{"as_of":"2026-08-17T03:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ae1b0876f7ceeaca51ef49027d07cc608bd5b94cbed8af065687178ff3d6a674","coverage":[{"denominator":115,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:15:02.864259Z","state":"measured"},{"denominator":101,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":101,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-22T09:22:47.640653Z","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":"2026-05-22T09:24:45.848994Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"cited_work":{"arxiv_id":"2504.18911","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.18911","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Li, G., Lin, G., Zhang, Z., and Zhou, Q","venue":null,"work_id":"1220b54a-496a-4d5b-bdd7-550b1be080de","year":null},"citing_paper":{"arxiv_id":"2605.21765","last_updated":"2026-05-20T21:57:21Z","snapshot_observed_at":"2026-08-14T13:39:17.112647Z","submitted_at":"2026-05-20T21:57:21Z","title":"Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-22T09:22:47.640653Z"},"links":{"cited_paper":"/paper/2504.18911","citing_paper":"/paper/2605.21765"},"observation_digest":"sha256:7145514fb529a926f9ac350cfcc4a7d546d0ef393c1546b313d2777846d9b04e","observation_id":"a7ec4f75-a630-4c0e-9a37-66b17d21894a","resolution":{"observed_at":"2026-05-22T09:24:45.851119Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2504.18911/citation-record","integrity":"/paper/2504.18911/integrity","json":"/paper/2504.18911/citation-record.json","paper":"/paper/2504.18911"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:15:02.271162Z","title":"TensorFlow: Large-scale machine learning on heterogeneous systems, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.271162Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:a105cf7d02ca7dda73e7022039e58b424445d75f4ab89529e7096fc82563e2b5","observation_id":"c16da9c4-11fc-43a3-95d2-b7e603529888","resolution":{"observed_at":"2026-08-16T10:15:02.271162Z","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":"2026-08-16T10:15:02.448191Z","title":"Adaptive batch sizes for active learning: a probabilistic numerics approach","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.448191Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:ef656c600526b373c3dd1adeb65b6dfc34bb8a447878ef1065d79eeb4a5baf63","observation_id":"43449a06-0938-4c32-ac39-07b70e8b146e","resolution":{"observed_at":"2026-08-16T10:15:02.448191Z","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":"2026-08-16T10:15:02.452908Z","title":null,"venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.452908Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:71cfed70d3d3ce5090aa877fdeaa36ab44588e0a56c9dd6b0afe7ccf97387c68","observation_id":"600836c6-acfe-4814-a672-b1e27a2d1ead","resolution":{"observed_at":"2026-08-16T10:15:02.452908Z","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":"2503.09411","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:15:03.448411Z","title":"Benefits of learning rate annealing for tuning-robustness in stochastic optimization","venue":null,"work_id":"9e7a7568-b2a0-4934-b7f7-27870e641026","year":2025},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.456916Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:75f958b27cee652d69e7d3050faad80cb757aa652f70fe758831d749530e07c3","observation_id":"822d7b43-b0df-45c2-8f21-191e3b165f15","resolution":{"observed_at":"2026-08-16T10:15:03.456074Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15155","last_updated":"2025-04-05T09:24:48Z","snapshot_observed_at":"2026-08-14T07:24:52.562859Z","submitted_at":"2025-01-25T09:37:59Z","title":"Sampling with time-changed Markov processes","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.15155","snapshot_observed_at":"2026-08-16T10:15:02.461542Z","title":"Sampling with time-changed Markov processes","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.461542Z"},"links":{"cited_paper":"/paper/2501.15155","citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:41e298b0a655c9b8b050f545bde0adee364d35037978a5f9b78224c87d7a6edc","observation_id":"de321f37-c627-4be8-9180-5ec7a8082a5a","resolution":{"observed_at":"2026-08-16T10:15:02.461542Z","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":"2026-08-16T10:15:02.466499Z","title":"The fundamental incompatibility of scalable Hamiltonian Monte Carlo and naive data subsampling","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.466499Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:6e260208dd3b68458cd35456b4e750bebd3c50c13ae3d490c6131d3f12b419c5","observation_id":"b00ebad5-b526-4c66-9f89-eebb126a56b8","resolution":{"observed_at":"2026-08-16T10:15:02.466499Z","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":"2026-08-16T10:15:02.471905Z","title":"AdamMCMC: combining Metropolis-adjusted Langevin with momentum-based optimization, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.471905Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:0ede089c5911ceb607b604147c66ef72e4eade4192efad11680238242da0ab07","observation_id":"97b9a478-d0d6-4845-a157-d93c5f038c8b","resolution":{"observed_at":"2026-08-16T10:15:02.471905Z","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":"2026-08-16T10:15:02.477632Z","title":"Covertype","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.477632Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:1a373101b70a0473eb0a6b35cc897db0fcdbb81607d64ca8ac711d199fc26b7f","observation_id":"2d72e991-c53e-4f5c-b98b-56de61b0e230","resolution":{"observed_at":"2026-08-16T10:15:02.477632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.08259","last_updated":"2024-08-15T16:59:22Z","snapshot_observed_at":"2026-08-16T13:26:12.377132Z","submitted_at":"2024-08-15T16:59:22Z","title":"Incorporating Local Step-Size Adaptivity into the No-U-Turn Sampler using Gibbs Self Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.08259","snapshot_observed_at":"2026-08-16T10:15:02.482579Z","title":"Incorporating local step-size adaptivity into the No-U-Turn Sampler using Gibbs self tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.482579Z"},"links":{"cited_paper":"/paper/2408.08259","citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:29a5fe77d16dd2b22abde11abc570ce70e7604d8f7bf79598a7fa0a249fa9e5f","observation_id":"602903e0-d6bd-4b40-bf72-baf46670c484","resolution":{"observed_at":"2026-08-16T10:15:02.482579Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.15253","last_updated":"2025-06-24T21:42:56Z","snapshot_observed_at":"2026-08-16T13:58:26.887748Z","submitted_at":"2024-04-23T17:39:20Z","title":"GIST: