{"as_of":"2026-08-16T17:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a75d1424744c57d3a1c62e292fb0c7cba6c025afd3192771f2a1a92f40a4a7ed","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:39:11.477985Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.02910/citation-record","integrity":"/paper/1908.02910/integrity","json":"/paper/1908.02910/citation-record.json","paper":"/paper/1908.02910"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:39:12.428243Z","title":"Distributed delayed stochastic optimization","venue":null,"work_id":"0038f58c-63e5-402d-aad1-1b15990af1f3","year":2011},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.153621Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:7db1eace9c02f492a6f14ac05584b70f2e1838d21a4c847e139b412fe3fd0fd4","observation_id":"eaaa870d-8252-48e0-bd8b-297a01a43a50","resolution":{"observed_at":"2026-08-14T14:39:12.434871Z","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":"1206.6380","last_updated":"2012-06-27T19:59:59Z","snapshot_observed_at":"2026-08-15T00:55:08.237443Z","submitted_at":"2012-06-27T19:59:59Z","title":"Bayesian Posterior Sampling via Stochastic Gradient Fisher Scoring","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1206.6380","snapshot_observed_at":"2026-08-14T14:39:11.161950Z","title":"Bayesian posterior sampling via stochastic gradient Fisher scoring","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.161950Z"},"links":{"cited_paper":"/paper/1206.6380","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:8ac0117105d0d2077bb7c97c0137286ffdb1d1e1c643092c574a893577a3181d","observation_id":"e30ade1e-c653-4bcd-abab-22e55387820a","resolution":{"observed_at":"2026-08-14T14:39:11.161950Z","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":"2026-08-14T14:39:12.408354Z","title":"The pseudo-marginal approach for efficient monte carlo computations","venue":null,"work_id":"5f52aa59-556f-4549-99f2-bc6b98505ea6","year":2009},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.168130Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:2c8593c8157dfb13977227963402bdf289ffa42dfe46521436645766f07e9139","observation_id":"3c92c048-ea6f-474f-818b-ca96f2d665b3","resolution":{"observed_at":"2026-08-14T14:39:12.414830Z","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":"2026-08-14T14:39:12.385785Z","title":"Towards scaling up Markov chain Monte Carlo: an adaptive subsampling approach","venue":null,"work_id":"cca43a5f-dd98-409b-aa11-847fbb99b48d","year":2014},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.176209Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:7d29b20e02419b0a167d4f87335e949dadb30fdc145ae940a9b29c63232c4334","observation_id":"7df05cd4-e9e3-4762-8d30-fca6cfbfa553","resolution":{"observed_at":"2026-08-14T14:39:12.391943Z","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":"1505.02827","last_updated":"2015-05-11T22:51:02Z","snapshot_observed_at":"2026-08-14T22:48:59.845307Z","submitted_at":"2015-05-11T22:51:02Z","title":"On Markov chain Monte Carlo methods for tall data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1505.02827","snapshot_observed_at":"2026-08-14T14:39:11.187935Z","title":"On Markov chain Monte Carlo methods for tall data","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.187935Z"},"links":{"cited_paper":"/paper/1505.02827","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:17060945250540c27c81307dea2683906911acde2aaf4f4282528682d82b718f","observation_id":"d407ac4c-e6a4-4a67-93bf-2ce33cb6835c","resolution":{"observed_at":"2026-08-14T14:39:11.187935Z","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":"2026-08-14T14:39:12.364971Z","title":"Spectrally-normalized margin bounds for neural networks","venue":null,"work_id":"0884788f-8fb5-4ec5-9b82-f91076b2452b","year":2017},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.196765Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:1d64a39a9aa910faad53ddc0bcd6ce4b5996e7ac6ea211794a58417b6c9b3b33","observation_id":"8b772f92-ae72-4b2e-b174-78dd69f2960e","resolution":{"observed_at":"2026-08-14T14:39:12.370321Z","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":"2026-08-14T14:39:12.337757Z","title":"The