{"as_of":"2026-08-22T06:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fd32aea349aa4d35de3fdcb707e3e52e635ddb552a272dfc2b1dc9e244678c63","coverage":[{"denominator":94,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":94,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:05:23.841043Z","state":"measured"},{"denominator":95,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":95,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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":"2026-08-03T23:19:58.363966Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.13710","snapshot_observed_at":"2026-08-03T23:19:58.363966Z","title":"Gradient-normalized smoothness for optimization with approximate Hessians.arXiv preprint arXiv:2506.13710, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.07341","last_updated":"2026-07-22T13:41:28Z","snapshot_observed_at":"2026-08-16T22:38:14.595829Z","submitted_at":"2025-11-10T17:42:46Z","title":"Universal Reduced-Operator Method and High-Order Global Curvature Bounds","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T23:19:58.363966Z"},"links":{"cited_paper":"/paper/2506.13710","citing_paper":"/paper/2511.07341"},"observation_digest":"sha256:3c61ab5c419549e5b3ef52a1006739dbf3495c18609dadeb990a2c69e76bbb30","observation_id":"4637c052-00eb-4fae-beb1-9c1131479444","resolution":{"observed_at":"2026-08-03T23:19:58.363966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.13710/citation-record","integrity":"/paper/2506.13710/integrity","json":"/paper/2506.13710/citation-record.json","paper":"/paper/2506.13710"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:23.503693Z","title":"Inexact tensor methods and their application to stochastic convex optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.503693Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:1f7578f57c0fac33563b1921e9f2c03306eef783cbd347343afe78787789a1cc","observation_id":"33cc48c2-fc97-411a-831c-11bb3deae0d8","resolution":{"observed_at":"2026-08-15T20:05:23.503693Z","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":"2026-08-15T20:05:23.508105Z","title":"Rethinking Gauss-Newton for learning over-parameterized models.Advances in neural information processing systems, 36:33379– 33402, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.508105Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:1cf47d751b8c26a2911aa06745939f512518cbf0b2656b4d0a1445275c2647a1","observation_id":"4bbf89bb-6876-4699-97be-ba4925446791","resolution":{"observed_at":"2026-08-15T20:05:23.508105Z","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":"2026-08-15T20:05:23.511570Z","title":"Gradient descent converges linearly for logistic regression on separable data","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.511570Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:6e142debe6cdb32d29e25526679b00e4b6d2557795c65583deb5df46c34f6500","observation_id":"d519f34e-916f-49d8-8c76-101138eff041","resolution":{"observed_at":"2026-08-15T20:05:23.511570Z","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":"2026-08-15T20:05:23.514889Z","title":"Self-concordant analysis for logistic regression","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.514889Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:3ee7dfd27abf75f125cfaaee9f99d267a67e33ffffc9c613043fba9426d918f1","observation_id":"70c81930-a057-4d95-beef-94af7afeb36d","resolution":{"observed_at":"2026-08-15T20:05:23.514889Z","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":"2026-08-15T20:05:23.518258Z","title":"A descent lemma beyond Lipschitz gradient continuity: first-order methods revisited and applications.Mathematics of Operations Research, 42(2):330–348, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.518258Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:29f51759904823000dfd1d3c280312966b459f57ec230434f6586a44f2377717","observation_id":"c4d6a485-c5c2-4038-be2b-95f1662de287","resolution":{"observed_at":"2026-08-15T20:05:23.518258Z","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":"2026-08-15T20:05:23.521767Z","title":"Worst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularized models.Mathematical Programming, 163:359–368, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.521767Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:0a3c1c1c50f21f8be7b7ff24c7f3a9660537b44031b4bd8e472a6baf55e92ab7","observation_id":"faa2183c-99f3-48c7-a365-04cdbad343e7","resolution":{"observed_at":"2026-08-15T20:05:23.521767Z","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":"2026-08-15T20:05:23.525268Z","title":"Optimal and adaptive Monteiro-Svaiter acceleration.Advances in Neural Information Processing Systems, 35:20338–20350, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.525268Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:2577b1fa5dd8e72466b8b0a41f5cf99d2f28042678228e648afafea40224335b","observation_id":"cbc6b794-438f-49a8-9170-945a89d37f0f","resolution":{"observed_at":"2026-08-15T20:05:23.525268Z","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":"2026-08-15T20:05:23.529505Z","title":"Acceleration with a ball optimization oracle.Advances in Neural Information Processing Systems, 33:19052–19063, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.529505Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:26f4154fac71a7890705e4f728837586803798ffa8651cdab587287099b9e3be","observation_id":"000cc47f-f6c0-4c66-8e00-20f02e431960","resolution":{"observed_at":"2026-08-15T20:05:23.529505Z","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":"2026-08-15T20:05:23.533419Z","title":"Adaptive cubic regularisation methods for unconstrained optimization","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.533419Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:60a34c4e945af979c45cf3453dc4c1d09ded8febaf941976340cd2ed79056af6","observation_id":"b8b411f2-b4fd-4998-afc8-5f12144d098c","resolution":{"observed_at":"2026-08-15T20:05:23.533419Z","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":"2026-08-15T20:05:23.537510Z","title":"Adaptive cubic regularisation methods for unconstrained optimization","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.537510Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:2c8b65f424bb4dd738010f766a3edd10b832221ad321a1259497c4f47b6b699f","observation_id":"89bdded2-26cc-4a0d-b636-19dc897edf42","resolution":{"observed_at":"2026-08-15T20:05:23.537510Z","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":"2026-08-15T20:05:23.541614Z","title":"On the oracle complexity of first- order and derivative-free algorithms for smooth nonconvex minimization.SIAM Journal on Optimization, 22(1):66–86, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.541614Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:8ff7749af897d389f976c729f1f653231d60e9a8aee18b65761f6f501d3c8892","observation_id":"1e15c26d-3c8b-4a70-8a17-0281fcb199c6","resolution":{"observed_at":"2026-08-15T20:05:23.541614Z","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":"2026-08-15T20:05:23.546674Z","title":"Gould, and