{"as_of":"2026-08-08T07:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e7b51fb3c861381a48704a3a609afa8ae5873cbe9de341251aba2a398da72c37","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:41:38.954047Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T12:38:28.920474Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-30T00:04:06.672064Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"cited_work":{"arxiv_id":"2506.04878","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.04878","snapshot_observed_at":"2026-06-30T00:04:06.672064Z","title":"ktula: A langevin sampling algorithm with improved kl bounds under super-linear log-gradients.arXiv preprint arXiv:2506.04878, 2025","venue":null,"work_id":"4bf21703-82cd-48da-b9fd-ad9e5752ad82","year":2025},"citing_paper":{"arxiv_id":"2605.24937","last_updated":"2026-05-24T08:35:24Z","snapshot_observed_at":"2026-08-06T12:30:11.722284Z","submitted_at":"2026-05-24T08:35:24Z","title":"Error estimates for tamed Euler and Randomized Euler schemes for SDEs with locally Lipschitz drift with applications to non-logconcave sampling and optimization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-29T23:54:31.232162Z"},"links":{"cited_paper":"/paper/2506.04878","citing_paper":"/paper/2605.24937"},"observation_digest":"sha256:f958c14d9dd158a1a84297139a81c2016bf80ded9252225fdb5d736a61dedae6","observation_id":"a785c0f4-b79f-4680-ae8d-b083bda93324","resolution":{"observed_at":"2026-06-30T00:04:06.673839Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.04878","snapshot_observed_at":"2026-08-01T12:38:28.920474Z","title":"Lytras, S","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19544","last_updated":"2026-07-21T19:43:54Z","snapshot_observed_at":"2026-08-06T16:01:51.858828Z","submitted_at":"2026-07-21T19:43:54Z","title":"RELTA-SGLD: Relative-Growth Localized Taming for Nonconvex Stochastic-Gradient Langevin Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T12:38:28.920474Z"},"links":{"cited_paper":"/paper/2506.04878","citing_paper":"/paper/2607.19544"},"observation_digest":"sha256:f7cf721a261d36ab27cbd5cf6249554aa164837938f02048260260ee6d8c28e2","observation_id":"8cf152b2-4806-48ec-8ffe-b835a8219b9b","resolution":{"observed_at":"2026-08-01T12:38:28.920474Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.04878/citation-record","integrity":"/paper/2506.04878/integrity","json":"/paper/2506.04878/citation-record.json","paper":"/paper/2506.04878"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.604565Z","title":"Smooth sigmoid wavelet shrinkage for non-parametric estimation","venue":null,"work_id":"34558122-66e5-444a-9c14-3629b8264072","year":2008},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.027553Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:4f6f5b9e7f49599ccb8cbe3dd53d62ec0124de372217cb9e5dbc180f2f67430c","observation_id":"18235c3d-937d-472d-aa47-bfbbf9bbe240","resolution":{"observed_at":"2026-08-07T10:41:39.609975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.587606Z","title":"Towards a theory of non-log-concave sampling: first-order stationarity guarantees for Langevin monte carlo","venue":null,"work_id":"4a98e7d2-a4dc-4ef3-92ad-32154bbab6db","year":2022},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.080205Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:3452df6a81ad63d72bdd4c054235a6de6a76a470f3e84defd605da0e38e51117","observation_id":"d858dfee-c8f9-465b-8aca-cfa3338adcb7","resolution":{"observed_at":"2026-08-07T10:41:39.593397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.01731","last_updated":"2025-08-09T02:58:06Z","snapshot_observed_at":"2026-07-06T19:44:34.642049Z","submitted_at":"2024-11-04T01:24:19Z","title":"$L^2$-Wasserstein contraction of modified Euler schemes for SDEs with high diffusivity and applications","version":2},"cited_work":{"arxiv_id":"2411.01731","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.01731","snapshot_observed_at":"2026-08-07T10:41:39.119050Z","title":"$L^2$-Wasserstein contraction of modified Euler schemes for SDEs with high diffusivity and