zig-zag process and super- efficient sampling for bayesian analysis of big data","venue":null,"work_id":"1fe7fac8-0170-41a3-bce0-8fda633764bc","year":2019},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.204797Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:804d009a1258617edfefaabc6f4bca0d4aab7aa8f0484edc3cf5d079514a4580","observation_id":"2d27adf2-50e7-4623-be5a-2f1c1dfdd661","resolution":{"observed_at":"2026-08-14T14:39:12.345026Z","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":"2026-08-14T14:39:12.315441Z","title":"Variational inference: A review for statisticians","venue":null,"work_id":"6a8f9981-3c75-4e11-be0f-c63dd1fa4007","year":2017},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.215486Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:d4dd7cc713c615cca01fcf38ee05b84284656dec7ed7e8be2c0387bbb3e1c137","observation_id":"a1ffb179-596c-48a0-b53b-0fb5068cc2ec","resolution":{"observed_at":"2026-08-14T14:39:12.321052Z","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":"1610.06848","last_updated":"2017-07-09T16:36:03Z","snapshot_observed_at":"2026-08-14T21:34:36.503535Z","submitted_at":"2016-10-19T00:19:25Z","title":"An Efficient Minibatch Acceptance Test for Metropolis-Hastings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.06848","snapshot_observed_at":"2026-08-14T14:39:11.222423Z","title":"An efficient minibatch acceptance test for Metropolis-Hastings","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.222423Z"},"links":{"cited_paper":"/paper/1610.06848","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:5ad6f952fb3b1e4fdccaa372639c5fc4f68beb375f01291598cf249232869c57","observation_id":"d6d5fdda-8e9a-4b67-83c9-e85f5cd006f9","resolution":{"observed_at":"2026-08-14T14:39:11.222423Z","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":"2026-08-14T14:39:11.229657Z","title":"Stochastic gradient hamiltonian monte carlo","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.229657Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:6b8817cdfaf5d50e56cbebdb4a7c20024861327bee10ed5f68fa359a6c09de14","observation_id":"7c2f5259-8c03-46fc-8fce-16853f6d7bf7","resolution":{"observed_at":"2026-08-14T14:39:11.229657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.06086","last_updated":"2018-06-15T18:26:11Z","snapshot_observed_at":"2026-08-14T19:03:07.455313Z","submitted_at":"2018-06-15T18:26:11Z","title":"Minibatch Gibbs Sampling on Large Graphical Models","version":1},"cited_work":{"arxiv_id":"1806.06086","doi":null,"metadata_source":"pith","pith_arxiv_id":"1806.06086","snapshot_observed_at":"2026-08-14T14:39:11.774336Z","title":"Minibatch Gibbs Sampling on Large Graphical Models","venue":"cs.LG","work_id":"d8ec36f5-12db-445e-87b5-3f8f95d5eda4","year":2018},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.244022Z"},"links":{"cited_paper":"/paper/1806.06086","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:8ac5101d967307de7b885d517586aea2efa2c006cdc2ec7b1d0563d4bb753908","observation_id":"7d5929b0-5f7d-4d8a-b09c-c2827f2d2877","resolution":{"observed_at":"2026-08-14T14:39:11.782722Z","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":{"arxiv_id":"1802.00568","last_updated":"2018-02-02T05:52:48Z","snapshot_observed_at":"2026-08-14T19:49:39.914739Z","submitted_at":"2018-02-02T05:52:48Z","title":"An Instability in Variational Inference for Topic Models","version":1},"cited_work":{"arxiv_id":"1802.00568","doi":null,"metadata_source":"pith","pith_arxiv_id":"1802.00568","snapshot_observed_at":"2026-08-14T14:39:11.737209Z","title":"An Instability in Variational Inference for Topic Models","venue":"stat.ML","work_id":"786a208b-e029-41e6-b3fc-84d90f0bb612","year":2018},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.252116Z"},"links":{"cited_paper":"/paper/1802.00568","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:924a06cac5c2a48a752a096ce3bee905ead520a02c8a93072a8b2309b97d608f","observation_id":"0be4dac3-4216-481e-8b6c-033f7f05d2ad","resolution":{"observed_at":"2026-08-14T14:39:11.746968Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:39:12.267888Z","title":"On