Gibbs self-tuning for locally adaptive Hamiltonian Monte Carlo","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.15253","snapshot_observed_at":"2026-08-16T10:15:02.488745Z","title":"GIST: Gibbs self-tuning for locally adaptive Hamiltonian Monte Carlo","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.488745Z"},"links":{"cited_paper":"/paper/2404.15253","citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:54baded33670fcf9b0ebeeac605e436ae34be91db3cca21a83a0613ff9dfdafb","observation_id":"561ffee0-0b70-469f-8256-4455fdd60047","resolution":{"observed_at":"2026-08-16T10:15:02.488745Z","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":"2026-08-16T10:15:02.492978Z","title":"Long-run accuracy of variational integrators in the stochastic context","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.492978Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:dd7dec5d897d23109bff5bea992649f17a8f731b1703fff9223e0cbb60cf221c","observation_id":"188bcaa2-d938-41c5-8296-01f9e541f2d6","resolution":{"observed_at":"2026-08-16T10:15:02.492978Z","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":"2026-08-16T10:15:02.496714Z","title":"Randomized Hamiltonian Monte Carlo","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.496714Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:ef398902b1be6ec6d8b9518f80753d5b6b47fe550b071fe988cf26f082d49075","observation_id":"8bfb8ddd-7246-46d7-bd19-339f2895a36e","resolution":{"observed_at":"2026-08-16T10:15:02.496714Z","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":"2026-08-16T10:15:02.500410Z","title":"Handbook of Markov chain Monte Carlo","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.500410Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:fa35a0eb8b1eea8b5991a4a3a38bd75499e8e4e59eb905744faa509c22c1ede2","observation_id":"6a15592d-d69f-4d95-9785-8c972865f7d0","resolution":{"observed_at":"2026-08-16T10:15:02.500410Z","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":"2026-08-16T10:15:02.504257Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.504257Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:6503d755e5a0e5ea43982ca111ed1f6c2613add1acc433dbc844292c691b0d72","observation_id":"6d590cfa-68ed-43e4-bd38-8e5afb25f862","resolution":{"observed_at":"2026-08-16T10:15:02.504257Z","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":"2026-08-16T10:15:02.508088Z","title":"Stochastic boundary conditions for molecular dynamics simulations of ST2 water","venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.508088Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:802c23bee69364dc5c620b3d8ce7d7be8869ff2f1f676e358eaccefd8a36067e","observation_id":"c258e0dd-113a-4840-8fb9-e2438bfaa6de","resolution":{"observed_at":"2026-08-16T10:15:02.508088Z","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":"2026-08-16T10:15:02.511778Z","title":"Accurate sampling using Langevin dynamics","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.511778Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:4e7afb16923123e07745df4f4681c3555623e825062eb9a2135202e81ae9132d","observation_id":"7cebf363-4322-4789-a9b0-94a75bffe7ff","resolution":{"observed_at":"2026-08-16T10:15:02.511778Z","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":"2026-08-16T10:15:02.515569Z","title":"Cariñena, Eduardo Martínez, and Miguel C","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.515569Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:9d8adb6b6d852f3acab6f77e969d056064a0f1c1aed9ba917cec338b40f239d2","observation_id":"f2497e3a-a223-4954-9c75-7ebd82e17841","resolution":{"observed_at":"2026-08-16T10:15:02.515569Z","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":"2026-08-16T10:15:02.519432Z","title":"Statistical practice: Markov chain Monte Carlo in practice","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.519432Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:2e1fdc971d8c89b63ed58dff26d282965d5a751471f11d3d68208798f83d4064","observation_id":"6cd57754-a694-4b08-bf32-87f327ed8fbc","resolution":{"observed_at":"2026-08-16T10:15:02.519432Z","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":"2026-08-16T10:15:02.523236Z","title":"Unbiased kinetic Langevin Monte Carlo with inexact gradients","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.523236Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:fa99056d0f7a6367c6c6393e7614cd30615cfdd3ba27a859b26dac72f76c9160","observation_id":"771ff04b-f128-485c-b6b5-39756d7d17ec","resolution":{"observed_at":"2026-08-16T10:15:02.523236Z","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":"2026-08-16T10:15:02.528350Z","title":"Fox, and Carlos Guestrin","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.528350Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:80b45d62690f4da1138fb7ba523a2fe2dedeebaa00cfeac7b27ebabe0ba0f85d","observation_id":"2c20a560-bd0c-4d62-9fee-a5a828c5d092","resolution":{"observed_at":"2026-08-16T10:15:02.528350Z","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":"2026-08-16T10:15:02.532736Z","title":"On the convergence of a class of adam-type algorithms for non-convex optimization, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.532736Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:504c0d8a06bae840ff0f93130b76aebd08dbc0ec63ddd7f6aca58e036a79e6c0","observation_id":"b179e430-500f-4a57-baa9-c6826db410c5","resolution":{"observed_at":"2026-08-16T10:15:02.532736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.11479","last_updated":"2026-06-18T08:58:43Z","snapshot_observed_at":"2026-08-16T12:49:58.832323Z","submitted_at":"2025-03-14T15:05:52Z","title":"Towards practical PDMP sampling: Metropolis adjustments, locally adaptive step-sizes, and NUTS-based time lengths","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.11479","snapshot_observed_at":"2026-08-16T10:15:02.537137Z","title":"Towards practical PDMP sampling: Metropolis adjust- ments, locally adaptive step-sizes, and NUTS-based time lengths","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.537137Z"},"links":{"cited_paper":"/paper/2503.11479","citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:6822e5b98faf9012083c7b38630009d44d046cc597430829c1f01bb688e2b7b8","observation_id":"26ba2992-c0fa-4831-8ae6-e34731411a2b","resolution":{"observed_at":"2026-08-16T10:15:02.537137Z","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":"2026-08-16T10:15:02.541823Z","title":"A general system of differential equations to model first-order adaptive