Philippe L","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.546674Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:0418b0b630087315ac09eca748b146212fd5532ebbbd93a3361dd0cf1c6de592","observation_id":"5964b363-c63e-4039-94ad-b8aa54ba5c77","resolution":{"observed_at":"2026-08-15T20:05:23.546674Z","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":"2026-08-15T20:05:23.550525Z","title":"Universal regularization methods: varying the power, the smoothness and the accuracy.SIAM Journal on Optimization, 29(1):595– 615, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.550525Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:46567240eb1bc604bbba6c7b01cb2421b055212455ff3fb8a30e276c4b47f73c","observation_id":"ac04ab4a-f928-4916-bb07-e52d258b301f","resolution":{"observed_at":"2026-08-15T20:05:23.550525Z","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":"2026-08-15T20:05:23.554136Z","title":"Global convergence rate analysis of unconstrained optimization methods based on probabilistic models.Mathematical Programming, 169:337– 375, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.554136Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:f29bb8a67938df050a854313dd4d73bd3b7f4493c4e4930dce02e4768dce5a6e","observation_id":"ea8edd39-f06d-4404-ab00-2324f8d94c1c","resolution":{"observed_at":"2026-08-15T20:05:23.554136Z","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":"2026-08-15T20:05:23.557867Z","title":"Libsvm: A library for support vector machines.ACM Trans","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.557867Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:8f8b4cc609490da353e7718d86daa881d3823b5ce8f5b6d7113e0158e4b99cba","observation_id":"3e4b9eba-daa4-4eb6-83bf-99d902a421de","resolution":{"observed_at":"2026-08-15T20:05:23.557867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11962","last_updated":"2025-12-17T19:13:09Z","snapshot_observed_at":"2026-08-20T09:44:52.140229Z","submitted_at":"2023-02-23T12:18:28Z","title":"Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11962","snapshot_observed_at":"2026-08-15T20:05:23.561534Z","title":"Unified convergence theory of stochastic and variance-reduced cubic Newton methods.arXiv preprint arXiv:2302.11962, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.561534Z"},"links":{"cited_paper":"/paper/2302.11962","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:a19f3687f2f403186e17242f16a8f51f48da9b8bd228bbf839361cff45692614","observation_id":"ad5a9d35-63b3-49f7-a88f-8c82c1eca75c","resolution":{"observed_at":"2026-08-15T20:05:23.561534Z","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":"2026-08-15T20:05:23.565674Z","title":"SIAM, 2000","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.565674Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:b11e28c3747fa700f1ad56af5800a5df86c137cccad382a9e34326112e9db6e3","observation_id":"3fd22ec8-858a-4aac-b011-0431e940399d","resolution":{"observed_at":"2026-08-15T20:05:23.565674Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.876143Z","title":"Quasi-Newton methods, motivation and theory.SIAM review, 19(1):46–89, 1977","venue":null,"work_id":"b8b90e76-4623-4eae-8be0-3cc5c258bfe0","year":1977},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.569302Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:d4f21043eb93d58f0c92aea716a0552402269b77201f5be198a5d4a743028868","observation_id":"3cf995c8-428b-42df-b391-e3d88e810f99","resolution":{"observed_at":"2026-08-15T20:05:24.880709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2308.14742","last_updated":"2023-08-28T17:43:04Z","snapshot_observed_at":"2026-08-18T10:04:05.040398Z","submitted_at":"2023-08-28T17:43:04Z","title":"Minimizing Quasi-Self-Concordant Functions by Gradient Regularization of Newton Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.14742","snapshot_observed_at":"2026-08-15T20:05:23.572938Z","title":"Minimizing quasi-self-concordant functions by gradient regularization of Newton method.arXiv preprint arXiv:2308.14742, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.572938Z"},"links":{"cited_paper":"/paper/2308.14742","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:57bc3b0363996af6c124a3a0da6ef9f3cc8fc90d8bb8eec9e464c608931280cd","observation_id":"29d90483-c6af-4890-aa45-26ce01e5dd62","resolution":{"observed_at":"2026-08-15T20:05:23.572938Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.857889Z","title":"First and zeroth-order implementations of the regularized Newton method with lazy approximated hessians.Journal of Scientific Computing, 103(1):32, 2025","venue":null,"work_id":"f0aaa410-6f9f-447d-9268-ba555993db08","year":2025},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.577061Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:2eab8e47da18b86f026aaa95f1977d37d50153ee34037f70e883c775f190ba22","observation_id":"26aab011-cf16-4d3f-bc75-8cf48d3f8a26","resolution":{"observed_at":"2026-08-15T20:05:24.863512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.841913Z","title":"Super-universal regularized Newton method.SIAM Journal on Optimization, 34(1):27–56, 2024","venue":null,"work_id":"746c2952-a2c0-43cb-b99a-ca860aa5ffed","year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.580408Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:be81b4f119f4f0bfcfd38e6d4dc69a655d91d5d88c388fdeadd9a7a0e7961dbc","observation_id":"c8f84695-ee68-4e91-b2c3-f6d52ffa1eeb","resolution":{"observed_at":"2026-08-15T20:05:24.846418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.828691Z","title":"Minimizing uniformly convex functions by cubic regulariza- tion of Newton method.Journal of Optimization Theory and Applications, 189(1):317–339, 2021","venue":null,"work_id":"e4a36441-6eca-4df0-9cca-2b0390a78cfa","year":2021},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.583864Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:4efdeee7b8729ad482455f5c96cb6458b8a88e1c61d63ef54a9bf27fb58e7195","observation_id":"816d381e-1e3b-4030-98d5-953bf7f797b3","resolution":{"observed_at":"2026-08-15T20:05:24.832621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.816787Z","title":"Gradient regularization of Newton method with Bregman distances.Mathematical Programming, pages 1–25, 2023","venue":null,"work_id":"7ffb66dd-7077-439e-b13d-79a27caff319","year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.587312Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:ce16549bbf22aa05d323d0d8fb78fba13994dc897e456cf6dc1e8542ec0516fd","observation_id":"c6f69551-9a40-4a2e-8875-53c9cd892b4d","resolution":{"observed_at":"2026-08-15T20:05:24.821141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.803283Z","title":"Polynomial preconditioning for gradient methods, 