nonnegative unbiased estimators","venue":null,"work_id":"991e8f02-6d58-4098-80ad-48aa1fd8e067","year":2015},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.261680Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:06a2fe43ded67d01bc935b528be5503317ae4d5b752e291a14a4a1415e2a6792","observation_id":"58aa6ced-17bf-4964-a4c9-e645cb24df24","resolution":{"observed_at":"2026-08-14T14:39:12.279288Z","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":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-14T14:39:11.267031Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.267031Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:008f9eab61b2fa214f47c2cd2350dec97686aa013b4922ff675cd15c94d199fa","observation_id":"dd65e0e6-3172-4ca4-adb2-3ad196121253","resolution":{"observed_at":"2026-08-14T14:39:11.267031Z","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":"2026-08-14T14:39:12.237006Z","title":"Austerity in MCMC land: Cutting the Metropolis-Hastings budget","venue":null,"work_id":"c38c4a7e-fd76-4f47-9408-b8efdd94ea76","year":2014},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.275274Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:2dcfe440b5203688bb7a5cf110c3ee03996359983d60379815daca32c76c0949","observation_id":"12538733-fb76-4fb8-8b38-e2b21dcc1982","resolution":{"observed_at":"2026-08-14T14:39:12.248216Z","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":"2026-08-14T14:39:12.211655Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"af6abf44-88e7-4103-ace0-dec73c500ebf","year":2009},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.283540Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:af159ef09bf02f89d16d0de86a1316b29668369ada6e5e06adaac42567e7a635","observation_id":"995d52e3-a3d5-445f-bdfe-ba9c74f83d1a","resolution":{"observed_at":"2026-08-14T14:39:12.218789Z","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":"2026-08-14T14:39:12.191045Z","title":"Preconditioned stochastic gradient langevin dynamics for deep neural networks","venue":null,"work_id":"1899a3c7-610a-465d-b917-78293c13905a","year":2016},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.298194Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:4519009399b2e74f75bbafd7f87722ebeae438c993dd7b02ba10477dd2ffb5f3","observation_id":"264a47ad-37f5-4ac1-952d-edf48ba38687","resolution":{"observed_at":"2026-08-14T14:39:12.198596Z","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":"1707.09705","last_updated":"2018-05-21T18:09:49Z","snapshot_observed_at":"2026-08-14T20:44:20.214559Z","submitted_at":"2017-07-31T03:07:00Z","title":"Mini-batch Tempered MCMC","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.09705","snapshot_observed_at":"2026-08-14T14:39:11.311897Z","title":"Mini-batch tempered mcmc","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.311897Z"},"links":{"cited_paper":"/paper/1707.09705","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:307ee871edb6ea62fee8f783937fe197c265280e2cebd9ba5cfd41a3e9696950","observation_id":"64c7664c-bbfa-452c-88e1-7b5e31badc29","resolution":{"observed_at":"2026-08-14T14:39:11.311897Z","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":"2026-08-14T14:39:12.162220Z","title":"Firefly Monte Carlo: Exact MCMC with subsets of data","venue":null,"work_id":"0a722efb-ac09-498b-966c-78c43bc9c163","year":2014},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.320916Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:50ccbca52dddba6f9469200afe18b41a5e5a4a2ab518f9da032c86e36e8701de","observation_id":"c16b2033-f958-440e-b95a-6d336915c3aa","resolution":{"observed_at":"2026-08-14T14:39:12.171000Z","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":"2026-08-14T14:39:12.131855Z","title":"Mean field for the stochastic blockmodel: Optimization landscape and convergence issues","venue":null,"work_id":"802cd96c-5776-4c42-8cca-32ab272f7ba3","year":2018},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.334852Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:6b4ebc5a10a375b3c8d5a6eafae0527502a7a073acf3f0413b76af5c9980986e","observation_id":"fdc84b1c-3a22-40ef-9589-241f5d84c44a","resolution":{"observed_at":"2026-08-14T14:39:12.144986Z","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":"2026-08-14T14:39:11.344358Z","title":"Mcmc