{"as_of":"2026-08-14T12:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a4d66181716530ae5860f3a2be7ece0576e7f08b01d4f4bd6fcdbfa8e56000e9","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:58:16.172148Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.23335/citation-record","integrity":"/paper/2506.23335/integrity","json":"/paper/2506.23335/citation-record.json","paper":"/paper/2506.23335"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:22.059199Z","title":"Katyusha: The first direct acceleration of stochastic gradient methods","venue":null,"work_id":"fdac76c7-3647-4f3b-8a38-c78efdaeb19d","year":2017},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:11.689519Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:f9694ad0602f826c6d7af4031b5b396423dcf5a8b9dbcb123d70c1bd7bb0b3e2","observation_id":"117ef500-7b80-4c93-a9be-d1c2afd38f7e","resolution":{"observed_at":"2026-08-06T21:58:22.106772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:21.921037Z","title":"KatyushaX:Simplemomentummethodforstochasticsum-of-nonconvexoptimization","venue":null,"work_id":"c1b98e48-3e04-46ab-98c2-b6fc29c82a85","year":2018},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:11.759867Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:89ee6d6c6b17bf6652e2006fe9f7a3d0a13e777540fdb322a6903905544ed52c","observation_id":"0d183afd-14f6-4ccf-a7d8-bc32c24ed996","resolution":{"observed_at":"2026-08-06T21:58:21.978349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:21.768263Z","title":"Variance reduction for faster non-convex optimization","venue":null,"work_id":"229ccd96-8be9-4c56-9dc5-46dc08a62297","year":2016},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:11.840048Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:093b317bb8a8d50f6bb3894d1a5e09b6014bcc1e4db1e6c1a3a2ae78786a1c01","observation_id":"336989af-4568-4cbf-ad22-9ed042da6b3f","resolution":{"observed_at":"2026-08-06T21:58:21.872692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:21.643860Z","title":"On the convergence of nesterov’s accelerated gradient method in stochastic settings","venue":null,"work_id":"b62f8a53-0f31-4f97-8a1e-e65ad7e911a0","year":2020},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:11.898060Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:1ca2643c906921d6ce08ecb6e46602c743ab2145d1f77ca551f7a60695f247a0","observation_id":"9d060bd2-26d1-4406-88a2-1fb21b04b2cc","resolution":{"observed_at":"2026-08-06T21:58:21.706030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:21.456443Z","title":"Gradient convergence in gradient methods with errors","venue":null,"work_id":"ff7fdcef-a7b1-411f-a03c-12abbb075d96","year":2000},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:11.955255Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:a05b819482d0dba59a3d4a2d748a42a50d8695199599b390c26aa9de31003ede","observation_id":"52b1b56d-17ae-4400-84a3-42c1730e2719","resolution":{"observed_at":"2026-08-06T21:58:21.552127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:12.040449Z","title":"Oxford University Press, 02 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:12.040449Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:a856716f8e64defba0cd48095cc2e32ab5bcdf2d77b876b141f5c8bc68db8f95","observation_id":"b56cb8c7-d3d3-4599-bd8d-ca47679e4611","resolution":{"observed_at":"2026-08-06T21:58:12.040449Z","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":"2026-08-06T21:58:12.128208Z","title":"High-probability bounds for non-convex stochastic optimization with heavy tails.Advances in Neural Information Processing Systems, 34:4883–4895, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:12.128208Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:281fb51046534de24599bb1e25fccb6a6026029ab669f1d7101440d69e85a5cb","observation_id":"b452b4b2-9706-490d-a945-a61ac8dcc115","resolution":{"observed_at":"2026-08-06T21:58:12.128208Z","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":"2026-08-06T21:58:21.189934Z","title":"Stochastic first order methods in smooth convex