{"as_of":"2026-08-08T12:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2f9342c66afe58efa5eca684ad34aedb6ffe63afc12d539b3e018b99152bfd3d","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:17:07.810767Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2505.15888/citation-record","integrity":"/paper/2505.15888/integrity","json":"/paper/2505.15888/citation-record.json","paper":"/paper/2505.15888"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:04.564376Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:04.564376Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:801992258d40ee97532270d84f7817af3289b892328a9c9e9f056f106eba5a8f","observation_id":"e7955d9f-9405-443b-b4b6-a4868b423017","resolution":{"observed_at":"2026-08-07T15:17:04.564376Z","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":"2026-08-07T15:17:14.172249Z","title":"Fieguth, Xiaochun Cao, Abbas Khosravi, U","venue":null,"work_id":"7ee459e5-3742-4704-b04f-9bef6c4f1b13","year":2021},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:04.615804Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:14bca2a0d67ac54b259170bbe05b07bfde1a692031744c3812473d9ec34b25ac","observation_id":"70f73b4a-5cb3-4860-a04e-bae801780225","resolution":{"observed_at":"2026-08-07T15:17:14.260765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:04.679341Z","title":"Variational inference: A review for statisticians","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:04.679341Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:d5f1be822cf944f42e7791e71c584610a17a5922fe267d1b7f228d64ab11a2ff","observation_id":"3f401219-0b1e-446c-ba6b-14ea3e391c24","resolution":{"observed_at":"2026-08-07T15:17:04.679341Z","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":"2026-08-07T15:17:04.739339Z","title":"Weight uncertainty in neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:04.739339Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:708823532c6e6d0563e8c79606590536e09bc7f4a64d7e60c86c3d1566cdaf63","observation_id":"32d38805-d057-403d-b87b-bbd60aa0d0c0","resolution":{"observed_at":"2026-08-07T15:17:04.739339Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1604.07316","last_updated":"2016-04-25T16:03:56Z","snapshot_observed_at":"2026-07-06T04:53:59.754200Z","submitted_at":"2016-04-25T16:03:56Z","title":"End to End Learning for Self-Driving Cars","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1604.07316","snapshot_observed_at":"2026-08-07T15:17:04.812434Z","title":"End to end learning for self-driving cars","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:04.812434Z"},"links":{"cited_paper":"/paper/1604.07316","citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:7e1e71502420f4e4709d2d5b428984b2a8c8a24935040af5b7d926e57d07f618","observation_id":"803002b6-9d07-4989-8a9e-b4e5f6d19926","resolution":{"observed_at":"2026-08-07T15:17:04.812434Z","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":"2026-08-07T15:17:13.954336Z","title":"Stochastic gradient hamiltonian monte carlo","venue":null,"work_id":"a7ac753c-c26f-44d5-bd09-a23e27a167be","year":2014},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:04.881162Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:099bede9d84cfcd469c24702f6ff0cdf4cd89d460aa50e2451271b285664ee30","observation_id":"997cb583-8ddb-439a-a1a0-e7ebef8fb979","resolution":{"observed_at":"2026-08-07T15:17:14.051254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:13.707168Z","title":"Laplace redux-effortless B ayesian deep learning","venue":null,"work_id":"c85312a3-f47b-41c3-bdd4-9ed44c99b345","year":2021},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:04.944064Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:d596befe650d342126f7d46801ba9def23a3e43041104452f5e2f014836e3b6e","observation_id":"1384e97e-e923-41a7-9f88-ff39a7d7665a","resolution":{"observed_at":"2026-08-07T15:17:13.850677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:13.507910Z","title":"NICE : Non-linear independent components estimation","venue":null,"work_id":"6793d227-c88f-40f0-91f5-c277b62dcaf7","year":2015},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.016203Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:0b1d50e07304d6a22e3e4c621eb151c9ce2765b749aecf0a8b9533e04a23d7aa","observation_id":"256d4429-7a48-40d3-9569-1ab37617e533","resolution":{"observed_at":"2026-08-07T15:17:13.617823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:13.325588Z","title":"Neural spline flows","venue":null,"work_id":"894e0338-a0c5-42ea-8f3f-c1c1f5848f15","year":2019},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.092489Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:956dbca383e7c422c181554869135676b71e50b3c10ee0a438648462129b2ab8","observation_id":"3bdd0d80-1b79-44bc-b006-76b919d30847","resolution":{"observed_at":"2026-08-07T15:17:13.419498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:05.211360Z","title":"nflows : normalizing flows in PyTorch , November 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.211360Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:3a527cda19e57513158f4819cf667478f27f520ffa7c9e29e5e7df14722152f6","observation_id":"bba1c13a-fc95-4a4a-b2b6-f54dba801e22","resolution":{"observed_at":"2026-08-07T15:17:05.211360Z","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":"2026-08-07T15:17:13.184044Z","title":"Dermatologist-level classification of skin cancer with deep neural networks","venue":null,"work_id":"850a7e77-43e9-45dd-a286-3dbc207ff542","year":2017},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.294777Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:5e9867542b7fa74e46241814b60bf121645f255a19f22afd62249a8e87265da8","observation_id":"43c65a46-721e-4309-a06d-b730c9b73448","resolution":{"observed_at":"2026-08-07T15:17:13.250931Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:13.067196Z","title":"Dropout as a B ayesian approximation: Representing model uncertainty in deep learning","venue":null,"work_id":"4264acde-3724-4405-ba09-c282223f8b03","year":2016},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.368609Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:cbb4706956b81c5e3ff3b63afb7a4586862daa6cb064478caf6b6fce4dfb3769","observation_id":"37432edf-9968-475f-9dad-f0befe55f7d6","resolution":{"observed_at":"2026-08-07T15:17:13.125792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:12.869042Z","title":"Practical variational inference for neural networks","venue":null,"work_id":"602d202a-989b-4b62-92e6-61a0a962b99e","year":2011},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.461319Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:d721778f2c0627043fc171240428a4698392dca8e9433a07f3be42961b3e0ab8","observation_id":"eec9eb4e-731a-4a08-b047-bfa4bb8a7f0a","resolution":{"observed_at":"2026-08-07T15:17:12.947541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:12.693453Z","title":"Variational B ayesian last layers","venue":null,"work_id":"f01d9ef6-d15f-4626-8f0b-8e3bc8633f34","year":2024},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.535825Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:4fb7a33e990b6be7964080749e4ea526eb16808fd7a31a700be91caac71b9eda","observation_id":"7da000e6-2963-4fe3-a4b4-0c22e001b559","resolution":{"observed_at":"2026-08-07T15:17:12.775617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:12.505885Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"0e37de62-c097-4ce3-9fce-7db1849fb410","year":2016},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.601700Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:bc42af2861c205724681204afbcd07c1dad677bca73cd5d7b3191d043517637f","observation_id":"d5fc7948-3549-4997-80a0-a9810cf2c302","resolution":{"observed_at":"2026-08-07T15:17:12.596537Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:12.321272Z","title":"Probabilistic backpropagation for scalable learning of B ayesian neural networks","venue":null,"work_id":"ed9862c6-2717-4486-8a2d-22b56de6fbfa","year":2015},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.645773Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:4225c880a2025d417872b39d89d7619135a47937bce080033da13581b06194d8","observation_id":"8f84936e-79b1-438c-a107-011a430d3e6f","resolution":{"observed_at":"2026-08-07T15:17:12.405997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:12.168834Z","title":"Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods","venue":null,"work_id":"04bc11db-2352-49e2-849d-ca3d11232df6","year":2021},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.704819Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:8c98e4b3b3a76bf7561760c7532042998197306e743e73e8da2a453725162050","observation_id":"a6e0b5b4-ff42-47d4-afd9-92d006036628","resolution":{"observed_at":"2026-08-07T15:17:12.228159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:05.804584Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.804584Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:b8cf3aad0b086d810583012fcc7f710e5796fe20db64a9d4f4a0dfb843b3d108","observation_id":"3afa23a9-8412-4ebb-80ee-ee31f1a985d6","resolution":{"observed_at":"2026-08-07T15:17:05.804584Z","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":"2026-08-07T15:17:11.977971Z","title":"Auto-encoding variational Bayes","venue":null,"work_id":"d486ef1a-65dd-4166-937d-f12de371ee00","year":2014},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.873049Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:086ce99eeca0f2343a82d02759bb448b3fc145c73802d80de4963d8bbe491c68","observation_id":"dac3688f-6020-4920-b061-632256d9d89c","resolution":{"observed_at":"2026-08-07T15:17:12.079600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:11.751837Z","title":"Improved