using hamiltonian dynamics","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.344358Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:4005c8c74ff9fd64d78f693281292e22bf8c26aa73547a450e4cb79503959742","observation_id":"467ddf46-6637-4aca-bc7d-671a7c9ac397","resolution":{"observed_at":"2026-08-14T14:39:11.344358Z","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":"2026-08-14T14:39:12.084314Z","title":"Asymptotically exact, embarrassingly parallel mcmc","venue":null,"work_id":"f32dda14-8fde-424c-bfbc-0a7f58d23e0e","year":2013},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.358794Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:f499939baed2a6088696a9e44efd148ae7a210db719d7224541f1e1cf737d55b","observation_id":"d633f801-0768-4f9b-ba7b-13441f2843f2","resolution":{"observed_at":"2026-08-14T14:39:12.091351Z","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":"2026-08-14T14:39:12.049182Z","title":"Speeding up mcmc by efficient data subsampling","venue":null,"work_id":"01cce929-1447-43c7-89db-17cb338dc086","year":2018},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.368196Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:904555519371b3047e7e25de1068269257a9e5193bbd6f21393ff7c4c84afb9d","observation_id":"7b8881a4-7daa-4253-8a89-09395d8f9a13","resolution":{"observed_at":"2026-08-14T14:39:12.058296Z","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":"1702.03849","last_updated":"2017-06-04T04:26:02Z","snapshot_observed_at":"2026-08-14T21:16:43.585950Z","submitted_at":"2017-02-13T16:11:38Z","title":"Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.03849","snapshot_observed_at":"2026-08-14T14:39:11.380209Z","title":"Non-convex learning via stochastic gradient langevin dynamics: a nonasymptotic analysis","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.380209Z"},"links":{"cited_paper":"/paper/1702.03849","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:e1949e66c870d9b1e86f0529eb631c27efacd8032cf2d2cc47ed82ac76fd4042","observation_id":"4aa40953-b6a3-4348-929a-7da0a42eecd2","resolution":{"observed_at":"2026-08-14T14:39:11.380209Z","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":"2026-08-14T14:39:12.018167Z","title":"A stochastic approximation method","venue":null,"work_id":"2bf95673-701b-4db4-94fe-b56dee716622","year":1985},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.390890Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:aff553fe13ddb68872f1e295ee472cbd179288da041c15ba1df2c92365f9ec18","observation_id":"8cceea58-7356-4eeb-a413-555004313d97","resolution":{"observed_at":"2026-08-14T14:39:12.028671Z","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":"2026-08-14T14:39:11.991801Z","title":"Exponential convergence of langevin distributions and their discrete approximations","venue":null,"work_id":"67617b30-c508-4441-bbd8-45c3a32b187e","year":1996},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.402126Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:b7e1f72042659832c875ec310d088f1c78e8c8047fbb4c191190910dbfcf388c","observation_id":"05f90bec-9973-4d62-b8b9-c4353f060f23","resolution":{"observed_at":"2026-08-14T14:39:11.996858Z","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":"2026-08-14T14:39:11.965057Z","title":"Bayes and big data: The consensus monte carlo algorithm","venue":null,"work_id":"231f5e0e-f539-485e-bd4b-bec06f5a7507","year":2016},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.409268Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:bb46bd8ddaae7ac93cd2c58f35440a2daa3b77b19371197177f9cbd1be72cced","observation_id":"1a5a6e9f-ffc0-4144-9853-6006c360298f","resolution":{"observed_at":"2026-08-14T14:39:11.974188Z","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":"2026-08-14T14:39:11.947466Z","title":"Consistency and fluctua- tions for stochastic gradient langevin