2023","venue":null,"work_id":"4ed682b5-51de-4135-8e26-aebbf18ad6a4","year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.590902Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:98dc0066bed84bfbbe3758988b95ccf054b137b4b1f170a50a576c4130560831","observation_id":"f3f0aa94-f402-46f3-95c5-52a1d3080c88","resolution":{"observed_at":"2026-08-15T20:05:24.807458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.790209Z","title":"Spectral preconditioning for gradient methods on graded non-convex functions","venue":null,"work_id":"19f643a0-6aed-418a-9649-48d7ae8e8199","year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.594356Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:b3238844a8429e72ac51b1a151a3e0ba56ad57cacedf14b3a0668b0b978597dd","observation_id":"d13ee338-2a1c-4789-b70a-cf8b2fe8a14b","resolution":{"observed_at":"2026-08-15T20:05:24.795003Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.778010Z","title":"Sharp analysis of stochastic optimization under global Kurdyka-Lojasiewicz inequality.Advances in Neural Information Processing Systems, 35:15836–15848, 2022","venue":null,"work_id":"b10d0d81-be5f-498b-befe-466c32da070b","year":2022},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.597787Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:d1423b92c4056c96ada0a5076eb57e4bab3731de1e4ea6fb5afc4a4cba92b854","observation_id":"abd4e59a-489a-43ab-b829-850b1c09fd57","resolution":{"observed_at":"2026-08-15T20:05:24.781597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.765413Z","title":"M-fac: Efficient matrix-free approximations of second-order information.Advances in Neural Information Processing Systems, 34:14873– 14886, 2021","venue":null,"work_id":"7f50b2fe-cc2c-45b4-bad0-cd178041ad08","year":2021},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.602034Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:24c7f1526f926555ceb4e73b86040859a7886b5a1cee772d1c046de33ad6f240","observation_id":"3e3ab534-e3ae-4f2b-a647-a9afe459ee6a","resolution":{"observed_at":"2026-08-15T20:05:24.769237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2209.04170","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.072571Z","title":"Randomized subspace regularized Newton method for unconstrained non-convex optimization.arXiv preprint arXiv:2209.04170, 2022","venue":null,"work_id":"a9976773-c7dd-49c8-bd7d-ca4a9a688f82","year":2022},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.605439Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:492246ae9533a7f153c7b866cb80c0366bf983a5246223d2058c49618b3459ed","observation_id":"842828d5-33f6-4255-a409-ef3ae15ff672","resolution":{"observed_at":"2026-08-15T20:05:24.080282Z","resolver_source":"raw_fallback","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":{"arxiv_id":"2409.14989","last_updated":"2024-12-25T15:02:32Z","snapshot_observed_at":"2026-08-18T18:58:07.563598Z","submitted_at":"2024-09-23T13:11:37Z","title":"Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.14989","snapshot_observed_at":"2026-08-15T20:05:23.608717Z","title":"Methods for convex (l_0,l_1) -smooth optimization: Clipping, acceleration, and adaptivity.arXiv preprint arXiv:2409.14989, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.608717Z"},"links":{"cited_paper":"/paper/2409.14989","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:24f1536cce2ff0685564ff83e8d9216a189cd6c4a3e4077f3b238c1d1faa2795","observation_id":"b97c589f-50c7-4d4b-8b82-dba8b1c38848","resolution":{"observed_at":"2026-08-15T20:05:23.608717Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.753213Z","title":"Rsn: randomized subspace Newton.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"4f1dbd08-76aa-4e6b-bd97-433bba88e72b","year":2019},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.612197Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:10b67e9b109d5e959a62f691489c8172fed855bfadd32fd5ec971f366e27baf6","observation_id":"885aa9b0-22d3-4ba7-9921-cba30e344a52","resolution":{"observed_at":"2026-08-15T20:05:24.757438Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.735121Z","title":"A cubic regularization of newton’s method with finite difference hessian approximations.Numerical Algorithms, pages 1–24, 2022","venue":null,"work_id":"5efb0ea7-a573-4f0c-938b-6e30c662eaa7","year":2022},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.615275Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:966569f8eac2bf134f88bb3edd4d30fa9cb54c3223ef7d8708a88dd51213187b","observation_id":"ad4c9556-8068-4734-ad0a-6a97517cb7bc","resolution":{"observed_at":"2026-08-15T20:05:24.739850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.722353Z","title":"On inexact solution of auxiliary problems in tensor methods for convex optimization.Optimization Methods and Software, 36(1):145–170, 2021","venue":null,"work_id":"3a081224-167a-4ead-af6e-0750acb7feed","year":2021},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.618505Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:387100596359c2257ccc70bc406cfc3b64eb895a93fc5defde612d21c84632db","observation_id":"3cd5eb52-bdbb-4abd-8ea9-e85a182015ce","resolution":{"observed_at":"2026-08-15T20:05:24.726304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2505.04807","last_updated":"2026-02-17T11:09:26Z","snapshot_observed_at":"2026-08-18T18:57:36.150605Z","submitted_at":"2025-05-07T21:16:11Z","title":"A Fast Newton Method Under Local Lipschitz Smoothness","version":2},"cited_work":{"arxiv_id":"2505.04807","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.04807","snapshot_observed_at":"2026-08-15T20:05:23.994202Z","title":"A Fast Newton Method Under Local Lipschitz Smoothness","venue":"math.OC","work_id":"48a561ae-47f0-4906-ba25-a2f0c4e1e346","year":2025},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.621390Z"},"links":{"cited_paper":"/paper/2505.04807","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:1db781cb1f6064f9c6c9feda1016eb420d83bd4e33f1313f8760d4dd2c945e9d","observation_id":"998dcdc1-687d-4d7d-9f3c-f359ee471c4b","resolution":{"observed_at":"2026-08-15T20:05:23.999283Z","resolver_source":"local_arxiv","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.711053Z","title":"The modification of Newton’s method for unconstrained optimization by bounding cubic terms","venue":null,"work_id":"47ee7c54-965c-4f23-9e36-fa6902c8ed67","year":1981},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.624738Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:76cba7663b3809de78abd40d7dee82c919c6a233894931367cb755810863fcab","observation_id":"28cce406-c302-48cd-8b7c-e52e75260a12","resolution":{"observed_at":"2026-08-15T20:05:24.715010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.698680Z","title":"On Nesterov’s nonsmooth Chebyshev–Rosenbrock functions.Nonlinear Analysis: Theory, Methods & Applications, 75(3):1282–1289, 