variational inference with inverse autoregressive flow","venue":null,"work_id":"9eda98e7-3905-40b3-9c35-0b507e854932","year":2016},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:05.945782Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:704e772937861ae5d9e0cf8cab1ab70400d305a706cc3a87baf4158f7e79d09a","observation_id":"5f6f0876-b8a5-481d-b1f1-221e0e58c6d5","resolution":{"observed_at":"2026-08-07T15:17:11.838282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:11.611675Z","title":"Being B ayesian, even just a bit, fixes overconfidence in relu networks","venue":null,"work_id":"2de3b99a-0267-43e0-bdf8-9ed38f5e295a","year":2020},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.015573Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:152a96b90366a4a8d63cf1c8ce27c5900b7d1c8901401d629fecbbb74091c862","observation_id":"26d3d5f0-9b6c-44d0-8dda-b7e0e8e88aaa","resolution":{"observed_at":"2026-08-07T15:17:11.675420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:06.089961Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.089961Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:4cb9111dfb7c326905ed377b51b4531b824faee4eb00d5ff6bc0441b6e97fca4","observation_id":"b234dd18-9796-4b81-b90c-b74bb425fc9c","resolution":{"observed_at":"2026-08-07T15:17:06.089961Z","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":"2026-08-07T15:17:06.147708Z","title":"Simple and scalable predictive uncertainty estimation using deep ensembles","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.147708Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:7e1e713cea4f59e2b492a5878f5060446e5d51f2c4d05da29ec69cd83eb5943b","observation_id":"c9cd3f2c-ed0f-4fff-adc5-5bc0d40bdcab","resolution":{"observed_at":"2026-08-07T15:17:06.147708Z","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":"2026-08-07T15:17:11.387760Z","title":"Marginalized neural network mixtures for large-scale regression","venue":null,"work_id":"76ad2d6f-0da2-4327-9892-5594d094f434","year":2010},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.212933Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:d26de9ef95391fb5a06a8d2ae7940bf186d2c4ab2777a19785091bbcc0f81eb5","observation_id":"ccb65e3f-175f-4925-9cbc-13dadb6abe90","resolution":{"observed_at":"2026-08-07T15:17:11.476226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:06.322943Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.322943Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:bc9d4a8557e42542e615b04754aa94e28ac7eb483b52e2067ee6f82bba075715","observation_id":"72db6b3e-1861-49ba-90b8-a073e1b8d145","resolution":{"observed_at":"2026-08-07T15:17:06.322943Z","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":"2026-08-07T15:17:11.175584Z","title":"A survey on deep learning in medical image analysis","venue":null,"work_id":"64ac984c-36ae-4715-b723-9074c938f9bc","year":2017},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.369571Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:4328654401515d7c253392fcfaa14ad620d2a5601e727582fe087cc18be06f5b","observation_id":"e59aea5e-a56c-476d-852c-8053b95053c0","resolution":{"observed_at":"2026-08-07T15:17:11.279957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:11.001043Z","title":"Maximum entropy flow networks","venue":null,"work_id":"15664b10-e893-4524-8fc0-a30f8b2dd63b","year":2017},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.425298Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:c90d246259e112d2dd415346a8eb775425900529d668818d70f6e1605980bbd2","observation_id":"4fe32d1c-b428-4ee4-bc00-4ed3850af2d4","resolution":{"observed_at":"2026-08-07T15:17:11.084060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17917","last_updated":"2025-01-29T19:00:01Z","snapshot_observed_at":"2026-07-06T20:28:04.863224Z","submitted_at":"2025-01-29T19:00:01Z","title":"Deep Ensembles Secretly Perform Empirical Bayes","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.17917","snapshot_observed_at":"2026-08-07T15:17:06.472635Z","title":"Deep ensembles secretly perform empirical bayes","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.472635Z"},"links":{"cited_paper":"/paper/2501.17917","citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:8d4041ed73df8440f61d06a5f17d6e54dd26739ce8261110289ade3ddbcf963a","observation_id":"cc21cd62-6150-4528-aed1-30ecd4035aa4","resolution":{"observed_at":"2026-08-07T15:17:06.472635Z","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":"2026-08-07T15:17:10.758509Z","title":"Structured and efficient variational deep learning with matrix G aussian