{"as_of":"2026-08-13T07:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4cc20cc118d192153b54c0b3ae1b708f20ebb8549fd916453eaac7b6d0fcbf88","coverage":[{"denominator":72,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":72,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T11:16:07.861480Z","state":"measured"},{"denominator":73,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":73,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T08:45:34.884703Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"cited_work":{"arxiv_id":"2411.18425","doi":"10.48550/arxiv.2411.18425","metadata_source":"arxiv_reference","pith_arxiv_id":"2411.18425","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Streamlining","venue":"arXiv (Cornell University)","work_id":"06ecd918-34bc-47ad-b05d-ced1002644de","year":null},"citing_paper":{"arxiv_id":"2606.23591","last_updated":"2026-06-22T17:00:04Z","snapshot_observed_at":"2026-08-02T00:14:44.848420Z","submitted_at":"2026-06-22T17:00:04Z","title":"Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-06-26T08:45:34.884703Z"},"links":{"cited_paper":"/paper/2411.18425","citing_paper":"/paper/2606.23591"},"observation_digest":"sha256:f2f14827084c826bcd7bfe5281896cdbd5c7aa189d45281c65227177e8c3ded9","observation_id":"4912675a-5d68-4d04-9f65-955547103d60","resolution":{"observed_at":"2026-06-26T08:49:14.839196Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.18425/citation-record","integrity":"/paper/2411.18425/integrity","json":"/paper/2411.18425/citation-record.json","paper":"/paper/2411.18425"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T11:16:07.578678Z","title":"Post-hoc probabilistic vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.578678Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:8b5e68f45e0b3dba6e393a745c8c76d56175e5e8138bfa0e04f06ba8db17fc75","observation_id":"12233be5-34b2-4d13-aaa2-8fc991c50ca9","resolution":{"observed_at":"2026-08-12T11:16:07.578678Z","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":"2026-08-12T11:16:07.582999Z","title":"The need for uncertainty quantification in machine-assisted medical decision making","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.582999Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:a58af8d349c4b188beab854b9c402dca805a6ca4df6e920830a9e3b9b48171be","observation_id":"1990a506-776d-4714-ab86-74b9f93f1412","resolution":{"observed_at":"2026-08-12T11:16:07.582999Z","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":"2026-08-12T11:16:07.586526Z","title":"Variational inference: A review for statisticians","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.586526Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:c3cbadc70ee9a8a64905e6de5ce155bcc6e8cc8f0148b3d6ee997f3c915c25df","observation_id":"bdad991c-13e4-4637-99de-7580d2339da7","resolution":{"observed_at":"2026-08-12T11:16:07.586526Z","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":"2026-08-12T11:16:08.726381Z","title":"Weight uncertainty in neural network","venue":null,"work_id":"2cd86512-66d7-4969-8e4c-dd6851a2dd0d","year":2015},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.590239Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:4bcd9bd7e9fe3476af395fd5b1a6c7da4af48fbb887fb8e7a5f496705304b824","observation_id":"15bc754f-d2a0-4a9c-9c9c-e9dae8115326","resolution":{"observed_at":"2026-08-12T11:16:08.729985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.714757Z","title":"Sample average approximation for black-box variational inference","venue":null,"work_id":"071ea0b5-a381-4dcc-887d-b5def7372533","year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.594446Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:2e3fca1a0b761ee48bf752cc7a3bfaa79de1a74824230d7ad24b1d0172772a3f","observation_id":"b35fbc8a-1eb6-4133-bdff-d2b2de4f6c2b","resolution":{"observed_at":"2026-08-12T11:16:08.718737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:07.599129Z","title":"Remote sensing image scene classification: Benchmark and state of the art","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.599129Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:4572d9ee0f86bef2208149baba168a285b94362040c6b0460f4626bf97ea571a","observation_id":"e779d96e-8ed3-47c7-bb71-d9a2dffd16ce","resolution":{"observed_at":"2026-08-12T11:16:07.599129Z","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":"2026-08-12T11:16:08.694644Z","title":"Describing