile robots using nonsingular terminal sliding mode,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:8a724e46c3e8d48bff8e33948b0a0c067de263bad24e5aad1515891d24fdc422","observation_id":"c57dfc4b-5b0d-4e23-ac25-bc80204f5065","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","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":"2026-07-12T02:49:16.884263Z","title":"Kinematic modeling for feedback control of an omnidirectional wheeled mobile robot,","venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-12T02:49:16.884263Z"},"links":{"citing_paper":"/paper/2607.03393"},"observation_digest":"sha256:50b98cb02d405074152ce6490f2423a73af4ab635d5b2480268d42e2dd6e2507","observation_id":"345bd967-b6ec-4bf4-97b1-e4bac67baf47","resolution":{"observed_at":"2026-07-12T02:49:16.884263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.03393","last_updated":"2026-07-03T14:51:09Z","latest_version":1,"primary_category":"eess.SY","snapshot_observed_at":"2026-08-17T08:49:29.393016Z","submitted_at":"2026-07-03T14:51:09Z","title":"Direct Data Driven Natural Gradient Descent for Control"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":28,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":28},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2607.03393."}