algorithms","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.541823Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:4d0ce6af5865df36a04366949bf9a1ce74545a1a5b56da5e936bcca722b1eb3e","observation_id":"d4432329-36e2-4cde-a47c-6a274e8d47bf","resolution":{"observed_at":"2026-08-16T10:15:02.541823Z","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":"2026-08-16T10:15:02.546688Z","title":"On sampling from a log-concave density using kinetic langevin diffusions","venue":null,"work_id":null,"year":1956},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.546688Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:9367d12e3bfbeae38ecedc9163e4c2d36863d8ce499a3e17007766978d525c88","observation_id":"be280fe3-ef0d-42da-a1ef-9aabd49cc043","resolution":{"observed_at":"2026-08-16T10:15:02.546688Z","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":"2026-08-16T10:15:02.551333Z","title":"Note on learning rate schedules for stochastic optimization","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.551333Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:5c9b9909f272ccfd111c30ab5ca6ba209ded228f912cf843b0323c58f93f9149","observation_id":"9d07e91a-8772-40fa-9f0a-45f054c3683e","resolution":{"observed_at":"2026-08-16T10:15:02.551333Z","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":"2026-08-16T10:15:02.555906Z","title":"Role of molecular dynamics and related methods in drug discovery","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.555906Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:b2b516fd8f95cd7eb2f7f5ee75ad298414d992e4686076c8ba057e11b1a854bf","observation_id":"113610a8-c927-475d-a0f5-b0a9e60120c9","resolution":{"observed_at":"2026-08-16T10:15:02.555906Z","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":"2026-08-16T10:15:02.560808Z","title":"Optimal linear decay learning rate schedules and further refinements, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.560808Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:6df20cbe9f93df6bbf0cd06954c3d294381fdbdf45aa618147b33969478c9b48","observation_id":"4e88d0ae-3dd4-45d3-afdd-0bb98c471773","resolution":{"observed_at":"2026-08-16T10:15:02.560808Z","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":"2026-08-16T10:15:02.566416Z","title":"A simple convergence proof of Adam and Adagrad","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.566416Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:ed87375ad64ee3cae0592c1855e570338ec1b365dbbe09f705b76610fc39bfc7","observation_id":"ba888e33-b844-4302-929c-2f759b49fc13","resolution":{"observed_at":"2026-08-16T10:15:02.566416Z","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":"2026-08-16T10:15:02.571135Z","title":"The mnist database of handwritten digit images for machine learning research","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.571135Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:fa8c0d66dc6ffd64595beef3ef5f5093a0ceb43830086eb1cb702ee93b25983a","observation_id":"775904cf-d31d-4a11-a7ea-7306fb0ef0d9","resolution":{"observed_at":"2026-08-16T10:15:02.571135Z","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":"2026-08-16T10:15:02.574899Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.574899Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:5f05e4351509e965815f219fa61c3591870815e3e3b7c2b073f1934dbbceeb6d","observation_id":"c32c2a6b-0fe5-4a20-b80d-003c5b3a2ca1","resolution":{"observed_at":"2026-08-16T10:15:02.574899Z","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":"2026-08-16T10:15:02.578576Z","title":"Bayesian sam- pling using stochastic gradient thermostats","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.578576Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:de4cc7266af0109982d922d5bf4444224076eb58c8c53210bdc01265fa765623","observation_id":"426246b9-c718-415b-a66b-19413b7294ec","resolution":{"observed_at":"2026-08-16T10:15:02.578576Z","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":"2026-08-16T10:15:02.582499Z","title":"Incorporating Nesterov Momentum into Adam","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.582499Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:44b41cb3c9e6e742c2d7f36b439278b3f2c0dc59931bf21fa5b6a24488179d0c","observation_id":"4c940ee3-4928-490c-9b19-5d7ab753b1c6","resolution":{"observed_at":"2026-08-16T10:15:02.582499Z","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":"2026-08-16T10:15:02.586466Z","title":null,"venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.586466Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:26b430ead98ef63ca8344616977ab66e3e552e6c3d5b4f75bc7e8cb6a75c25de","observation_id":"674189ed-24c0-45a9-b25b-8904c8e42a1a","resolution":{"observed_at":"2026-08-16T10:15:02.586466Z","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":"2026-08-16T10:15:02.590131Z","title":"Adaptive subgradient methods for online learning and stochastic optimization","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.590131Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:3458d9c36935353c8935342492d923458dce18fe9cb042c3799f9602d105c91e","observation_id":"30abee3c-a53f-499f-8bbf-377bb9541e27","resolution":{"observed_at":"2026-08-16T10:15:02.590131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.14542","last_updated":"2023-04-21T17:06:30Z","snapshot_observed_at":"2026-08-16T18:06:22.587474Z","submitted_at":"2021-07-30T10:45:03Z","title":"Uniform minorization condition and convergence bounds for discretizations of kinetic Langevin dynamics","version":3},"cited_work":{"arxiv_id":"2107.14542","doi":null,"metadata_source":"pith","pith_arxiv_id":"2107.14542","snapshot_observed_at":"2026-08-16T10:15:03.261602Z","title":"Uniform minorization condition and convergence bounds for discretizations of kinetic Langevin dynamics","venue":"math.PR","work_id":"b2a13827-7f5c-4392-a8a0-0b435b95193d","year":2021},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.594156Z"},"links":{"cited_paper":"/paper/2107.14542","citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:2f3d25ede134204e7856f729e80e99cb5fca1f2af7cdbda83c0325e1df4f2010","observation_id":"9ae8b4fa-96d5-43e7-b3a7-2cc07f876d21","resolution":{"observed_at":"2026-08-16T10:15:03.267003Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:02.598247Z","title":"Peláez, Charlles R","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.598247Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:1d3c6a43e6b2d60fd5804c605a3518d2c9014bb22a8ebabe914d78f813e43367","observation_id":"8092d7f3-cd92-44fe-87d2-8cf29e4533f5","resolution":{"observed_at":"2026-08-16T10:15:02.598247Z","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":"2026-08-16T10:15:02.601934Z","title":"New