textures in the wild","venue":null,"work_id":"d083f63c-a92c-46b5-b335-668d84772d49","year":2014},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.603895Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:bf839af8f54ba7cd702fd91a51a6aa7b3e2fdbf517cd9b38643f9572ee6c9c4b","observation_id":"7855537c-ec5b-4a10-8c62-122ff54230be","resolution":{"observed_at":"2026-08-12T11:16:08.698462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.680984Z","title":"Wide mean-field bayesian neural networks ignore the data","venue":null,"work_id":"c15811bc-4c72-442c-ab73-6e94ffca93e0","year":2022},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.607854Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:9cef7ab7316807954efa691d416dcdebb37302655a83f29957ef298bdc385ae8","observation_id":"fce4c868-49df-490b-a5a4-6f08f83123b3","resolution":{"observed_at":"2026-08-12T11:16:08.685549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.668463Z","title":"Kronecker-factored approximate curvature (kfac) from scratch","venue":null,"work_id":"5f68b25e-a7e3-4150-8276-a9c2805d1992","year":2025},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.611450Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:1fcf64bbb42b9d81e448c08cbd3312440d82e92c2c298d2c20aeb4d7167f0ee2","observation_id":"37e837a5-9257-4791-af59-3516be01b2e5","resolution":{"observed_at":"2026-08-12T11:16:08.672774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.656060Z","title":"Laplace redux -- effortless B ayesian deep learning","venue":null,"work_id":"d7dce4bb-5354-4481-8a0f-0b5813c77582","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.618767Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:cfb175a08cde38adf1413bc09e6aafed4d354ac6b588e5cefe465d3554af85bf","observation_id":"9f18fb92-7e2a-46f6-a5e3-459f4fdb81f9","resolution":{"observed_at":"2026-08-12T11:16:08.659744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.643605Z","title":"B ayesian deep learning via subnetwork inference","venue":null,"work_id":"7d6d33a5-bd7a-44b7-9ebb-503ffed61c1d","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.622683Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:0734636cc86183e3eca69da40ae8ad58cc5b3bf6542be35c00c775ee20afec72","observation_id":"9e73eccd-33ed-4810-9071-2625770c6b09","resolution":{"observed_at":"2026-08-12T11:16:08.648068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.632020Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":"09ccb175-fca5-45fa-8017-220c68aa5084","year":2009},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.626258Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:1e2ba7a315feddf07237d1cf6e52d95db73dfc81e21e66be208d987f82e2e100","observation_id":"e9f2fdef-e023-49f5-b108-c1c4deec0df9","resolution":{"observed_at":"2026-08-12T11:16:08.636211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.620998Z","title":"Efficient parametric approximations of neural network function space distance","venue":null,"work_id":"3ce24a62-f002-4d70-8c83-a87255053385","year":2023},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.630651Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:db25cf26067ebf77af949cf71a126bba683d9050dbd4396cb9e6b375669432c0","observation_id":"306ed092-7c6c-48ad-a58b-4b8700f2b94e","resolution":{"observed_at":"2026-08-12T11:16:08.624989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:07.633889Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.633889Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:83c84975dd20ec87b786a8c889d1d3b0920c05c90315fa3653e733467a5cc3a7","observation_id":"52dde7b4-b559-4273-8c85-dba703d17f2e","resolution":{"observed_at":"2026-08-12T11:16:07.633889Z","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":"2026-08-12T11:16:08.600216Z","title":"Mixtures of L apkace approximations for improved post-hoc uncertainty in deep learning","venue":null,"work_id":"136df28a-201f-427c-bf24-877b71283239","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.638101Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:4b1fdea2b3504cc21e1fbe4a8a910d79235b54c49e446cfed99205f705ccd992","observation_id":"78e31b69-44ad-45cb-906a-6843b3b4594c","resolution":{"observed_at":"2026-08-12T11:16:08.604638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.588048Z","title":"On the expressiveness of approximate inference in B ayesian neural