applications","venue":"math.PR","work_id":"8fe2394e-83a3-48f8-8393-1ffc9522a431","year":2024},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.143445Z"},"links":{"cited_paper":"/paper/2411.01731","citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:0cfa16514419fbf82715dd4d0a7bac6d22e62d8048db83210de99b31ffe61de4","observation_id":"3fee2f62-cb5f-48ee-b486-7d1aab3feaca","resolution":{"observed_at":"2026-08-07T10:41:39.126280Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:38.232387Z","title":"On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case.Bernoulli, 27(1):1–33, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.232387Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:a1fa8b7c976a0245a55373e9aa02546a4fc8b96c35fac025fe22ac0ad285a210","observation_id":"b3f67e83-54af-4c94-be65-c9211ff7cc04","resolution":{"observed_at":"2026-08-07T10:41:38.232387Z","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":"2026-08-07T10:41:39.561904Z","title":"The tamed unadjusted Langevin algorithm.Stochastic Processes and their Applications, 129(10):3638–3663, 2019","venue":null,"work_id":"a2f0c3ef-5366-40a4-b9e3-40906268da83","year":2019},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.345396Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:713d57c883087dcf125d5049783b55f64874e6ac7627283ab38fd0e35400ab04","observation_id":"09e3a012-ac5e-4ef8-bee5-9236508de9f7","resolution":{"observed_at":"2026-08-07T10:41:39.566830Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.545309Z","title":"On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case.SIAM Journal on Mathematics of Data Science, 3(3):959–986, 2021","venue":null,"work_id":"9706b880-bb7d-4b2d-ac09-e8528e4e58b7","year":2021},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.468104Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:3c95bda43471ef16812eede63cbbabe6d7a7a098cef9559f2eab07e67bce602e","observation_id":"ce4f4d21-398b-404b-9d07-d60191ad6b38","resolution":{"observed_at":"2026-08-07T10:41:39.550501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.01648","last_updated":"2020-07-06T06:49:05Z","snapshot_observed_at":"2026-07-06T06:37:21.273030Z","submitted_at":"2018-05-04T08:16:00Z","title":"Sharp convergence rates for Langevin dynamics in the nonconvex setting","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.01648","snapshot_observed_at":"2026-08-07T10:41:38.559333Z","title":"Sharp convergence rates for Langevin dynamics in the nonconvex setting.arXiv preprint arXiv:1805.01648, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.559333Z"},"links":{"cited_paper":"/paper/1805.01648","citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:1d9affbc7b01c2f7b0c1e8d0a52c28b194342b51ebd3eb3e015cd6e54968fca9","observation_id":"a8d5eb80-96da-41d2-92df-cd7d237dbb78","resolution":{"observed_at":"2026-08-07T10:41:38.559333Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.12662","last_updated":"2024-07-10T16:45:27Z","snapshot_observed_at":"2026-07-06T12:22:00.203012Z","submitted_at":"2021-12-23T15:56:33Z","title":"Analysis of Langevin Monte Carlo from Poincar\\'e to Log-Sobolev","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.12662","snapshot_observed_at":"2026-08-07T10:41:38.622839Z","title":"Analysis of Langevin Monte Carlo from Poincar´e to Log-Sobolev.arXiv preprint arXiv:2112.12662, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.622839Z"},"links":{"cited_paper":"/paper/2112.12662","citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:6bb99851e8d778fb9437517d3f883dddfe5ece5d037c84ae47b49b45d881ece2","observation_id":"1c45844c-b340-4f2d-b3a1-ba8497db592b","resolution":{"observed_at":"2026-08-07T10:41:38.622839Z","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":"2026-08-07T10:41:39.529140Z","title":null,"venue":null,"work_id":"74792f6b-31e7-4799-a2a1-30051e1d9718","year":2017},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.697392Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:27ba85b00213854c7cdaad9d868dd454743ed45376dec8e96050533093505739","observation_id":"bac5a9e7-8592-49a7-acd1-f4419d6e4473","resolution":{"observed_at":"2026-08-07T10:41:39.534590Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.511287Z","title":"Nonasymptotic convergence analysis for the unadjusted Langevin algorithm.The Annals of Applied Probability, 27(3):1551–1587, 