high-order runge-kutta formulas with step size control for systems of first and second-order differential equations","venue":null,"work_id":null,"year":1964},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.601934Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:95ae1931cfa22604055e6d73507b112c0d47363849d7d4da20b4f19307a487af","observation_id":"97239e07-0284-4d34-8168-1930a869a2c3","resolution":{"observed_at":"2026-08-16T10:15:02.601934Z","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":"2311.14201","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:15:03.235569Z","title":"On the convergence of adaptive approximations for stochastic differential equations","venue":null,"work_id":"c15a60b7-72b2-45ff-95bf-035ad1b354b4","year":2023},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.605592Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:c87e00f3541ea85771b65303e1c70eb8c46998bad8ecc960bc8c36891874ef96","observation_id":"044d7134-fc58-4fb8-a2f1-9ae411f5c2f4","resolution":{"observed_at":"2026-08-16T10:15:03.242973Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:02.609253Z","title":"Riemann manifold langevin and hamiltonian monte carlo methods","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.609253Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:86d741012c26a1352e8237b4849625f16a6708b407760cbc480457c0a7df5c43","observation_id":"1ccbdbb2-0152-4c2f-9b2d-39e7172c95aa","resolution":{"observed_at":"2026-08-16T10:15:02.609253Z","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":"2026-08-16T10:15:02.612981Z","title":"Velocity jumps for molecular dynamics","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.612981Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:37b5feef949daa3f676a1df1bd8a17b7f3029b7b3f005c0424e1e1adc00de6b1","observation_id":"f47e80e7-f6c8-4c12-87de-472d6195b9ce","resolution":{"observed_at":"2026-08-16T10:15:02.612981Z","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":"2026-08-16T10:15:02.617012Z","title":null,"venue":null,"work_id":null,"year":1970},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.617012Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:9d2917d85d32a7eca23946527c6a06f93d9fcb7ba367ec04a9732d5d1f456630","observation_id":"dc883e66-2c32-4367-aed5-39ce93de3532","resolution":{"observed_at":"2026-08-16T10:15:02.617012Z","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":"2026-08-16T10:15:02.620555Z","title":"Hopkins, Scott Le Grand, Ross C","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.620555Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:b611fdb8a59fac869a6b62485e04f46866c6cd17bce575e4ea56a3c73f223438","observation_id":"1051967c-f0fb-4080-b6f1-15ecd1db4abe","resolution":{"observed_at":"2026-08-16T10:15:02.620555Z","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":"2026-08-16T10:15:02.624579Z","title":"Horowitz","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.624579Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:f568c22ce2eabc219ea56f84bfc1624c75fd8c537a747f1ca558990a880bc670","observation_id":"fd794bea-4192-4778-a53a-e1963a5abb74","resolution":{"observed_at":"2026-08-16T10:15:02.624579Z","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":"2026-08-16T10:15:02.628471Z","title":"The adaptive verlet method","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.628471Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:eb9144fac660b9374105de34ceb247e9603c0bf147f991c6a35bddf28b1b97ac","observation_id":"50bcb021-266b-492b-b1ee-16f4adcab78b","resolution":{"observed_at":"2026-08-16T10:15:02.628471Z","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":"2026-08-16T10:15:04.359848Z","title":"Binarized neural networks","venue":null,"work_id":"3b63b1ab-6b04-458c-a180-0a6b1d61d94e","year":2016},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.632056Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:c5612c00ef76fc1c920e400f5a32fa6d65258739ff32e4f50842c448f2e3c5b9","observation_id":"608b371f-715c-44bb-9709-c8b5089e5442","resolution":{"observed_at":"2026-08-16T10:15:04.365100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:02.636086Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.636086Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:dbbab2b43f77c82046397532bbecbe1133b8903942f55cef992521c78124ee34","observation_id":"d31000de-5878-41a2-adc2-2a130fdd40d1","resolution":{"observed_at":"2026-08-16T10:15:02.636086Z","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":"2026-08-16T10:15:02.640139Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.640139Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:c3ba03c1ece9a5164f710c2465a419b71740fe5484e86f061d56efdd6ac04b27","observation_id":"6ed22500-9caf-442b-9558-d8c04ca0508d","resolution":{"observed_at":"2026-08-16T10:15:02.640139Z","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":"2026-08-16T10:15:02.644166Z","title":"Single-seed generation of Brownian paths and integrals for adaptive and high order SDE solvers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.644166Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:20f010907fbdb41ffea76c1071ec3a635c55bfa9d2b95293c17362dbadbc4bfa","observation_id":"a4220cf6-785a-4742-8fc3-754ef7c27fc4","resolution":{"observed_at":"2026-08-16T10:15:02.644166Z","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":"2026-08-16T10:15:04.328966Z","title":"Adaptive stochastic methods for sampling driven molecular systems","venue":null,"work_id":"6074d096-ca36-4d09-985e-849bdf56247f","year":2011},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.648414Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:29c8932b4c75f43fded3de833e7756785ac94df98bbe43146b17d344d4fa657a","observation_id":"6d8c6d22-ad80-401f-a483-38df438fb6f0","resolution":{"observed_at":"2026-08-16T10:15:04.332816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.314569Z","title":"Hands-on Bayesian neural networks—a tutorial for deep learning users","venue":null,"work_id":"48e21de4-f8c0-4da5-b35d-0c937ea0d065","year":2022},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.652323Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:1bc5a867b1bbe958618a3ad46dfeca5137f9f6cb638d5be18067de519a8690dc","observation_id":"b25e8029-8baf-4c85-ba34-65f9d20f5745","resolution":{"observed_at":"2026-08-16T10:15:04.319557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.300478Z","title":"Higher-order