optimization","venue":null,"work_id":"bc953e6e-e58b-4e4e-9842-1908cbb175d9","year":2011},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:12.190834Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:84654585f458c3e668b8ace5750880303226d47eda1be36c57fe8f0beda5c715","observation_id":"e994e8cc-0776-4aa1-aae5-6409f56a9546","resolution":{"observed_at":"2026-08-06T21:58:21.315177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06305","last_updated":"2020-02-15T02:40:10Z","snapshot_observed_at":"2026-08-12T00:45:25.809655Z","submitted_at":"2020-02-15T02:40:10Z","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06305","snapshot_observed_at":"2026-08-06T21:58:12.293683Z","title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping.arXiv preprint arXiv:2002.06305, 2020","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:12.293683Z"},"links":{"cited_paper":"/paper/2002.06305","citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:ba0e24092f1b8cae5d1e98174167f50c5305c15559b39416f12ca2c1311038af","observation_id":"022713d0-2942-4f9d-bdb6-55ae00c8bcbc","resolution":{"observed_at":"2026-08-06T21:58:12.293683Z","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":"2026-08-06T21:58:20.977163Z","title":"The power of adaptivity in sgd: Self-tuning step sizes with unbounded gradients and affine variance","venue":null,"work_id":"6a4c6c2f-e02f-4dd8-b789-b2f9b0c855b5","year":2022},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:12.413393Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:f85269d75942e0b5df1040203dd4d0a8d87f7af86f3985f3170c65e868b32bd2","observation_id":"a280f997-54fc-4234-9fc9-6d2a9c6b5824","resolution":{"observed_at":"2026-08-06T21:58:21.051339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:20.752886Z","title":"Stochastic heavy ball.Electronic Journal of Statistics, 12(1):461–529, 2018","venue":null,"work_id":"a28e3ff8-5f61-44ee-92ee-26acfd9be9df","year":2018},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:12.523332Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:2ba7ae8a57da9f7f63c9390eb4242ab5ea631c5e87ba95454c76c39401ec96a6","observation_id":"653fa8dc-bd1f-4ecd-8751-d68ba5f14259","resolution":{"observed_at":"2026-08-06T21:58:20.866306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:20.562934Z","title":"Stabilized SVRG: Simple variance reduction for nonconvex optimization","venue":null,"work_id":"bee2b6d2-6e46-458f-9d92-bce5eb15835e","year":2019},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:12.661000Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:0fbba6c1c5d71b013c27727c1435bb14acfd869309c19af4ba4b6e2b81c84db0","observation_id":"c819efeb-4a34-45f0-b96e-e23394cda9b6","resolution":{"observed_at":"2026-08-06T21:58:20.676197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:20.439213Z","title":"Stochastic first-and zeroth-order methods for nonconvex stochastic programming","venue":null,"work_id":"ebba078a-6ca0-4b70-9c43-ca3f1c324080","year":2013},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:12.744758Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:e7f83ded5ad6612d67ab31d6fd141830acef17633a6aa9d0e1fcc60e191d667a","observation_id":"8859b425-51c2-4f41-84bf-2de8b487ee51","resolution":{"observed_at":"2026-08-06T21:58:20.494280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:20.282349Z","title":"Understanding the role of momentum in stochastic gradient methods.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"736d9c9e-9d18-4a46-aeba-9c3fbb7374af","year":2019},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:12.853304Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:d3532ffc2ee406f0ab7b5d34886a53ba24bce1271d576f0cbabeaf86503b5d9f","observation_id":"9d6c863b-4a00-4435-8f73-94469f55cc1e","resolution":{"observed_at":"2026-08-06T21:58:20.367268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:12.949155Z","title":"Goodfellow, Yoshua Bengio, and Aaron Courville.Deep Learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:12.949155Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:2c2c670e4f3faea168654ec011d89621543cfc5f9d7becba71caeff8377487f3","observation_id":"7a2398fd-95ce-41b5-b67a-43ba9946d9e9","resolution":{"observed_at":"2026-08-06T21:58:12.949155Z","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":"2026-08-06T21:58:20.127816Z","title":"Stochastic optimization with heavy- tailed noise via accelerated gradient clipping.Advances in Neural Information Processing Systems, 33:15042–15053, 