2017","venue":null,"work_id":"acbe5e19-199d-43ff-8fa6-411209999009","year":2017},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.747831Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:1c56f376de27515c9db8ba9334ef8cfc2de0d3c34c6389dde3e1868b520edf65","observation_id":"17aeffc2-38a8-471a-b1b4-e7ba90ea7096","resolution":{"observed_at":"2026-08-07T10:41:39.517267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.493502Z","title":"High-dimensional Bayesian inference via the unadjusted Langevin algorithm.Bernoulli, 25(4A):2854–2882, 2019","venue":null,"work_id":"a6a44664-a058-4711-bfe9-8e8d136e71c6","year":2019},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.810496Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:79f44721271123ba7d2514e5088a7478ee81bd097a999e61d61e1e8327bf7731","observation_id":"6015fffc-1694-4d08-a035-3e56e24adc4e","resolution":{"observed_at":"2026-08-07T10:41:39.498816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.477674Z","title":"Convergence of Langevin Monte Carlo in chi-squared and R ´enyi divergence","venue":null,"work_id":"b117c8b2-c4c2-4b37-b321-950f8a845b32","year":2022},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.827375Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:069930173ad628fb0c25279db4d420f5d524da49e12aad11bffab0c7ad77b627","observation_id":"9fe2a93e-4464-418b-9150-7107ec67159d","resolution":{"observed_at":"2026-08-07T10:41:39.482319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.462647Z","title":"On the diffeomorphisms of Euclidean space.The American Mathematical Monthly, 79(7):755–759, 1972","venue":null,"work_id":"8849b232-da79-41e9-9eb8-fe25674f4645","year":1972},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.832134Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:959a2b4604672a92976d8ebe8aa45b8ff41a276158ac3e83bb439480d90bf861","observation_id":"f9fff660-5425-4663-b5c6-a81fe6abcf56","resolution":{"observed_at":"2026-08-07T10:41:39.467370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.445714Z","title":null,"venue":null,"work_id":"e6c19113-d825-47d4-b330-8f5f10242a7b","year":2011},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.836312Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:1259649f5d9cd40ac4a11e0179f325d4ea3ea3fa9a35c2d6eaced89b79310b8a","observation_id":"31b9e2a2-5577-44d0-97f9-c8517c05cdb3","resolution":{"observed_at":"2026-08-07T10:41:39.451502Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.428522Z","title":null,"venue":null,"work_id":"3507d3ca-0531-49d7-aae1-ae0c07ed5998","year":2012},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.840834Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:b341a4abc1ca4dac31bde18c43555a2c717d0b3add9697d04aea1aaee234098b","observation_id":"adbc135c-7a26-4f62-a936-7a7ae750774d","resolution":{"observed_at":"2026-08-07T10:41:39.433488Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.410107Z","title":"Laplace’s method revisited: weak convergence of probability measures.The Annals of Probability, 8(6):1177–1182, 1980","venue":null,"work_id":"206d455f-514d-464e-a045-4ffc47794edf","year":1980},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.844829Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:df5530659c274a18111c848f70d4d6fb6b280feabf6b8e56746740265436d1fc","observation_id":"3fbe3dcd-e108-4512-9ffd-5c19d920e30c","resolution":{"observed_at":"2026-08-07T10:41:39.415788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.08039","last_updated":"2023-01-19T12:32:41Z","snapshot_observed_at":"2026-07-06T14:42:49.605796Z","submitted_at":"2023-01-19T12:32:41Z","title":"Kinetic Langevin MCMC Sampling Without Gradient Lipschitz Continuity -- the Strongly Convex Case","version":1},"cited_work":{"arxiv_id":"2301.08039","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.08039","snapshot_observed_at":"2026-08-07T10:41:39.064016Z","title":"Kinetic Langevin MCMC Sampling Without Gradient Lipschitz Continuity -- the Strongly Convex