damping mechanisms with applications in optimisation and machine learning","venue":null,"work_id":"5e3dff32-bc72-4a80-8b28-034e0c98d195","year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.656782Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:7ce3ad5882e86b4f0859b2efff004646671bbb8249b5e3e8d1e1cdab018ec255","observation_id":"78c38a5b-3d73-4002-8b2a-993dde316bd6","resolution":{"observed_at":"2026-08-16T10:15:04.304879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.286075Z","title":"Analyzing and improving the training dynamics of diffusion models","venue":null,"work_id":"bceecd15-cb07-4bc1-a9d2-949341c4fa5a","year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.660837Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:71f97f439403d6d51ccdd9bf7c3ccf4252c2ff0f35a863840a2caebaca1d9b43","observation_id":"e70a2dd6-71ea-4f15-9b61-55c29aced220","resolution":{"observed_at":"2026-08-16T10:15:04.290775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:02.664937Z","title":"A style-based generator architecture for generative adversarial networks, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.664937Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:d4a8091669f4e5e58169a0d406ee460dfeea0cde79eac0e4cf25bb91d68527c1","observation_id":"25cccefd-b0a3-4967-bf44-2c0e3491a169","resolution":{"observed_at":"2026-08-16T10:15:02.664937Z","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":"2026-08-16T10:15:02.669455Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.669455Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:9b46223eab28935e2530d9d9d213081f71f57b762b8d077106dd0ac0ec56022e","observation_id":"5b0ff181-3988-4029-bee0-93c6bd110f35","resolution":{"observed_at":"2026-08-16T10:15:02.669455Z","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":"2026-08-16T10:15:04.251193Z","title":"Computational methods in ordinary differential equations","venue":null,"work_id":"9e0f4dd6-b212-4ee1-ac7d-a7229a1dc38b","year":1973},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.673767Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:9204766b37f2428760570cf50bda31300638a8e776c879e047e8d5d4249fe312","observation_id":"0b74f05a-7104-49fc-bce9-919f699507b3","resolution":{"observed_at":"2026-08-16T10:15:04.256450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.237003Z","title":"Rational construction of stochastic numerical methods for molecular sampling","venue":null,"work_id":"1b58980a-f114-490b-9351-b7587fd7758b","year":2012},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.678110Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:1e679f7c5bded1da9c8695359b5e2be9f80f6e19061c6ebd6238925d6a0d7072","observation_id":"b5ca6e3b-7ff2-4eba-82cf-79880ee05e9c","resolution":{"observed_at":"2026-08-16T10:15:04.241280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.224415Z","title":"Efficient molecular dynamics using geodesic integration and solvent–solute splitting","venue":null,"work_id":"4b70aa47-5ce7-4756-85b6-ad17f1b14a99","year":2016},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.682886Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:995a4ec6e637fe77b2d4a759254bcb921282e100e07babe069bcdaff6e717762","observation_id":"e19820ac-95b6-475d-8999-9f1e2aeefdb5","resolution":{"observed_at":"2026-08-16T10:15:04.228348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.210191Z","title":"The computation of averages from equilibrium and nonequilibrium Langevin molecular dynamics","venue":null,"work_id":"4eec2291-414a-47d5-9695-5335abf4e650","year":2016},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.687364Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:6e5d7928bffb8e25b6c56242b90acfbedef8b953089ebd0017b96f3e776ebe21","observation_id":"a6ef8470-34db-4862-918a-9f307e380b29","resolution":{"observed_at":"2026-08-16T10:15:04.215084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.195760Z","title":"Ensemble preconditioning for Markov chain Monte Carlo simulation","venue":null,"work_id":"816024b9-3f61-4f7e-b8de-001be3882d94","year":2018},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.692560Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:6559c2626fd91fda4e37cb793a47a78f78dbf7bd80cfac586a5b2cd4e4a66e89","observation_id":"7e502444-5572-4861-82f6-aa20fe30028c","resolution":{"observed_at":"2026-08-16T10:15:04.200419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.181034Z","title":"Molecular Dynamics: With Deterministic and Stochastic Numerical Methods","venue":null,"work_id":"b4298f7b-ce23-4ae4-a50e-238856cb6410","year":2015},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.697250Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:8a482bb87e16b7ebe862d3e5b0ecf917fc03dcaa04ea55dfae46eca49fbbdd3e","observation_id":"c4656043-a3aa-4e28-bd7d-13c7815e16be","resolution":{"observed_at":"2026-08-16T10:15:04.185684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.166791Z","title":null,"venue":null,"work_id":"fd655ca7-c18f-41c5-9a92-e496597c7ac0","year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.702033Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:e7b872be584b47f218378caa82bd995841c8ffb3fc5765d576a5e1af0bb3641c","observation_id":"bec2e060-1f7b-4ad3-b65b-210799cdc9fd","resolution":{"observed_at":"2026-08-16T10:15:04.171215Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.152351Z","title":null,"venue":null,"work_id":"44daa712-cd82-49fd-aa19-4ebd419812ac","year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.706276Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:48c3480bfffd121b872c5fe4fb3afbf454d31e875cfe13258a205786095000a1","observation_id":"293009fb-a179-473c-93a9-d5a48b63ec7d","resolution":{"observed_at":"2026-08-16T10:15:04.157089Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.137930Z","title":"How do adam and training strategies help bnns optimization","venue":null,"work_id":"5a6e6f2c-5ccb-49c1-9998-c8c59ea7477c","year":2021},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.709903Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:f041ee341a383908612f2637794748583e9c7840becb4ae1e52a0076560842ad","observation_id":"a5061662-1c5b-4e21-8f4d-e9a12f3247f5","resolution":{"observed_at":"2026-08-16T10:15:04.142008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.124396Z","title":"Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise","venue":null,"work_id":"534b8de9-14dd-4bee-969c-71caf622918c","year":2002},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.713691Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:a62abe099b7ad5df8d3d7549bbf126764b7e82aa41828e7328939a030ded71de","observation_id":"9e7e7263-2c79-4dc8-abb9-f50b78cc2014","resolution":{"observed_at":"2026-08-16T10:15:04.128925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.06162","last_updated":"2018-12-14T20:49:09Z","snapshot_observed_at":"2026-08-14T17:43:20.166812Z","submitted_at":"2018-12-14T20:49:09Z","title":"An