2020","venue":null,"work_id":"7f51acf9-1761-4749-87c0-bcaabd81617c","year":2020},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.079058Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:7dbb3c0252e3ec8497db4633fb0b6f3b506e6168dc803f2a208b23532ab602fd","observation_id":"0b2434b3-f45d-43b0-b82a-28034f50a8a3","resolution":{"observed_at":"2026-08-06T21:58:20.178360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:13.205688Z","title":"Tight analyses for non-smooth stochastic gradient descent","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.205688Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:1bf93131d3c37bb09e14af3dab966d06ca1c1b6009560e6534588058cf672af4","observation_id":"d9d7dddd-5078-410b-8ed2-3c827f8ee529","resolution":{"observed_at":"2026-08-06T21:58:13.205688Z","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":"2026-08-06T21:58:19.930888Z","title":"Making the last iterate of SGD information theoretically optimal","venue":null,"work_id":"97454775-9a40-4780-92a9-b7ccdd8ea571","year":2021},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.278935Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:9a1bed72fa7c3089667735fabb0092fef27ddcef0700ff68a006816833eeda95","observation_id":"c135eb54-c9f6-4b54-80ed-26f72a51579c","resolution":{"observed_at":"2026-08-06T21:58:20.007728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:13.341562Z","title":"Accelerating stochastic gradient descent using predictive variance reduction","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.341562Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:93f3eef2c9e7ebed3e3220fb69af12d33530bcec479311a4370b905468514cf7","observation_id":"f51eeb78-f867-44ec-be48-971d6e0f55cf","resolution":{"observed_at":"2026-08-06T21:58:13.341562Z","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":"2026-08-06T21:58:19.738397Z","title":"Linear convergence of gradient and proximal-gradient methods under the polyak-łojasiewicz condition","venue":null,"work_id":"eebbaca5-dd41-4eed-b999-ce64f3a8f421","year":2016},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.410175Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:b5524b7a11626755151da5d2e047d07f755c31102e7e9dc80bd5e7c39fa613cd","observation_id":"bf0716f3-ebd8-4b0b-a886-d898db2f3ae4","resolution":{"observed_at":"2026-08-06T21:58:19.834673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:19.556961Z","title":"High probability bounds for a class of nonconvex algorithms with adagrad stepsize","venue":null,"work_id":"254b9fd3-54de-40dd-b400-a5c2cc3e373a","year":2021},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.459711Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:e12c85f66635691c4d2678214706a10b08a914bb31063e51b9f676e2ee7c7de8","observation_id":"3503eb94-4bbc-40c4-8211-db993c7235a5","resolution":{"observed_at":"2026-08-06T21:58:19.621557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:19.385752Z","title":"On the insufficiency of existing momentum schemes for stochastic optimization","venue":null,"work_id":"3d948cf9-88cb-4020-b27a-65752c07cc04","year":2018},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.599031Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:470724d5e797d0e0e8e3d2a1e00d405b25ba360b7c7f17e54fe15011382e0679","observation_id":"b4b09144-7881-43a7-a90e-d123f7b8335e","resolution":{"observed_at":"2026-08-06T21:58:19.475227Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:19.171649Z","title":"Stochastic estimation of the maximum of a regression function.The Annals of Mathematical Statistics, pages 462–466, 1952","venue":null,"work_id":"f3628b8f-843f-4b00-963d-c2ad969c3588","year":1952},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.668389Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:d03ffe99fae2f4e733a416bb106d66288ae376c69ad24e424db34832e53d97be","observation_id":"8b4d9f79-aefa-4a87-b501-87fe4f3f9e89","resolution":{"observed_at":"2026-08-06T21:58:19.298169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:19.011749Z","title":"Kushner and Hai Huang","venue":null,"work_id":"ebce6507-64c4-4d9a-bf28-ca2546717e6e","year":1981},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.735270Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:5082c193701954918eab9ab8f6056d85806e356c7d4eb17811b7618288fcc559","observation_id":"8e9ff5cc-ea96-449b-9bc6-d8d068110a98","resolution":{"observed_at":"2026-08-06T21:58:19.099508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:18.861921Z","title":"An