2012","venue":null,"work_id":"17e6951e-2b30-4f89-a734-644ab4fa2713","year":2012},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.627779Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:3064f1abadae7db148a90cdfd40913d4232c322e61dca608532ed0d88fa38854","observation_id":"b04b39b5-4bd4-44c1-b8c6-6a9da5d81efb","resolution":{"observed_at":"2026-08-15T20:05:24.703219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.686658Z","title":null,"venue":null,"work_id":"9b305802-2b97-483a-b8b1-ea144c14d521","year":2012},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.630481Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:40b6c60b5a9c77120859c2331bcb64037bb65f3160873efea7fa9a1528da7213","observation_id":"4b59acf2-f48b-4388-a24a-6de37ecbd22f","resolution":{"observed_at":"2026-08-15T20:05:24.690254Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.675078Z","title":"Sketch-and-project meets Newton method: Global O(1/kˆ2) convergence with low-rank updates","venue":null,"work_id":"27f5bc32-7200-459c-944e-54ff4ab88c36","year":2025},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.634093Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:03925e03b6ecc2eb393af8422bef2b6e5ef332080f95d96adf683e5acabadfa5","observation_id":"d4e3a2f7-1102-44e6-930d-8d607673bc47","resolution":{"observed_at":"2026-08-15T20:05:24.679193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2405.18926","last_updated":"2024-11-20T08:22:59Z","snapshot_observed_at":"2026-08-18T18:58:09.701761Z","submitted_at":"2024-05-29T09:31:45Z","title":"Newton Method Revisited: Global Convergence Rates up to $\\mathcal {O}\\left(k^{-3} \\right)$ for Stepsize Schedules and Linesearch Procedures","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.18926","snapshot_observed_at":"2026-08-15T20:05:23.637976Z","title":"Newton method revisited: Global convergence rates up to o(k-3) for stepsize schedules and linesearch procedures.arXiv preprint arXiv:2405.18926, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.637976Z"},"links":{"cited_paper":"/paper/2405.18926","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:436fecce4210b139d03225029c967cc24a40b9be8fb6d6f898086c083631f13c","observation_id":"151b1704-b32a-41d0-995a-c22513008778","resolution":{"observed_at":"2026-08-15T20:05:23.637976Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.662164Z","title":"On Nesterov’s smooth Chebyshev–Rosenbrock function.Optimization Methods & Software, iFirst, 12 2011","venue":null,"work_id":"9f3ef7e7-b80d-41ef-a412-ec3ee0b382b8","year":2011},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.641786Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:11177f7377ea06ac313028d06482b3f6bfc3e72270bb2c9000a2a1c27075bbf5","observation_id":"ec8d624e-76d3-483b-bfb0-a2499b137973","resolution":{"observed_at":"2026-08-15T20:05:24.666437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.649553Z","title":"Beyond nonconvexity: A universal trust-region method with new analyses.arXiv e-prints, pages arXiv–2311, 2023","venue":null,"work_id":"4a8fd3f5-c83a-4479-befe-02571a1fb20a","year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.645415Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:6f31468600147125448616d2866cee192b1c6a53ed37e529fa725ef012fdf447","observation_id":"184c69bc-a4a8-4624-936f-f7f893e8d494","resolution":{"observed_at":"2026-08-15T20:05:24.653913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2404.16731","last_updated":"2025-01-08T01:41:29Z","snapshot_observed_at":"2026-08-18T18:58:06.479588Z","submitted_at":"2024-04-25T16:41:57Z","title":"Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16731","snapshot_observed_at":"2026-08-15T20:05:23.649663Z","title":"Non-asymptotic global convergence analysis of BFGS with the Armijo-Wolfe line search.arXiv preprint arXiv:2404.16731, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.649663Z"},"links":{"cited_paper":"/paper/2404.16731","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:c95cac3cc75f67b3bbd1a8bcfdbddf16cc784698b3994a18610680068c1a4db2","observation_id":"37893271-1d19-4f92-9637-039828b9bc14","resolution":{"observed_at":"2026-08-15T20:05:23.649663Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.634048Z","title":"Non-asymptotic superlinear convergence of standard quasi- Newton methods.Mathematical Programming, 200(1):425–473, 2023","venue":null,"work_id":"175f5b43-afa8-4985-ac08-6e3f822137c6","year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.653477Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:a3ec19bf1f69af8fa6d41a76f6bc21c8e7f4ac5983edfba333eb62a08c437a7c","observation_id":"418ae7f7-477f-4a8c-98fc-40b94aa6eb03","resolution":{"observed_at":"2026-08-15T20:05:24.639638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T20:05:23.657106Z","title":"Spinger, 2006","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.657106Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:1c7e03f590b3c182b8fb868a9dd8436080462d945c246cf73e660de61cd728a6","observation_id":"0def4ffa-5026-403c-a240-ac8370a3c11c","resolution":{"observed_at":"2026-08-15T20:05:23.657106Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.609838Z","title":"Moreau envelope and proximal-point methods under the lens of high-order regularization, 2025","venue":null,"work_id":"9590e2ea-877d-4aae-9fa0-8021da200c05","year":2025},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.660727Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:ecee14fc38a2fef977d1055e97e39768b57e35815863eb8316e646810e9bc2ac","observation_id":"2a77cb49-0d5a-4b6a-acc8-1a3b53a91272","resolution":{"observed_at":"2026-08-15T20:05:24.615431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2302.04987","last_updated":"2023-05-29T01:06:27Z","snapshot_observed_at":"2026-08-16T22:36:43.868180Z","submitted_at":"2023-02-10T00:21:14Z","title":"Cubic Regularization is the Key! The First Accelerated Quasi-Newton Method with a Global Convergence Rate of $O(k^{-2})$ for Convex Functions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.04987","snapshot_observed_at":"2026-08-15T20:05:23.664212Z","title":"Cubic regularization is the key! the first accelerated quasi-Newton method with a global convergence rate of O(kˆ-2) for convex functions.arXiv preprint arXiv:2302.04987, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.664212Z"},"links":{"cited_paper":"/paper/2302.04987","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:9f11dafff8feb1fb2568f20cf7274100507b6b77d68130d0448c48ec6d7e4245","observation_id":"47e0f25d-80a1-4a67-a690-fdadb5bd9eb5","resolution":{"observed_at":"2026-08-15T20:05:23.664212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00413","last_updated":"2018-06-01T15:58:54Z","snapshot_observed_at":"2026-08-20T09:42:48.380641Z","submitted_at":"2018-06-01T15:58:54Z","title":"Global linear convergence of Newton's method without strong-convexity or Lipschitz