Empirical Model of Large-Batch Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.06162","snapshot_observed_at":"2026-08-16T10:15:02.717474Z","title":"An empirical model of large-batch training","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.717474Z"},"links":{"cited_paper":"/paper/1812.06162","citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:fb7dae4dec016cde05f422d9c2579bddbbac6b955982776efacf1c68a6bd5a72","observation_id":"8c521396-6745-4578-85a6-180a5a6cfee2","resolution":{"observed_at":"2026-08-16T10:15:02.717474Z","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":"2026-08-16T10:15:04.108740Z","title":"Adaptive bound optimization for online convex optimization, 2010","venue":null,"work_id":"2a9292a7-9fbe-4703-9a4e-c349886def2d","year":2010},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.721389Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:979dfa3ac118100ead45f14f5642174f167373af2c29c5f9ff0e6205512a9e43","observation_id":"10e5138a-2b92-49fa-ac39-2c031d9205ea","resolution":{"observed_at":"2026-08-16T10:15:04.114064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.092990Z","title":"Design of quasisymplectic propagators for langevin dynamics","venue":null,"work_id":"bfcd2b05-f9a0-4875-8adb-bc2de31af212","year":2007},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.725222Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:2059f6e379a230ef5c550e36fc6e01ed941dee0bf0df9e99dba50a3e39d2e75f","observation_id":"4809fbae-970b-4f26-927b-62707718ad64","resolution":{"observed_at":"2026-08-16T10:15:04.098592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.078297Z","title":"Rosenbluth, Marshall N","venue":null,"work_id":"40cfbf50-d8a7-4b17-8af0-28e1a9fa0869","year":1953},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.728836Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:72545f716e4e694c37dfba962170e386b6f07fc92492b894c950163ccaa0041a","observation_id":"6cdd6788-c0ba-4431-a86e-ccc5c581f23a","resolution":{"observed_at":"2026-08-16T10:15:04.083535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.064083Z","title":"Numerical integration of stochastic differential equations with nonglobally lipschitz coefficients","venue":null,"work_id":"8a2aebd0-8ed4-4cfc-8bab-e80ec4381820","year":2005},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.732472Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:6cddf4a5a25af8e54035fd95f99a41cd733fb664bc6bf608663ab4e9fd4bc493","observation_id":"84363ede-fa6f-4fa6-9fc8-3174e4bde9b3","resolution":{"observed_at":"2026-08-16T10:15:04.068727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.049308Z","title":"High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion","venue":null,"work_id":"bd3b1da3-9daf-4f2f-8aa4-359dac79df8a","year":2021},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.736176Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:71eaf47a2acf1d5bb6bfa7eca1ece2984477436bae10d281976e8e5a4b9e038d","observation_id":"83876ff5-dd89-4cc8-b5ad-f70734f7617a","resolution":{"observed_at":"2026-08-16T10:15:04.054092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.036349Z","title":"Monnahan, James T","venue":null,"work_id":"178438d3-b1a3-4649-8b0d-706833d793c4","year":2017},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.740126Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:49578238150783059b6fc02b005994da8ee174029aa0de59bd21bb2d66cf67d1","observation_id":"b87ec630-aeb6-4af1-be3c-2c0d5a04ce02","resolution":{"observed_at":"2026-08-16T10:15:04.040245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.022148Z","title":"Bayesian neural networks, 2018","venue":null,"work_id":"ac10ae85-98d4-4c36-9e54-0b5ef5d85f03","year":2018},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.744090Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:88bedcdf1291209bb9f3b144dce4f71a7ebe75d722f7a9cab24de391c0df838f","observation_id":"8499b3f1-0a2c-4494-b82d-24f923dfbb1d","resolution":{"observed_at":"2026-08-16T10:15:04.026471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:04.006549Z","title":null,"venue":null,"work_id":"32d32ea8-af06-4cc1-a844-fbda0ec9b15b","year":1996},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.747926Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:13e3a6f1c7e328bf85ce08d0980bf3f7b53f8364c871c22f28d0ea3400db310a","observation_id":"95fa15f9-85b9-4543-bb6b-ce761856c0ce","resolution":{"observed_at":"2026-08-16T10:15:04.011585Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.989644Z","title":null,"venue":null,"work_id":"b55243dc-92a6-4034-96cf-5f98806da221","year":2001},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.752402Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:20582d13df85cd74e4de3105b90cb6661e82d0fc38ac412275977b92008d2fcc","observation_id":"41296582-ba34-4798-ac5a-601302a9491e","resolution":{"observed_at":"2026-08-16T10:15:03.994113Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.974431Z","title":"PyTorch: An imperative style, high-performance deep learning library","venue":null,"work_id":"11ab6103-d868-42ba-99dd-096928cdb81b","year":2019},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.756301Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:b25752b39ee47265c4793aab0f3807e2051ca3b8002fa4f93c658ba3a9dcf2b0","observation_id":"1bc9e479-9e58-4f50-bb8d-8d46e24a4572","resolution":{"observed_at":"2026-08-16T10:15:03.979480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.960517Z","title":"Sampling from Bayesian neural network posteriors with symmetric minibatch splitting Langevin dynamics","venue":null,"work_id":"783d11f6-572c-4ad3-b41a-f43324fd12a0","year":2025},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.760085Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:6bb4d0401c3971c66edb40de1bfef2ee69f7e7d85cc736d2285d0c0d0ece4348","observation_id":"56b81ff7-90a3-4952-ab0e-f1fa42db6c38","resolution":{"observed_at":"2026-08-16T10:15:03.964786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.945711Z","title":"Stochastic processes and applications: diffusion processes, the Fokker-Planck and Langevin