posteriors","venue":null,"work_id":"98c2e603-74ee-4bdd-be35-a7782517e08d","year":2016},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.546624Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:7317761be5a496b1ddd3590724bb02852b77ae89067298f1e6b45a23035b05b0","observation_id":"fc25b1a6-13bb-4b0c-bf62-38bd001b841e","resolution":{"observed_at":"2026-08-07T15:17:10.878892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:10.574610Z","title":"Multiplicative normalizing flows for variational B ayesian neural networks","venue":null,"work_id":"1c2fcdd3-678f-4dc1-b850-be7e3455a2f5","year":2017},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.595765Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:861c142b198d60cfce8adbc9a6b943760cff860d06376d229cceb9f0d7141884","observation_id":"59666254-9e32-4155-94ab-a6ca3778ab8b","resolution":{"observed_at":"2026-08-07T15:17:10.669373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:10.377961Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"3ae2b096-8a9e-457f-ac8e-59a0af864e34","year":2011},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.668313Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:683de24cbbde96d7b62d76aaa2e6596da8ba2cfa04e00a9797ff2f1f10369346","observation_id":"14b8243f-e447-418b-bdb0-eea9e773e225","resolution":{"observed_at":"2026-08-07T15:17:10.490792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:10.161426Z","title":"Practical deep learning with B ayesian principles","venue":null,"work_id":"4214d95b-9d21-4ffd-bcd0-5d8daf2d52f5","year":2019},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.726985Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:db6375635c24533e78f712c743c76173c4ebadccf0b2775ed764deff6bae5a94","observation_id":"4b8b8f06-999f-4cc8-9352-455673ab3e76","resolution":{"observed_at":"2026-08-07T15:17:10.278611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:09.960607Z","title":"Uncertainty quantification in scientific machine learning: Methods, metrics, and comparisons","venue":null,"work_id":"0403a27d-841d-4621-88d7-643aebcd29b2","year":2023},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.805374Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:ca8dbda7ebf9f1827971ad135cdcb7ec585a210f14e459f3c2bf94e83dcd7961","observation_id":"bd492b8a-4ec9-4525-9c7e-d1f879f28d95","resolution":{"observed_at":"2026-08-07T15:17:10.033479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:09.762759Z","title":"Variational inference with normalizing flows","venue":null,"work_id":"8407dc2a-4292-410e-b0fe-2ee5fc08d52f","year":2015},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.885760Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:e8180205b671d2afb3a2651f60cd88a692892d9b610f95da4e2b5d21c120488a","observation_id":"f5a007ba-75fe-4bb1-b832-6ab05ce8dfca","resolution":{"observed_at":"2026-08-07T15:17:09.851311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:09.561953Z","title":"Stochastic backpropagation and approximate inference in deep generative models","venue":null,"work_id":"24e23ddd-385c-4110-b0a1-a0ce4632591b","year":2014},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:06.967760Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:f99be3b764af10911ab88ad38818cd788fae4b6e05e3e6bac95695bbc6b25d49","observation_id":"73c27554-0b0e-4ae6-a9f9-1d1ba34befac","resolution":{"observed_at":"2026-08-07T15:17:09.638597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:09.376939Z","title":"A scalable L aplace approximation for neural networks","venue":null,"work_id":"8a8dd150-efd0-4753-b17c-2697976c38e8","year":2018},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.053951Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:877fa733980d994f6fe02391c6f64229d954c40cd77a0a6e8e1e85944feadd9c","observation_id":"cd275eef-04fd-411d-b8d7-d2b2087c08bf","resolution":{"observed_at":"2026-08-07T15:17:09.483495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:09.146353Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":"6608494a-b36f-4466-9206-c6ee9779bdb6","year":1929},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.121285Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:70c556b46af38dc4f33cb97d082147d32866f633363f7300bd3e0a89495e8e78","observation_id":"70631966-0f66-43cb-acd5-af5c0bc18213","resolution":{"observed_at":"2026-08-07T15:17:09.244312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:08.930972Z","title":"Graphical models, exponential families, and variational inference","venue":null,"work_id":"6989be3d-f08a-4a75-b452-7b5c483f7faa","year":2008},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.210332Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:1a014af50cd58bee7cfbe60d3bfd7e038019e4f7a71d84b29263364c34024005","observation_id":"998c3aa3-b3f9-472d-84b5-8e5d5b6cb9b4","resolution":{"observed_at":"2026-08-07T15:17:09.027376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:08.767106Z","title":"Neural linear