gradients","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.00413","snapshot_observed_at":"2026-08-15T20:05:23.668547Z","title":"Global linear conver- gence of Newton’s method without strong-convexity or Lipschitz gradients.arXiv preprint arXiv:1806.00413, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.668547Z"},"links":{"cited_paper":"/paper/1806.00413","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:2ab34ac6d20584f68def97f185663b05944b1a220cb7cdd619ee27ad979fe859","observation_id":"a59f42a5-c1b4-41e0-9f19-cb2339d993ac","resolution":{"observed_at":"2026-08-15T20:05:23.668547Z","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":"2026-08-15T20:05:23.673124Z","title":"Revisiting gradient clipping: Stochastic bias and tight convergence guarantees","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.673124Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:1baf89bd164869030d7de54413d6347ccb0c4ed5b011dedc73593a40944d0cf0","observation_id":"ac818394-5c91-47c2-89e5-f0629df8c8f2","resolution":{"observed_at":"2026-08-15T20:05:23.673124Z","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":"2026-08-15T20:05:23.676689Z","title":"Limitations of the empirical fisher approximation for natural gradient descent.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.676689Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:186a68f2cf59d72687eee67d75ffe9ade5ca70b163f57b2af47ba78dc7450ada","observation_id":"706a6e74-544c-46a0-8a49-8a9152e3524e","resolution":{"observed_at":"2026-08-15T20:05:23.676689Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.581049Z","title":"Anisotropic proximal gradient.Mathematical Pro- gramming, pages 1–45, 2025","venue":null,"work_id":"e647b4b8-57ab-4170-af50-0ca6b9e2af1e","year":2025},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.680265Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:e0d118806b163afada8261fd1095595ec6465a1ce51399cf0337f8ef94cfeb44","observation_id":"7d8990e0-2b76-4620-b9fe-64cbda07a7f8","resolution":{"observed_at":"2026-08-15T20:05:24.584997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.567697Z","title":"Convex and non- convex optimization under generalized smoothness.Advances in Neural Information Processing Systems, 36:40238–40271, 2023","venue":null,"work_id":"66d6206f-15a0-4c53-8c66-29dd53ba5aa3","year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.683710Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:d86c70c9026b6396c745e9e83cb2c9dc99b74167863fac4cae3d87ea30ef81b7","observation_id":"4b257ac7-0fe7-4776-96a0-1d4ce3bd40b0","resolution":{"observed_at":"2026-08-15T20:05:24.571899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T20:05:23.687961Z","title":"Relatively smooth convex optimization by first-order methods, and applications.SIAM Journal on Optimization, 28(1):333–354, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.687961Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:d90901332cd965d80d23188842672b7200bd1bcb2cd9e945e0c5bc650fab7209","observation_id":"f004eb03-5232-4988-859a-86a2ea23f883","resolution":{"observed_at":"2026-08-15T20:05:23.687961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06159","last_updated":"2023-10-09T21:16:57Z","snapshot_observed_at":"2026-08-20T09:44:17.389778Z","submitted_at":"2023-10-09T21:16:57Z","title":"Provably Accelerating Ill-Conditioned Low-rank Estimation via Scaled Gradient Descent, Even with Overparameterization","version":1},"cited_work":{"arxiv_id":"2310.06159","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.06159","snapshot_observed_at":"2026-08-15T20:05:23.921924Z","title":"Provably Accelerating Ill-Conditioned Low-rank Estimation via Scaled Gradient Descent, Even with Overparameterization","venue":"cs.LG","work_id":"f08affac-ef5e-4942-89c1-f19586a84ba2","year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.691666Z"},"links":{"cited_paper":"/paper/2310.06159","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:939efae54db86c7168b1ad1486b1a1c25b8ebb88e45ede430d32f0fe8a2535fb","observation_id":"99295052-3810-4e3d-b49b-a398093292cf","resolution":{"observed_at":"2026-08-15T20:05:23.928393Z","resolver_source":"local_arxiv","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":"2026-08-15T20:05:23.695482Z","title":"New insights and perspectives on the natural gradient method.Journal of Machine Learning Research, 21(146):1–76, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.695482Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:60e053459cb5ca146361c7629848b4711626b7135c8db92ebf67322a63f89938","observation_id":"d2f1a6da-890b-4ed9-ae78-3a6c577a91f5","resolution":{"observed_at":"2026-08-15T20:05:23.695482Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.536595Z","title":"Inverting modified matrices","venue":null,"work_id":"854a7a77-3259-4b8b-a431-3065a1029405","year":1950},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.698505Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:79cbd35e4015d0fa9fae8ee4b27d9d0ea516e8c2a1dee2b5d959fec9a407ab69","observation_id":"d6ce282d-22d7-45e4-9c5a-4c26f237e0b2","resolution":{"observed_at":"2026-08-15T20:05:24.541000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.523665Z","title":"Regularized Newton method with globalO(1/k2) convergence.SIAM Journal on Optimization, 33(3):1440–1462, 2023","venue":null,"work_id":"1d975683-e51b-4fa4-b9e9-56d20ab4f2a0","year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.701493Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:f880b4d2c7bdeff420a00be3e0e7a86738853c62f22ceea6c2b913848599c234","observation_id":"66c9b4f1-b18b-407d-b11e-e8862aab8891","resolution":{"observed_at":"2026-08-15T20:05:24.527859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.509266Z","title":"Problem complexity and method efficiency in optimization","venue":null,"work_id":"9cd7af44-a682-43d0-945c-83dcd021fe6d","year":1983},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.704280Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:031778d1498cf22de8e65fb7688f1005070d25ad126b2b3247451688ab4224b5","observation_id":"64b7875b-47ea-4e79-8b3c-982d12260190","resolution":{"observed_at":"2026-08-15T20:05:24.514377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.494872Z","title":"Modified Gauss–Newton scheme with worst case guarantees for global perfor- mance.Optimisation methods and software, 22(3):469–483, 2007","venue":null,"work_id":"eb9ca5d8-e614-4b26-b51a-74781e95d203","year":2007},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.707168Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:76082d0ea6766af716edf00a3102d92114473b29f121022b1960e26a01904042","observation_id":"809bc7a0-6af9-4a31-a48a-7af768e720f3","resolution":{"observed_at":"2026-08-15T20:05:24.499738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.478554Z","title":"Universal gradient methods for convex optimization problems.Mathematical Programming, 152(1):381–404, 