optimal method for stochastic composite optimization.Mathematical Programming, 133(1-2):365–397, 2012","venue":null,"work_id":"4e3adbb8-f0bc-40e8-a798-8e263e45a067","year":2012},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.843232Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:302eb67941dc16a52cf6750b100b1645547b12b9da6544a63b30b15bea2a1e8f","observation_id":"e08f7b85-d87e-4510-9692-eefc137a2f7e","resolution":{"observed_at":"2026-08-06T21:58:18.919139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:13.932964Z","title":"Springer, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:13.932964Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:622ffe7b89d877ea143c2dceeed5b15019f0a66805affb9014781df28d394269","observation_id":"34ca3088-321c-429a-a5d2-98256491880e","resolution":{"observed_at":"2026-08-06T21:58:13.932964Z","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":"2026-08-06T21:58:18.661617Z","title":"Validation analysis of mirror descent stochastic approximation method.Mathematical programming, 134(2):425–458, 2012","venue":null,"work_id":"5f52e6f2-c150-4d81-8d44-33463fce83ea","year":2012},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:14.061415Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:58c3aaa4b6cc297d44b7a4997712a8b91f38b8899c184f5ff7a65f9dd16cf8e1","observation_id":"1ec68be0-002f-4a53-895f-7c4dc824d941","resolution":{"observed_at":"2026-08-06T21:58:18.747676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:18.505729Z","title":"High probability guarantees for nonconvex stochastic gradient descent with heavy tails","venue":null,"work_id":"06a65eb1-59f0-4ff8-870d-09218952733b","year":2022},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:14.153123Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:15828e23c79641c8bc9364b28ee25a7c88619d404104d15b6322439d1eb12299","observation_id":"cd07e7dc-bfec-4942-af74-64b295e3683d","resolution":{"observed_at":"2026-08-06T21:58:18.591134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:18.341477Z","title":"On the convergence of stochastic gradient descent with adaptive stepsizes","venue":null,"work_id":"6f1e7cb7-3b08-4021-b5e2-d539e35692ee","year":2019},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:14.244296Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:05410662b94d7fc5d4f5f39c4a154cd251ffaec342c8f9e7a7842c36bc6d35fe","observation_id":"d63ad830-ed82-46c0-a991-62283bcb1ef1","resolution":{"observed_at":"2026-08-06T21:58:18.423525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:18.200370Z","title":"A high probability analysis of adaptive sgd with momentum","venue":null,"work_id":"648396a0-162f-43c3-ad83-6a2e28f4f2a2","year":2020},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:14.368710Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:db39e6fa7c44066f277f077946c6ae615af94b90fef178f7f256b2e1ba00ebd3","observation_id":"0a494767-2a9d-4bd1-92ab-05990cd2e010","resolution":{"observed_at":"2026-08-06T21:58:18.246187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:14.473337Z","title":"An improved analysis of stochastic gradient descent with momentum","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:14.473337Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:5f6be27ee3282763c8f9eecec1594b55cd7f0e2b887ec7169f63e214f77b24bb","observation_id":"41515cc5-7c9d-4229-97f9-f5cfb1401727","resolution":{"observed_at":"2026-08-06T21:58:14.473337Z","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":"2026-08-06T21:58:14.623938Z","title":"High probability convergence of stochastic gradient methods","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:14.623938Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:94ea89f55d5ab796b762ba41fdae24d27213a1c4941e7cf6c07e847a4e0da58e","observation_id":"e3c557e4-cc67-40b4-b68a-42ae1b54114d","resolution":{"observed_at":"2026-08-06T21:58:14.623938Z","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":"2026-08-06T21:58:14.739761Z","title":"Revisiting the last-iterate convergence of stochastic gradient