Case","venue":"math.PR","work_id":"58235067-7a19-4231-94ac-0e00c2623ba6","year":2023},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.848671Z"},"links":{"cited_paper":"/paper/2301.08039","citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:f37400dc8e07637e663fa6ee7b2b2b863e670118c648b62ef9e1aadbc14931d9","observation_id":"534ca0e9-6fa9-4b66-bb96-62d2464dfa76","resolution":{"observed_at":"2026-08-07T10:41:39.070117Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1137/1135082","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:38.986832Z","title":null,"venue":null,"work_id":"a62565b3-4981-44db-aa64-d6b5a6c75e12","year":1991},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.853167Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:0eef8f1567487c4d43761172908235d672439971b5a633dafa8a2f2fdc2b4f96","observation_id":"561655b6-37df-4f00-b368-b33afef7e078","resolution":{"observed_at":"2026-08-07T10:41:38.994418Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.392932Z","title":"Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function.IMA Journal of Numerical Analysis, 2023","venue":null,"work_id":"2109d404-bbb8-4fad-92ca-3eba5fa58e77","year":2023},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.857415Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:6ccb410c4dbd242d94ff8a505eb0c12b0082e6758b9c54404d163ac2076d14bb","observation_id":"7904cdb1-862b-4104-be32-c518a2161159","resolution":{"observed_at":"2026-08-07T10:41:39.398306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.376840Z","title":"Langevin dynamics based algorithm e-TH ε O POULA for stochastic optimization problems with discontinuous stochastic gradient.Mathematics of Operations Research, 2024","venue":null,"work_id":"0af4e2a5-9971-4696-b220-bc3a1e37f8a3","year":2024},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.861803Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:dad512a9a4781a01f3e2c8988e1d3908d8298b9f2d382d8bee5b2bddad4c9c30","observation_id":"cd173d8f-21a7-4ee3-8153-b12247ceb557","resolution":{"observed_at":"2026-08-07T10:41:39.382224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.360703Z","title":"Taming neural networks with tusla: Nonconvex learning via adaptive stochastic gradient langevin algorithms.SIAM Journal on Mathematics of Data Science, 5(2):323–345, 2023","venue":null,"work_id":"7472692f-d169-4ad7-a506-a7107ac9bd57","year":2023},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.866224Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:ec40e0481aa5ea9b8370661981751ffaf7f8c636777c42a5edecba78b74dde2d","observation_id":"5f796b75-9b91-4cda-981b-cd27960ead68","resolution":{"observed_at":"2026-08-07T10:41:39.365938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17693","last_updated":"2024-05-27T23:00:40Z","snapshot_observed_at":"2026-07-06T18:20:57.086853Z","submitted_at":"2024-05-27T23:00:40Z","title":"Tamed Langevin sampling under weaker conditions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17693","snapshot_observed_at":"2026-08-07T10:41:38.870584Z","title":"Tamed Langevin sampling under weaker conditions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.870584Z"},"links":{"cited_paper":"/paper/2405.17693","citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:6f53c89a511ad3f56d6dc91d52d84286ba8f9fee681a1ad35045a8a9cf6445f5","observation_id":"b990311f-4bef-456a-a917-5829fb844886","resolution":{"observed_at":"2026-08-07T10:41:38.870584Z","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":"2026-08-07T10:41:38.875472Z","title":"Taming under isoperimetry.Stochastic Processes and their Applications, page 104684, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.875472Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:41d8e9c6be28e03690ed8c1f18802112d085d64228e2f566208f59afa6596300","observation_id":"710d862c-39c6-45ed-ae9c-ecb289fae808","resolution":{"observed_at":"2026-08-07T10:41:38.875472Z","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":"2026-08-07T10:41:39.333317Z","title":"Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity.Bernoulli, 28(3): 1577–1601, 2022","venue":null,"work_id":"78aa3144-fc5b-455d-a103-b49b313b9329","year":2022},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.880582Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:3f2276ddd6ae558dc60cd95c717e9853c3be07f2da80991c9b205dcd15fff365","observation_id":"9bffb13c-cda5-477a-ba49-8301c47845a5","resolution":{"observed_at":"2026-08-07T10:41:39.339168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.317496Z","title":"Supplement to ”Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity”","venue":null,"work_id":"a0361bf0-833f-4cf4-8f86-8e36d0752955","year":2022},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.886259Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:e725a61060ffc839d11fb85555e5b2a8f10fbf667b49d86a876932796c003a3e","observation_id":"c19bf098-4d61-4982-8f36-677ed337a6b3","resolution":{"observed_at":"2026-08-07T10:41:39.322547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.302169Z","title":"Towards a complete analysis of Langevin Monte Carlo: Beyond poincar´e inequality","venue":null,"work_id":"cc9ea6ff-36f2-44ab-bcfb-851baef7d6d0","year":2023},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.890949Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:8650736442c3b5dd4286b50d43788d5b30b424cfdf4044998d562057e36f4154","observation_id":"54ab32b3-565d-4a2a-94ee-119c11889885","resolution":{"observed_at":"2026-08-07T10:41:39.307125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.05679","last_updated":"2025-08-08T14:35:12Z","snapshot_observed_at":"2026-07-06T18:12:01.364458Z","submitted_at":"2024-05-09T11:12:03Z","title":"Non-asymptotic estimates for accelerated high order Langevin Monte Carlo algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.05679","snapshot_observed_at":"2026-08-07T10:41:38.895788Z","title":"Non-asymptotic estimates for accelerated high order Langevin Monte Carlo algorithms.arXiv preprint arXiv:2405.05679, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.895788Z"},"links":{"cited_paper":"/paper/2405.05679","citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:78823fe1b149c465d0b7b24684430e89718e1ea6bcacf30072e21ac4b59c5cee","observation_id":"c7a484bb-bab7-4bcc-af52-4ec78f64d2b8","resolution":{"observed_at":"2026-08-07T10:41:38.895788Z","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":"2026-08-07T10:41:39.286248Z","title":"Non-asymptotic convergence bounds for modified tamed unadjusted Langevin algorithm in non-convex setting.Journal of Mathematical Analysis and Applications, 543(1):128892, 2025","venue":null,"work_id":"9321cddc-96b5-4aea-a070-f96d409cba74","year":2025},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.901953Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:e335fd6b251ce03238d0031dc7873c946170bcde22a38536f1f40ba77d9ecb1b","observation_id":"1c5c6129-821d-4b97-87be-2b906585bc9e","resolution":{"observed_at":"2026-08-07T10:41:39.291354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.267684Z","title":"Wasserstein continuity of entropy and outer bounds for interference channels.IEEE Transactions on Information Theory, 62(7):3992–4002, 2016","venue":null,"work_id":"a4a0ce22-e98d-4969-9531-61f6f216b78f","year":2016},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.906563Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:5acab381287d31c5c7def57bf59beded6af7cabeae819e3878161561ccf43558","observation_id":"68af1fa0-18dc-4e40-8d45-9f89de98cf51","resolution":{"observed_at":"2026-08-07T10:41:39.273574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.249586Z","title":"Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis","venue":null,"work_id":"ba512c96-2724-4f46-ac59-1b2012da298f","year":2017},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.912207Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:c663136f70648abbaadf0421f51574aebe3adf13da7eaa841dba9302e877cb1d","observation_id":"875872cd-e330-4421-a4c8-0f3fc077ca8c","resolution":{"observed_at":"2026-08-07T10:41:39.255654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.232523Z","title":"Information theoretic proofs of entropy power inequalities.IEEE transactions on information theory, 57(1):33–55, 2010","venue":null,"work_id":"546e8476-824e-472b-951b-ffa98b3e048d","year":2010},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.917367Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:c0de5e20d7f54c2394292f267f6c53babf57be52d3ea5179c18cff471c808b57","observation_id":"c6d4e147-f504-49a6-bf8f-f3b1c8780cf8","resolution":{"observed_at":"2026-08-07T10:41:39.238067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.217383Z","title":"A note on tamed Euler