2015","venue":null,"work_id":"2edd7182-0b55-458d-876c-a89a766ff098","year":2015},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.709862Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:933296effd6a4be0714dfb430d8a3e95f01acc8e31548da8ce329ecb3d414f18","observation_id":"5bda79ba-60ad-480d-8318-6eacfbd8f95a","resolution":{"observed_at":"2026-08-15T20:05:24.484464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T20:05:23.713553Z","title":"Springer, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.713553Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:9175a5f5fd3ebc6beabdd8e202b8144a35ab8a935d701a32ea9df46d1138d5ea","observation_id":"1f197504-1d29-4b6f-811a-8c23079772df","resolution":{"observed_at":"2026-08-15T20:05:23.713553Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.450064Z","title":"Implementable tensor methods in unconstrained convex optimization.Mathe- matical Programming, 186:157–183, 2021","venue":null,"work_id":"d7c9ad0a-9214-4393-85ea-4dffab2edd7c","year":2021},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.716940Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:a9f3c2972d7ad6f98d7d1e446696a8a2b8822ec641cbf21b2cad4f8021ae59c3","observation_id":"7c98357e-7c2b-4232-b96f-7365f6c90ede","resolution":{"observed_at":"2026-08-15T20:05:24.456643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T20:05:23.720205Z","title":"Superfast second-order methods for unconstrained convex optimization.Journal of Optimization Theory and Applications, 191:1–30, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.720205Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:fa92ddf37dabe92b4535db245b34451f8d930acb5b759a2f2ca0950061185d4f","observation_id":"adb9b673-a760-45d2-8bb1-e54a4d377afd","resolution":{"observed_at":"2026-08-15T20:05:23.720205Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.428544Z","title":"Primal subgradient methods with predefined step sizes.Journal of Optimization Theory and Applications, pages 1–33, 2024","venue":null,"work_id":"81980482-38c1-4bff-bfc0-bd83f7527eaa","year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.723442Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:9b765501dc6e68817923cf8f362fc0da06ebb843b58fc80526b3a0f93e7743c3","observation_id":"00435c1b-d5c6-45e3-9e3f-37b8784883c9","resolution":{"observed_at":"2026-08-15T20:05:24.432848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.416020Z","title":"SIAM, 1994","venue":null,"work_id":"5789d8e6-9a1b-44d7-9d38-8708248a23c8","year":1994},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.726794Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:e341175560c28927bc5a07d2af1bc0275df19fa055c9c6bf410675b938404486","observation_id":"7fa613a7-c7d2-4906-9be5-5417075c675b","resolution":{"observed_at":"2026-08-15T20:05:24.420120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.403379Z","title":"Cubic regularization of newton method and its global performance.Mathematical programming, 108(1):177–205, 2006","venue":null,"work_id":"c50c6dba-c98b-43fe-8dc1-15c69fac3eb0","year":2006},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.730585Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:ecf848ccb80584f17d4909fbc619349fb7bfe8734da95ccbc34e85ea2704c2a6","observation_id":"a3c5ea79-44b4-4b42-a6dd-4587c6aa78b4","resolution":{"observed_at":"2026-08-15T20:05:24.407556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.391625Z","title":"Newton’s method and its use in optimization.European Journal of Operational Research, 181(3):1086–1096, 2007","venue":null,"work_id":"bd54e507-6bed-4fa1-b467-87bab47b2c42","year":2007},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.734189Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:4db2384ac6e37ca7d62c3e9205fb2015145a36766ccd529327ae4e2bc7234532","observation_id":"665e95a8-9326-450d-af9d-4c73f54d11fa","resolution":{"observed_at":"2026-08-15T20:05:24.395527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.380496Z","title":"Regularized Newton method for unconstrained convex optimization.Mathe- matical programming, 120:125–145, 2009","venue":null,"work_id":"9722d649-725b-4a1e-8c4f-66e00ae23a70","year":2009},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.738068Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:79e5e9a0fc5ac39a5cac4cc360b710f664777f4da6c12361d1dc9ffb5bcd16cf","observation_id":"b38381f3-fb85-42f2-b1c2-3644893684c1","resolution":{"observed_at":"2026-08-15T20:05:24.383839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.369487Z","title":"PhD thesis, PhD thesis, UCL-Université Catholique de Louvain, 2022","venue":null,"work_id":"8c905eb8-86b3-43bd-8c51-8e701afecadb","year":2022},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.741850Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:872a5b2a7e49872e11dddb7baa688dc16d8f8b028f39965ccf78d337ae8e38f1","observation_id":"479aab8e-0ba1-4780-b61e-343c81d6f491","resolution":{"observed_at":"2026-08-15T20:05:24.373452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2404.15051","last_updated":"2024-04-23T13:50:35Z","snapshot_observed_at":"2026-08-20T09:45:05.561727Z","submitted_at":"2024-04-23T13:50:35Z","title":"Global Complexity Analysis of BFGS","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.15051","snapshot_observed_at":"2026-08-15T20:05:23.745471Z","title":"Global complexity analysis of BFGS.arXiv preprint arXiv:2404.15051, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.745471Z"},"links":{"cited_paper":"/paper/2404.15051","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:86d960aa586c48327afbf4c1724c0f832a38f3543e01c9a16d58330fa0fdb585","observation_id":"9500750d-9f8f-41d5-9d83-28c156b597b1","resolution":{"observed_at":"2026-08-15T20:05:23.745471Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.357887Z","title":"New results on superlinear convergence of classical quasi-Newton methods.Journal of optimization theory and applications, 188:744–769, 2021","venue":null,"work_id":"85fa6804-4807-4117-bcd6-6a889f6a2ebe","year":2021},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.749474Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:af09b0d29ba70b097dcdeb8464080eacb63d42c453cce305d77cbc3fdc6ba22d","observation_id":"edf18fd0-f604-4766-94d4-b0bdd046f595","resolution":{"observed_at":"2026-08-15T20:05:24.361785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T20:05:23.753125Z","title":null,"venue":null,"work_id":null,"year":1960},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.753125Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:15a2f9b2b196cf01aef743af84f5fc76ed356aff4f2fddde6a119703fd49b823","observation_id":"e4acfd59-36bd-47b7-a958-c5f484a213ad","resolution":{"observed_at":"2026-08-15T20:05:23.753125Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.339391Z","title":"Adaptive quasi-Newton and Anderson acceleration framework with explicit global (accelerated) convergence