dynamics","venue":null,"work_id":"62891cca-6f79-4869-9705-a321192c8051","year":2016},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.416462Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:81fb9031400935dc271094fc4881a979907b1aefc704cdc9fb82de128897f79a","observation_id":"775bbaf8-8184-45d5-85df-32e3f0992b93","resolution":{"observed_at":"2026-08-14T14:39:11.952722Z","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":"2026-08-14T14:39:11.925210Z","title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","venue":null,"work_id":"c3d7ddfb-f3ad-483b-b391-3ee53d8e024d","year":2012},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.426996Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:2345b40076517f48eb0c8f024baaab33bf9b6524fc871a4214debc21b550b8cd","observation_id":"ba302be3-3804-4600-94b4-08b0aff92795","resolution":{"observed_at":"2026-08-14T14:39:11.932836Z","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":"1312.4605","last_updated":"2014-05-25T18:46:47Z","snapshot_observed_at":"2026-08-14T23:51:25.170248Z","submitted_at":"2013-12-17T01:43:39Z","title":"Parallelizing MCMC via Weierstrass Sampler","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.4605","snapshot_observed_at":"2026-08-14T14:39:11.437982Z","title":"Parallelizing mcmc via weierstrass sampler","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.437982Z"},"links":{"cited_paper":"/paper/1312.4605","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:ee7e14131686abd2f5d39c39fcdff02b59f13ea89945ba3ea75ebed637627cfc","observation_id":"c521ec57-6e9e-478a-8543-bba25aa74ff6","resolution":{"observed_at":"2026-08-14T14:39:11.437982Z","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":"2026-08-14T14:39:11.903531Z","title":"Bayesian learning via stochastic gradient Langevin dynamics","venue":null,"work_id":"c7a2a92b-f964-4dcf-a184-e441e101a580","year":2011},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.452454Z"},"links":{"citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:66e8a0956d03e34694633330ec8dd8fb45e6ef39dbedf254734c2db69394f314","observation_id":"56d1231c-6a06-44ea-9b1e-0831384770a9","resolution":{"observed_at":"2026-08-14T14:39:11.910572Z","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":"1802.08770","last_updated":"2018-05-30T01:15:02Z","snapshot_observed_at":"2026-08-14T19:42:41.203175Z","submitted_at":"2018-02-24T00:21:10Z","title":"A Walk with SGD","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.08770","snapshot_observed_at":"2026-08-14T14:39:11.468881Z","title":"A walk with sgd","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.468881Z"},"links":{"cited_paper":"/paper/1802.08770","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:4fddf011f4baf971488ffa0bea06ee7c01db4d0315439d58a4e174531cb6f904","observation_id":"2255279d-81a7-4dc8-b70c-46f503aad0b8","resolution":{"observed_at":"2026-08-14T14:39:11.468881Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04379","last_updated":"2017-10-10T12:27:09Z","snapshot_observed_at":"2026-08-14T21:12:08.890200Z","submitted_at":"2017-03-13T13:27:56Z","title":"Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.04379","snapshot_observed_at":"2026-08-14T14:39:11.477985Z","title":"Langevin dynamics with continuous tempering for training deep neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T14:39:11.477985Z"},"links":{"cited_paper":"/paper/1703.04379","citing_paper":"/paper/1908.02910"},"observation_digest":"sha256:6d8501bcfbc7ae2dcb33ccc05b2cc965ea113025c34a0c6ae6f28b0007c61fa3","observation_id":"f3d05fdc-0f21-4111-ae06-0a331a3607a9","resolution":{"observed_at":"2026-08-14T14:39:11.477985Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.02910","last_updated":"2019-08-28T14:14:42Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-16T07:27:07.922492Z","submitted_at":"2019-08-08T03:06:12Z","title":"Mini-batch Metropolis-Hastings MCMC with Reversible SGLD Proposal"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":2,"verified_fuzzy":20},"total_outbound_references":33},"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 16 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:1908.02910."}