approximations.Electron","venue":null,"work_id":"f9ca8fc0-5928-49a8-a090-a7c3f9be910b","year":2013},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.923202Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:6c66ea37cadd63089a2bb36c2da310fb361234c43051ed43d79c3cc5d0af4182","observation_id":"c9eb23db-9b25-41ae-959e-3fe67312dc6f","resolution":{"observed_at":"2026-08-07T10:41:39.222265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.200481Z","title":"Euler approximations with varying coefficients: the case of superlinearly growing diffusion coefficients.Ann","venue":null,"work_id":"4bc987e1-1dce-4a5e-8fa9-56e0932ee1e8","year":2016},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.928240Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:2232ac1c35105f4fbae90ed6148b4ec43c372d8e4e5d2ad7c9540c9cf8f6b7e5","observation_id":"4bfbb8c7-2550-49aa-85d4-489cd1bae7fc","resolution":{"observed_at":"2026-08-07T10:41:39.206721Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.183342Z","title":"Higher order Langevin Monte Carlo algorithm.Electronic Journal of Statistics, 13(2):3805–3850, 2019","venue":null,"work_id":"7a619789-c318-4182-a6b1-842006b54102","year":2019},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.933707Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:5be471bdd493a8fa0b21621812a0c6d40d711e5e725e9520a13d7d5f1e7cdf6c","observation_id":"76ff6509-61cf-45fb-898b-47566b3bb1f1","resolution":{"observed_at":"2026-08-07T10:41:39.189228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.01672","last_updated":"2020-07-02T17:11:57Z","snapshot_observed_at":"2026-08-06T00:35:39.550351Z","submitted_at":"2020-07-02T17:11:57Z","title":"A fully data-driven approach to minimizing CVaR for portfolio of assets via SGLD with discontinuous updating","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.01672","snapshot_observed_at":"2026-08-07T10:41:38.939069Z","title":"A fully data-driven approach to minimizing CVaR for portfolio of assets via SGLD with discontinuous updating.arXiv preprint arXiv:2007.01672, 2020","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.939069Z"},"links":{"cited_paper":"/paper/2007.01672","citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:c210c11f2a593b4705b08b4a4ba97d98d42e80094e4d87cd3c7f226ee385686c","observation_id":"31784c12-de95-4b44-97dd-c9f2514e4e8d","resolution":{"observed_at":"2026-08-07T10:41:38.939069Z","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":"2026-08-07T10:41:38.944369Z","title":"Rapid convergence of the unadjusted Langevin algorithm: Isoperimetry suffices.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.944369Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:fece1752a3c8b7d13b87124d6932693f6e554859160ee27ac3d4fbd055321a54","observation_id":"87e690dc-3923-4542-a919-351da58670c5","resolution":{"observed_at":"2026-08-07T10:41:38.944369Z","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":"2026-08-07T10:41:39.153402Z","title":"Global convergence of Langevin dynamics based algorithms for nonconvex optimization","venue":null,"work_id":"c8ec070a-83aa-423d-b7e1-fcef34d76ec5","year":2018},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.949312Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:8d97feaa6c6d39571f8cad11e387b2de73e670265962adac5fc2dc30c56e594e","observation_id":"cac948e8-8ec7-4e13-86ba-730f54355ed6","resolution":{"observed_at":"2026-08-07T10:41:39.158513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:41:39.137385Z","title":"Nonasymptotic esti- mates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization","venue":null,"work_id":"3ed600ac-d0c1-454a-a3f5-8a691d547d5c","year":2023},"citing_paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T10:41:38.954047Z"},"links":{"citing_paper":"/paper/2506.04878"},"observation_digest":"sha256:d362b165c4c3fb4b5db42326faa6e333f623f91045df665bc7bb4c14ffebd8cf","observation_id":"00fd2465-42fa-438c-b48a-9752bc1dcbad","resolution":{"observed_at":"2026-08-07T10:41:39.142279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.04878","last_updated":"2025-06-05T10:51:18Z","latest_version":1,"primary_category":"math.ST","snapshot_observed_at":"2026-08-07T10:29:03.054787Z","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":3,"verified_fuzzy":24},"total_outbound_references":38},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 2 inbound Pith citation observations for arXiv:2506.04878."}