rates","venue":null,"work_id":"97f83020-d02f-4e17-920a-940ce2a5b41c","year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.757217Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:b725c10ba86b5fcf3a04392944178cd7bbf98c15871bf037a74ae2b3d586726b","observation_id":"c49a54a8-738d-434d-a26c-b29e9441da2f","resolution":{"observed_at":"2026-08-15T20:05:24.343571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.327773Z","title":"Generalized self-concordant functions: A recipe for newton-type methods, 2018","venue":null,"work_id":"648f0939-79eb-4da7-824d-e50e335d0c27","year":2018},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.760711Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:1c2597568f7d4fd71e30b9a14322787dd4f6a7fe1cdda19008ca7b96fa225517","observation_id":"67f255c9-f7db-4819-acd7-5a690b6f8e2d","resolution":{"observed_at":"2026-08-15T20:05:24.331616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2412.11773","last_updated":"2025-06-27T06:34:09Z","snapshot_observed_at":"2026-08-13T08:19:14.013569Z","submitted_at":"2024-12-16T13:46:02Z","title":"Toward a Unified Theory of Gradient Descent under Generalized Smoothness","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.11773","snapshot_observed_at":"2026-08-15T20:05:23.764428Z","title":"Toward a unified theory of gradient descent under generalized smoothness","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.764428Z"},"links":{"cited_paper":"/paper/2412.11773","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:54f1d4f5e1243898a0146adc840426d085bd64b54b59414eb2e0baedabdb8e9b","observation_id":"596c37ec-7556-4be7-847c-315070f1c195","resolution":{"observed_at":"2026-08-15T20:05:23.764428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10800","last_updated":"2025-03-07T20:23:27Z","snapshot_observed_at":"2026-08-18T10:09:35.664902Z","submitted_at":"2024-10-14T17:57:33Z","title":"Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10800","snapshot_observed_at":"2026-08-15T20:05:23.768307Z","title":"Optimizing (l_0,l_1) -smooth functions by gradient methods.arXiv preprint arXiv:2410.10800, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.768307Z"},"links":{"cited_paper":"/paper/2410.10800","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:89152a2b569137722bcc54b5793517a2280a37e8701c9d895cbae7d898ba96a8","observation_id":"9c40df07-6873-486d-9c4e-09933ada79a3","resolution":{"observed_at":"2026-08-15T20:05:23.768307Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.316259Z","title":"Trust region methods for nonconvex stochastic optimization beyond Lipschitz smoothness","venue":null,"work_id":"cfff0799-e662-4b58-85ae-cc5a438315b7","year":2024},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.772244Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:cca5fe6c24876a210b0abe923a4b689871f90508c5f33d59a2691e84133b540c","observation_id":"ca009f8c-eacd-44c0-969e-2f91c5c52562","resolution":{"observed_at":"2026-08-15T20:05:24.320616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.304886Z","title":"Preconditioned gradient descent for over- parameterized nonconvex Burer–Monteiro factorization with global optimality certification","venue":null,"work_id":"af718859-bfa0-4e2f-a1e6-bc23b5b44751","year":2023},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.775703Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:e5d8a47365499bd70023256c8eb6cea6ece234ed421f2e3563b1482fc56708a2","observation_id":"df8ccd36-637d-4762-b6b6-a52df8e35d6c","resolution":{"observed_at":"2026-08-15T20:05:24.308797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"1905.11881","last_updated":"2020-02-10T22:58:53Z","snapshot_observed_at":"2026-08-14T16:25:08.350015Z","submitted_at":"2019-05-28T15:23:12Z","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11881","snapshot_observed_at":"2026-08-15T20:05:23.778640Z","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity.arXiv preprint arXiv:1905.11881, 2019","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.778640Z"},"links":{"cited_paper":"/paper/1905.11881","citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:9261da7eeab522e77db3e2f7918a0373d8cf4ba62a6f4d685301bca4a8772fe5","observation_id":"d1d151ed-d62c-4dfb-bcc9-1b5be8b4d84e","resolution":{"observed_at":"2026-08-15T20:05:23.778640Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.294392Z","title":"Cubic regularized subspace Newton for non- convex optimization","venue":null,"work_id":"7b535297-b860-4b6e-8ad3-850699d7e134","year":2025},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.781967Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:55629b5d26ed3e0274e92ef708d184b301444c4a71982ba50344066046de2c2a","observation_id":"175b6bea-5215-4ede-854e-0d7ef9459758","resolution":{"observed_at":"2026-08-15T20:05:24.298040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.283663Z","title":"SearchorExact Newton:stands for the partial case of Algorithm 1 using our adaptive search procedure (16), andH(x)≡∇ 2f(x)","venue":null,"work_id":"ac615474-ad45-483b-a71d-f81aa3f06baf","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.785244Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:4055538078c9ba3689475e935b074b8f21501a26eead54d8d89f2c10d1359b1f","observation_id":"fa7d9d8b-5bc9-4488-bd1f-fbe92e34178a","resolution":{"observed_at":"2026-08-15T20:05:24.287345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.272679Z","title":"SearchorWeighted Gauss-Newton:refers to the variant of Algo- rithm 1 with Hessian approximation of the form (13) or (19), combined with our adaptive search (16)","venue":null,"work_id":"f5d3bfc7-6882-4997-8101-d2a5305dee0f","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.788278Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:c8c582f1873292580bf7e16e734777f1be8f5625f90fc6fce4b210f6f225beb8","observation_id":"d9d3ff7b-4fe1-41bf-b536-47714b9855c7","resolution":{"observed_at":"2026-08-15T20:05:24.276445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.261854Z","title":"Search,γk = 1 Mk :denotes the Gradient-Regularized Newton Method with adaptive search as in [21], usingγk := 1 Mk andMk is chosen to satisfy the condition (17)","venue":null,"work_id":"02833f20-b68a-47c6-bf43-3eaf3f72518f","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.791310Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:537a6f4a5325cc58fd0191c5e2b0ceb679e1056a00d9725e985aa1dbf19ddfad","observation_id":"618af6b0-11de-41f3-8c9d-d0e72e6a484f","resolution":{"observed_at":"2026-08-15T20:05:24.265774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.250187Z","title":"Search,γk = ∥∇f(x k)∥∗ Mk :denotes the Gradient-Regularized Newton Method with adaptive search as in [21], usingγk := ∥∇f(xk)∥∗ Mk andMk is chosen to satisfy the condition (17)","venue":null,"work_id":"e0cc586b-6069-45a4-b04f-3700f51988fd","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.794692Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:302b9f2000a2e76861629e224613fca0c9f56190e2721d0e2f2b6542ae9f0f3c","observation_id":"2a43c2fc-0b53-47da-9bd1-0086297add24","resolution":{"observed_at":"2026-08-15T20:05:24.254120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.238489Z","title":null,"venue":null,"work_id":"22c31f88-cef4-448c-842a-b272009428b4","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.797956Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:b9c0637f445e5131cc3e8a0e50d7db55f575ab4e3cae9f91232a4812c035e270","observation_id":"18406e58-8b82-428f-bb4a-e1460d19d51a","resolution":{"observed_at":"2026-08-15T20:05:24.241986Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.228121Z","title":"To demonstrate that our theoretical findings are reflected in practice, we validate the effects observed in (Fig","venue":null,"work_id":"bfd40025-91c6-438e-a276-e73cdaf35a6f","year":2000},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.801779Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:2bccf9dbdda8320b826f6d05ee4fa51e2d5f72f47577a2e4f8fb9b1e31a98cfb","observation_id":"995902f1-dcab-440c-892a-c56665bc8f59","resolution":{"observed_at":"2026-08-15T20:05:24.231911Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.218038Z","title":null,"venue":null,"work_id":"3354fc15-8895-4787-a407-f4e22d840aea","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.805811Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:fd8062708aee9ab62e04439751b2f24e0501b76124c602521d631ca296853e3a","observation_id":"a1fa0185-f8a2-4b33-9fac-6478c1fd100a","resolution":{"observed_at":"2026-08-15T20:05:24.221559Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.205877Z","title":"In our experiments, we extend the Nesterov-Chebyshev-Rosenbrock function to (24)","venue":null,"work_id":"7581db99-12ec-4e72-8804-50a83b675b7f","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.809244Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:9803fbbe1a5d9bb6748a276febd64337c146040d1c512f1ed1399e61bf18b2f4","observation_id":"d20d16cd-3cc4-484a-b45a-84b0ebd9042b","resolution":{"observed_at":"2026-08-15T20:05:24.209671Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.193394Z","title":"Note that when operator u(·) is linear, H(x) is the exact Hessian","venue":null,"work_id":"d496b7aa-9d2b-454d-a39d-b3e37d3fbca8","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.813900Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:6903c32a25634ae7ef818182c0d11815205ffe0f42bb2e425a910eec39b63d9c","observation_id":"ebe75389-d0d0-4c6f-8725-8cbedcfe4225","resolution":{"observed_at":"2026-08-15T20:05:24.197318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.182009Z","title":null,"venue":null,"work_id":"5e6f6084-d4ab-4ba2-bc77-5b54f94f2895","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.817546Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:cdfb2be2e228411095b7bf195e3b0f8091f2dd11f92a51a9ecab38286d06ef0f","observation_id":"0cdd2b33-6bab-4d2d-90d5-d5466b8744a6","resolution":{"observed_at":"2026-08-15T20:05:24.185779Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.170037Z","title":"Repeating the reasoning from the previous case, it follows immediately that ∥∇2f(x)−H(x)∥ ≤ ξ0 + ξ1√µ ∥∇f(x)∥∗, which is the required bound","venue":null,"work_id":"b2fa4789-3359-4123-98c9-607730c1d233","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.821298Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:2ffafa289d4cfdd7da3ec02851544b1b333113eec85b09b698d7fdff5321e933","observation_id":"428200a2-d098-4952-bb70-dc3044260788","resolution":{"observed_at":"2026-08-15T20:05:24.174482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.157543Z","title":"(71) Note that it resembles a combination of the Gauss-Newton and Fisher approximation matrices, and forp= 2 it gives the classic Gauss-Newton approximation","venue":null,"work_id":"93f509d6-d53a-49ae-9f9c-36a0a26de546","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.824963Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:487facecce1eb838d51194b464ca616ee69e267e7c0fa11870a19678093ed66a","observation_id":"d3aaef5e-6ec2-4aaf-a612-c62c280efb15","resolution":{"observed_at":"2026-08-15T20:05:24.161469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.145830Z","title":null,"venue":null,"work_id":"3c9cfea9-1d59-41f2-a306-9ef714114d60","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.829139Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:6a613290baa8d549a0064d716f481f3adf2ac4ea3ab5457a1379df01f7036d10","observation_id":"6f314b71-89bd-4a70-a096-415ae87e85c7","resolution":{"observed_at":"2026-08-15T20:05:24.149904Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.134541Z","title":"Note this matrix can be equivalently represented as H(x) = (p−2)∥u(x)∥ p−4∇u(x)⊤Gu(x)u(x)⊤G∇u(x)","venue":null,"work_id":"60e986f3-e8e5-4f29-bd44-8db3a2df2059","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.833533Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:9d5d94e8cd76312ba8f0c38ff4f932ef72e81e2ec99bc6a21169a81e7844e336","observation_id":"f99986d6-19d0-4655-a60c-c3b6f1621d44","resolution":{"observed_at":"2026-08-15T20:05:24.138452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.122817Z","title":"Then, we have the bound: ∥∇2f(x)−H(x)∥ ≤ ξ2 0 +ξ 1 f(x)≤ ξ2 0 +ξ 1 f⋆ +Dc∥∇f(x)∥ 1+c ∗ ,0≤c≤1","venue":null,"work_id":"a2c9a2fa-c538-4bb1-9188-81152db6991f","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.837210Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:088c37d285e51b83925d6de934dde6347569e9cc83d1959cd7385b4a33a4697f","observation_id":"0f70308b-8ddf-43fd-8616-5d25a4da2f87","resolution":{"observed_at":"2026-08-15T20:05:24.127030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:05:24.109928Z","title":null,"venue":null,"work_id":"fa63de20-dad7-481a-8796-f494d5571456","year":null},"citing_paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:23.841043Z"},"links":{"citing_paper":"/paper/2506.13710"},"observation_digest":"sha256:e25386794f6f2eb9f58bc61f7256255e1f3bdcbd4fa6ac94758bf18f6b33f5d7","observation_id":"944755e6-6fb2-43dd-886f-4d76539007c4","resolution":{"observed_at":"2026-08-15T20:05:24.113709Z","resolver_source":"raw_fallback","status":"unresolved"},"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"}}],"paper":{"arxiv_id":"2506.13710","last_updated":"2025-06-16T17:19:34Z","latest_version":1,"primary_category":"math.OC","snapshot_observed_at":"2026-08-18T18:57:48.213439Z","submitted_at":"2025-06-16T17:19:34Z","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians"},"reference_resolution":{"displayed":94,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":41,"verified_exact":3,"verified_fuzzy":48},"total_outbound_references":94},"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 94 of 94 outbound references and 1 inbound Pith citation observation for arXiv:2506.13710."}