equations","venue":null,"work_id":"253f49d3-4737-4888-b9d4-fff006156678","year":2014},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.763839Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:0c4e12e273307527ebe2ee9dcae657b2f62ce1b791790364b3ddc609786e445b","observation_id":"1560ef3e-a8de-4537-8eca-20301a93e9fe","resolution":{"observed_at":"2026-08-16T10:15:03.950507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.929418Z","title":"Numerics with coordinate transforms for efficient Brownian dynamics simulations","venue":null,"work_id":"c066f2af-f6c7-4d67-9671-d36bfee4e27e","year":2024},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.767855Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:0800e5a710907cfddd4510e346aa26c9287472cf97b19d314b4a6341a9a4a6cd","observation_id":"3cb8eef1-a9b6-42a8-83b7-5fabb121d2bf","resolution":{"observed_at":"2026-08-16T10:15:03.935077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:02.772475Z","title":"Unsupervised representation learning with deep convolutional generative adversarial networks, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.772475Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:3c0ecd80c81936c5066e854c235e7bc27f4574aa57e4ad489a8fe762c9591595","observation_id":"84b7ef6d-c366-4040-bef0-261e089f0aa6","resolution":{"observed_at":"2026-08-16T10:15:02.772475Z","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":"2026-08-16T10:15:03.904981Z","title":"Improving language understanding by generative pre-training [openai blog]., 2018","venue":null,"work_id":"d4e00176-b0e6-45ac-9a96-1a49514361de","year":2018},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.776607Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:2ecc0661c7782e1ab8efa21a8b4e7ad5053fe7659b498c2821f2a8b6efa2b79b","observation_id":"0caff4c7-393d-4347-a3fc-497d51cf8df2","resolution":{"observed_at":"2026-08-16T10:15:03.909778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:02.780365Z","title":"Reddi, Satyen Kale, and Sanjiv Kumar","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.780365Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:b001941b4991bef9f946fec30d7a7cc5ad9b4ccde73839808e01de78d2c69b48","observation_id":"a0fcef43-2c62-474b-8c3b-d3cfc731edbf","resolution":{"observed_at":"2026-08-16T10:15:02.780365Z","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":"2026-08-16T10:15:03.880898Z","title":"Sarhan, and M","venue":null,"work_id":"6f735018-2e6c-4ea9-a681-a57f3f483dc1","year":2023},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.784085Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:3f53d95295eafd1b0ea307bf59457a470617ea46f21405d04abd4105938b1609","observation_id":"20736a53-2459-4478-8c8a-857f5d336034","resolution":{"observed_at":"2026-08-16T10:15:03.885177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.864898Z","title":"Metropolis adjusted Langevin trajectories: a robust alternative to Hamiltonian Monte Carlo, 2023","venue":null,"work_id":"105ab7cf-1e21-4d8c-bef0-eb8faa3cf424","year":2023},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.788615Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:69c3a300129f4dd76b2afa3338e3ddc1badda9834b5bbd907a5e54296a359b11","observation_id":"c4ee9b66-a47e-489d-9274-08d10b1f7397","resolution":{"observed_at":"2026-08-16T10:15:03.870813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.851313Z","title":"A Stochastic Approximation Method","venue":null,"work_id":"a7a5af0b-0b90-4066-9622-5b9a66595c2c","year":1951},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.792832Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:01353e37f6f3b5a67460fa1fc17e8ed157ed6d88a210640b5bea1394bbbe7647","observation_id":"791e67fc-ba4b-4521-a7c6-b4c2887e3760","resolution":{"observed_at":"2026-08-16T10:15:03.855575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:02.797235Z","title":"Optimal scaling of discrete approximations to Langevin diffusions","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.797235Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:3778d3cfbd1eae4bf163c7f22ea806d33b86411129bb3623e153cae6ccf40056","observation_id":"c5adfdda-0dd8-4012-ae2b-536bffbef94b","resolution":{"observed_at":"2026-08-16T10:15:02.797235Z","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":"2026-08-16T10:15:02.801574Z","title":"Roberts and Richard L","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.801574Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:8eddce3319a8f2e9e7f0cc607dd77ba4fb50d561deb9bc933ac0bd5bf75dc978","observation_id":"342cb840-466f-4f15-b671-ca3ded3b02ac","resolution":{"observed_at":"2026-08-16T10:15:02.801574Z","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":"2026-08-16T10:15:03.818808Z","title":"An adaptive discretization algorithm for the weak approximation of stochastic differential equations","venue":null,"work_id":"95c46fbc-cc3a-43f3-b40f-c59ca01156e1","year":2004},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.805832Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:dec79c0ac80b5c84afd983b8434393d3df8b6a50078a0c23d4dba9a7c65d4414","observation_id":"16bba334-0fb2-4c0f-bc10-c2d42662068d","resolution":{"observed_at":"2026-08-16T10:15:03.823198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.805105Z","title":"Langevin dynamics with variable coefficients and nonconservative forces: from stationary states to numerical methods","venue":null,"work_id":"4ed2a5b4-208d-4e14-a57c-d9649eb2b8be","year":2017},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.810312Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:2ef741c98dd44feca77a6414451687d98b508af4d34e57f13c8451e850a8d9ff","observation_id":"20869330-43e2-493a-9765-42a967d25dc3","resolution":{"observed_at":"2026-08-16T10:15:03.809637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.792270Z","title":"Biomolecular dynamics at long timesteps","venue":null,"work_id":"90a22c54-d25e-47f3-9df1-45ab1743f9d4","year":1997},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.814549Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:9fa689ee66b8fba2b704237ef8cae7e2de7c7dfd2df8d0d8bcfa6d4a31ad6c16","observation_id":"b9f5c713-9d98-49f6-88b6-642cafcc128c","resolution":{"observed_at":"2026-08-16T10:15:03.796147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.779735Z","title":"Covariance-controlled adaptive langevin thermostat for large-scale bayesian