methods","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:14.739761Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:fb88489bef1551641c81a6494189b0c8576c6b67591df2d70bdc4bea46605d8a","observation_id":"af95c303-fbb8-41ba-bde3-8d412c531fa2","resolution":{"observed_at":"2026-08-06T21:58:14.739761Z","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":"2026-08-06T21:58:14.838195Z","title":"High-probability convergence bounds for non-convex stochastic gradient descent.arXiv preprint arXiv:2006.05610, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:14.838195Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:e838620d49bbdf43c0e0802e4052ede2f93a9adb4180162e2b2fee1fe7c59db0","observation_id":"b5ee906e-0e1d-40cf-b860-a6d3b74a9939","resolution":{"observed_at":"2026-08-06T21:58:14.838195Z","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":"2026-08-06T21:58:18.067947Z","title":"Algorithms of robust stochastic optimization based on mirror descent method.Automation and Remote Control, 80:1607–1627, 2019","venue":null,"work_id":"91d89f55-c6d7-457b-897b-b901d0861a5d","year":2019},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:14.934698Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:18fa97663ae721ea96727f1f7e06ccd1dfc6350865143b84d0bd3dbca9e93a50","observation_id":"36e44824-f084-4829-a26a-19c0c6400df5","resolution":{"observed_at":"2026-08-06T21:58:18.094461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:17.826577Z","title":"Robust stochastic approximation approach to stochastic programming.SIAM Journal on optimization, 19(4):1574–1609, 2009","venue":null,"work_id":"d5826fad-d545-4131-9748-1e74554a6912","year":2009},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:15.025410Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:62bb86d00229835644a8d895bbaf44c972f0e55dee3f0b1e0fab8bc4b2a78ff8","observation_id":"e0d91a0c-4cac-4b0c-93ec-7569d6e2e4c4","resolution":{"observed_at":"2026-08-06T21:58:17.933716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:15.145389Z","title":"Early stopping-but when? InNeural Networks: Tricks of the trade, pages 55–69","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:15.145389Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:6367f0b878b66520635328654266899995ebe72d18101ca48966257a2e7b2b0f","observation_id":"24b9af45-a705-49cd-894e-4444cb898cd6","resolution":{"observed_at":"2026-08-06T21:58:15.145389Z","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":"2026-08-06T21:58:17.552095Z","title":"Robbins and D","venue":null,"work_id":"8ecf0ef3-2154-4cea-bb38-25cc0c5477ca","year":null},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:15.280422Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:c3ab417155be46ca37b54fb355829492c1ed2b82293464ede516e0149a896c5f","observation_id":"f3d33cad-e170-40ee-a06e-29033d86e678","resolution":{"observed_at":"2026-08-06T21:58:17.654208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:17.380812Z","title":"Rustagi, editor,Optimizing Methods in Statistics, pages 233–257","venue":null,"work_id":"1a29a43b-9d76-46a1-97ef-491a9ddc92bc","year":1971},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:15.364727Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:56c38bc65a990aee1e284251dc5bde2c4135cae6a8332401c78b8307857a3f42","observation_id":"05b5e893-c7c2-4c2f-88fa-fab2bfec96c1","resolution":{"observed_at":"2026-08-06T21:58:17.472358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:15.441369Z","title":"A stochastic approximation method.The annals of mathematical statistics, pages 400–407, 1951","venue":null,"work_id":null,"year":1951},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:15.441369Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:61741eda834b571be49880b5a786c3e58c13ccb38e2d865bc97d4336c31a212c","observation_id":"c26f7a77-da2b-4c85-a5b2-97657f3b7eea","resolution":{"observed_at":"2026-08-06T21:58:15.441369Z","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":"2026-08-06T21:58:17.144729Z","title":"Almost sure convergence rates for stochastic gradient descent and stochastic heavy