models with functional G aussian process priors","venue":null,"work_id":"5b75a8e7-ddbe-4230-842d-70b376f1fcbf","year":2020},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.281767Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:2d34849afb0d92f6fe1f756e397770fafa1fc4b38385ac6bd3fede17b3e112b6","observation_id":"a2501143-a3dd-4018-aaf3-91f80e10c8ac","resolution":{"observed_at":"2026-08-07T15:17:08.859627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:08.575610Z","title":"Latent derivative B ayesian last layer networks","venue":null,"work_id":"e7e6470c-f534-4ca7-9dfd-4bcb652edbe8","year":2021},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.352395Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:88f5440211558288b862639d2ad0df69a78e385fc6827098155b7943799baa76","observation_id":"600e0d78-0273-45b8-a295-1cc360ef554d","resolution":{"observed_at":"2026-08-07T15:17:08.645390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:08.414914Z","title":"Bayesian learning via stochastic gradient langevin dynamics","venue":null,"work_id":"ee27d0bb-072c-4de2-a007-3969cc590eee","year":2011},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.404322Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:c9eeb8525097fe5c3e15f26f6ab92672509b254139675497344a3d62e62ad237","observation_id":"5b2aae53-0ebd-4f53-8e40-f836c4896704","resolution":{"observed_at":"2026-08-07T15:17:08.489309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:08.220271Z","title":"Deterministic variational inference for robust B ayesian neural networks","venue":null,"work_id":"47e33dad-ad20-477f-99ff-a8d0e1a7a0d4","year":2019},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.478968Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:44e8f490251b99a6eb178cd2445bfa9a77b540cf236bbce63395c77074f2a472","observation_id":"5c377134-061c-400b-a2ee-d1c0e12c2f06","resolution":{"observed_at":"2026-08-07T15:17:08.315636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-07T15:17:07.555555Z","title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.555555Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:5bf952446dc45ff1af70145919c1bd4ae29e87eec4aa2d30cacc9bb829fdd044","observation_id":"b55c7b18-1451-4c51-a114-0b7d0e88254e","resolution":{"observed_at":"2026-08-07T15:17:07.555555Z","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":"2026-08-07T15:17:07.598337Z","title":"Bayesian low-rank adaptation for large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.598337Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:8edc376393fb77a4fafc236405fec05c1fdf9ab5c759d523b8477d3733b4fd68","observation_id":"f75b52da-d465-4225-9392-1b2fcbb1bdac","resolution":{"observed_at":"2026-08-07T15:17:07.598337Z","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":"2026-08-07T15:17:08.023032Z","title":"Cyclical stochastic gradient MCMC for B ayesian deep learning","venue":null,"work_id":"07cfb825-c35f-4ef1-9833-082e998105c8","year":2020},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.658447Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:b86bbed088e00aabbfa87704dff8bca84555c3d560a8029d1811fe89ca7d747d","observation_id":"6b140559-58dc-4ec1-a392-d8aa17d250af","resolution":{"observed_at":"2026-08-07T15:17:08.101580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:17:07.698758Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.698758Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:71172f94ff52de2977dfab6809d232e5df4464a584c93092966190eafa1cec6b","observation_id":"d7d39dfd-8a7b-4758-a051-d19bfafc41c9","resolution":{"observed_at":"2026-08-07T15:17:07.698758Z","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":"2026-08-07T15:17:07.771788Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.771788Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:0eafa42a86ef9814aa6b5799b75e51a472bdbb7de41a9c8e7d0fb2ca2a3562e3","observation_id":"1a040322-b591-4b4a-be94-57d455e82099","resolution":{"observed_at":"2026-08-07T15:17:07.771788Z","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":"2026-08-07T15:17:07.810767Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T15:17:07.810767Z"},"links":{"citing_paper":"/paper/2505.15888"},"observation_digest":"sha256:abcd6cd2beae3c575ef48a313d8704475d6f608b8e27f0468aff1691816db5b7","observation_id":"967b5c76-f386-42fc-bcea-c641e87fa012","resolution":{"observed_at":"2026-08-07T15:17:07.810767Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.15888","last_updated":"2025-05-21T18:00:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T15:08:49.417174Z","submitted_at":"2025-05-21T18:00:00Z","title":"Last Layer Empirical Bayes"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":0,"verified_fuzzy":33},"total_outbound_references":48},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2505.15888."}