sampling","venue":null,"work_id":"5a511bfa-d93b-43ce-9213-660cb4499109","year":2015},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.818809Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:e87fd6212f5a1e3bbb5c0bad1e5e30040ebfaf750dbe8329cdc7948c5bfeab36","observation_id":"d40ee48f-1914-4785-85f3-b5ae302a3eba","resolution":{"observed_at":"2026-08-16T10:15:03.783718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2501.16055","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T10:15:03.083284Z","title":"Random reshuffling for stochastic gradient Langevin dynamics","venue":null,"work_id":"58b4172b-2f91-43cc-8610-164079bd41fe","year":2025},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.823396Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:d2ae085d44a4ba171127a8a2211d830a89466f3a833503780dc0e672a3f371e2","observation_id":"1b48f3d8-34cd-465a-a9d5-8758f92e4a1c","resolution":{"observed_at":"2026-08-16T10:15:03.093138Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.04274","last_updated":"2025-04-05T20:07:34Z","snapshot_observed_at":"2026-08-16T12:43:42.291448Z","submitted_at":"2025-04-05T20:07:34Z","title":"Randomised Splitting Methods and Stochastic Gradient Descent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.04274","snapshot_observed_at":"2026-08-16T10:15:02.827928Z","title":"Randomised splitting methods and stochastic gradient descent","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.827928Z"},"links":{"cited_paper":"/paper/2504.04274","citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:7fc4114b97e5ec749c2cc2ab0e586e2c8020d7ed09fd982f963477ceaf90dc4c","observation_id":"47e9c28c-ce5e-4c84-ad0d-cb2694f26fd5","resolution":{"observed_at":"2026-08-16T10:15:02.827928Z","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":"2026-08-16T10:15:03.765643Z","title":"Integration schemes for molecular dynamics and related applications","venue":null,"work_id":"b6609600-1b8d-4887-b78c-384f27cd07bf","year":1999},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.832634Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:55e2e8105509609cf2ad62ff36328a71c224160c7f96892f07788cf525aba639","observation_id":"43c3f446-1540-4ea4-8709-80a854ed6f81","resolution":{"observed_at":"2026-08-16T10:15:03.770442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.751592Z","title":"An impulse integrator for Langevin dynamics","venue":null,"work_id":"8ec8b7b0-856b-4445-a384-c4b9bb6e35ea","year":2002},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.836940Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:519d91137d4048fa1181ea9402172f54873ed70f2d7b07c303e8ccc4b9b7fc80","observation_id":"80c37ae4-9bdf-49f0-87fc-444dc94a3ef9","resolution":{"observed_at":"2026-08-16T10:15:03.756209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.00489","last_updated":"2018-02-24T00:16:12Z","snapshot_observed_at":"2026-08-14T20:17:53.425800Z","submitted_at":"2017-11-01T18:04:31Z","title":"Don't Decay the Learning Rate, Increase the Batch Size","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.00489","snapshot_observed_at":"2026-08-16T10:15:02.841384Z","title":"Smith, Pieter-Jan Kindermans, and Quoc V","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.841384Z"},"links":{"cited_paper":"/paper/1711.00489","citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:07e87dfdc5be28f74ebd21e81dc41d5c1e62acdb5c52462c220f45a2bbcae88e","observation_id":"92dd7fa0-90d0-4bc9-a501-d30bfa369ae0","resolution":{"observed_at":"2026-08-16T10:15:02.841384Z","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":"2026-08-16T10:15:03.737381Z","title":"Variable steps for reversible integration methods","venue":null,"work_id":"2533f819-3b6e-48fb-b475-14c6f43f1e89","year":1995},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.845995Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:713219534aba17610558985b5cbfc5b61fb0544b53d4c33ac5a58522e5178a89","observation_id":"7d629361-d8b4-4822-9ddd-331346e07d2c","resolution":{"observed_at":"2026-08-16T10:15:03.742014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.722877Z","title":"Mémoire sur le problème des trois corps","venue":null,"work_id":"bbe4e88f-9c38-4b81-9a33-75b1142f6763","year":1912},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.850587Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:5a0f969b0e56216d075e0a89d06f151f4b33044f94e2815d0737856606704bb9","observation_id":"9d802ba7-b7c0-4f48-afdb-c8e2a559de4d","resolution":{"observed_at":"2026-08-16T10:15:03.727455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.707831Z","title":"Adaptive weak approximation of stochastic differential equations","venue":null,"work_id":"dff91d0f-5a8b-4665-bd3e-469225d9a2ed","year":2001},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.855007Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:dace32cb0a2013d3cfd55e7e4dc3ede15c6e863849b13efbc587c6a177cfa2ef","observation_id":"dd0a885b-d9c2-4f02-be61-177035c05528","resolution":{"observed_at":"2026-08-16T10:15:03.713116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.694204Z","title":"Stochastic hamiltonian systems: exponential convergence to the invariant measure, and discretization by the implicit euler scheme","venue":null,"work_id":"2a52bfa6-aa06-409d-a2e6-c2a5dffa1b03","year":2002},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.859763Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:a2feda75f3f9f7e63a81cfb751d2fb4b5cdf6452cd274cc7addae869368ced82","observation_id":"dbe1d9d5-507b-4439-a070-7684c5b1e73f","resolution":{"observed_at":"2026-08-16T10:15:03.698223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-16T10:15:03.680037Z","title":"Lecture 6.5 - rmsprop, coursera: Neural networks for machine learning., 2012","venue":null,"work_id":"2839cfdb-ebe0-445f-94cc-92a9db8c9867","year":2012},"citing_paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer","version":2},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-16T10:15:02.864259Z"},"links":{"citing_paper":"/paper/2504.18911"},"observation_digest":"sha256:8b36e6f9811510f633c93ea06f6d8ae723e66461930edb502a887da8bad1d9e8","observation_id":"e719f93f-fed7-42db-ab3a-b322137b5db7","resolution":{"observed_at":"2026-08-16T10:15:03.684842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.18911","last_updated":"2025-05-26T12:19:39Z","latest_version":2,"primary_category":"stat.CO","snapshot_observed_at":"2026-08-16T10:04:16.064836Z","submitted_at":"2025-04-26T12:57:57Z","title":"A Langevin sampling algorithm inspired by the Adam optimizer"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":57,"verified_exact":4,"verified_fuzzy":39},"total_outbound_references":115},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 100 of 115 outbound references and 1 inbound Pith citation observation for arXiv:2504.18911."}