ball","venue":null,"work_id":"b355d8f3-1b00-4847-80e8-d1418d7d86b4","year":2021},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:15.511998Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:ea40237b84e809c03f93a021658da3dbe128be744ff8ee302e084bba14bdb753","observation_id":"0bd7bf79-e673-45a8-8eb9-29089aa0ac20","resolution":{"observed_at":"2026-08-06T21:58:17.258755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:16.958923Z","title":"Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes","venue":null,"work_id":"e107603e-89ed-411b-937c-03556068334f","year":2013},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:15.600986Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:64d964d7f8935da47c5414f09eb0e3a64be70cc7fe7413a3551b1bd067937297","observation_id":"dd4c3791-d256-4deb-a187-d3147823b0a9","resolution":{"observed_at":"2026-08-06T21:58:17.063281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:15.722439Z","title":"High-dimensional probability: An introduction with applications in data science, volume 47","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:15.722439Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:ad038bc91cd77fe31c8e92f2e2e82ee8dfd730dc464ccf3ab948f1d406ed0599","observation_id":"3c8b564d-4277-469b-9af9-faa8a7bab1ec","resolution":{"observed_at":"2026-08-06T21:58:15.722439Z","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":"2026-08-06T21:58:15.794140Z","title":"Etude critique de la notion de collectif","venue":null,"work_id":null,"year":1939},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:15.794140Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:baa1f09fd5d3f2a16a985c860820318390c581ad1f33046ca236ea5afa89f9a5","observation_id":"550e24fe-f1ee-4dc0-8409-0c428820a33f","resolution":{"observed_at":"2026-08-06T21:58:15.794140Z","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":"2026-08-06T21:58:16.751285Z","title":"Cambridge University Press, 2019","venue":null,"work_id":"03e34985-a1e2-420a-9a57-56a2ccfc593d","year":2019},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:15.933788Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:742a14077d2d810809716f97306fb23ada75c98fca2c51f9a82134787e03fd30","observation_id":"e7e5571a-5c34-4429-8a17-036b0f239bc5","resolution":{"observed_at":"2026-08-06T21:58:16.842013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:58:16.556569Z","title":"Adagrad stepsizes: Sharp convergence over nonconvex landscapes","venue":null,"work_id":"396f3377-3bc3-4cf4-9ea8-083724f3096d","year":2020},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:16.017353Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:f9a817a87525ba2fac86d04dccd44414197465f15191c840a3579ba1f190f3a2","observation_id":"b72bd498-2e07-4f0e-aad8-262445373e64","resolution":{"observed_at":"2026-08-06T21:58:16.655757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1808.10396","last_updated":"2018-08-30T17:00:03Z","snapshot_observed_at":"2026-08-08T07:56:38.386325Z","submitted_at":"2018-08-30T17:00:03Z","title":"A Unified Analysis of Stochastic Momentum Methods for Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.10396","snapshot_observed_at":"2026-08-06T21:58:16.108035Z","title":"A unified analysis of stochastic momentum methods for deep learning.arXiv preprint arXiv:1808.10396, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:16.108035Z"},"links":{"cited_paper":"/paper/1808.10396","citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:0d58fff92790af62c3188ae99742bad5ae28873d82efefd36ecdaeded9715a29","observation_id":"d7bd50e3-7bb5-4320-bc73-88e7165168ee","resolution":{"observed_at":"2026-08-06T21:58:16.108035Z","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":"2026-08-06T21:58:16.422013Z","title":"Why are adaptive methods good for attention models?Advances in Neural Information Processing Systems, 33:15383–15393, 2020","venue":null,"work_id":"0cb8d0c9-c48d-462f-8dbb-96438c48081d","year":2020},"citing_paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T21:58:16.172148Z"},"links":{"citing_paper":"/paper/2506.23335"},"observation_digest":"sha256:3a0257c299d98abcaf5b299de14ce1d40d4ef376392bd8f4699b710eb43b88ab","observation_id":"6718a9ae-6904-4004-ae2d-4056eadedc93","resolution":{"observed_at":"2026-08-06T21:58:16.472173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.23335","last_updated":"2025-07-16T16:03:51Z","latest_version":2,"primary_category":"math.OC","snapshot_observed_at":"2026-08-13T08:43:04.012917Z","submitted_at":"2025-06-29T17:09:58Z","title":"Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":0,"verified_fuzzy":32},"total_outbound_references":48},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2506.23335."}