networks","venue":null,"work_id":"3029f016-4999-4532-b9a6-dcc07ac8c394","year":2020},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.642642Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:8201a9ec3a09e69e331bceb487c3ca2bfa31ed324019accd2d5e91b4446b741f","observation_id":"d9bfb01e-f154-4314-b27f-074c53d1b8e7","resolution":{"observed_at":"2026-08-12T11:16:08.592365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.576366Z","title":"B ayesian neural network priors revisited","venue":null,"work_id":"50cb174d-c40c-4b44-ad6e-3452a88f2e26","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.646131Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:ce677a722b3d307991c52b57ca771e9112d709e1327fb052018e68b71d2b3d94","observation_id":"37785a43-ea46-43b0-a666-3fb8e50aa4da","resolution":{"observed_at":"2026-08-12T11:16:08.580270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.563494Z","title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","venue":null,"work_id":"f3387cd5-6695-4a30-8b06-927e7b50ba62","year":2016},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.650089Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:b01b6a2b862ff0c1c630350416369811431e9c6b4d900848a0247121ad9cc280","observation_id":"f759a4c2-9a0a-4f65-8e96-6a79f39c5ac5","resolution":{"observed_at":"2026-08-12T11:16:08.567513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.552325Z","title":"Deep bayesian active learning with image data","venue":null,"work_id":"b2479266-c7a0-43e1-b7e5-877c71aeabd6","year":2017},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.653584Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:e0cd1dab565a184985ba418307343e92087024d5b99ce9bec40db939b1f2dd6b","observation_id":"3c7250cd-147a-4a87-af29-41b59ab80ebd","resolution":{"observed_at":"2026-08-12T11:16:08.556298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.541660Z","title":null,"venue":null,"work_id":"f2c2f53c-d6d1-4c98-b842-90a9368f4ddf","year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.657386Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:c2033f80375e46dc94965a7a5807149784e5f88b8ba72404245f67d6f83a4b73","observation_id":"771a216b-981d-4d02-b254-dfb039b2594f","resolution":{"observed_at":"2026-08-12T11:16:08.544971Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.529403Z","title":"Black box variational inference with a deterministic objective: Faster, more accurate, and even more black box","venue":null,"work_id":"66a88652-1ab4-45e2-bc55-c42400500c15","year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.661339Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:5d8437940682b4c27959e866545f4342807a9f5ab08d51f5b9d1ce2a86c7cd27","observation_id":"eb78e3d0-e17d-4cb2-9097-e3c46aa6af6f","resolution":{"observed_at":"2026-08-12T11:16:08.534259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.513974Z","title":"Tractable approximate G aussian inference for B ayesian neural networks","venue":null,"work_id":"83d62e44-5f76-4a93-afda-14abc9a2bfee","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.664818Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:6de4c10475c8ca1dc1c90aec17848d957ae42a82da49a9913079206b3d769ba2","observation_id":"d07181b6-4680-4bb4-8ae4-9e25778edfc2","resolution":{"observed_at":"2026-08-12T11:16:08.519112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.501089Z","title":"Training independent subnetworks for robust prediction","venue":null,"work_id":"ce956768-eb68-45eb-8042-4326c1a333b2","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.669588Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:12d11af5b738bb183626a12e02731f5958a9334a8a70e2e69c0fa24839c534c0","observation_id":"353a7634-9d6b-40ea-94a8-bfd479b24093","resolution":{"observed_at":"2026-08-12T11:16:08.505198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.488132Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"1661aa3b-3027-444c-a1e2-042751496e1f","year":2016},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.673329Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:f466b55c886904f02194e15c1bed3eb8de344200efde68de1570f00792694d8c","observation_id":"a5b01e40-2c33-4626-8dd6-921c19a22b16","resolution":{"observed_at":"2026-08-12T11:16:08.492481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.475098Z","title":"The many faces of robustness: A critical analysis of out-of-distribution generalization","venue":null,"work_id":"78034ad2-2a5d-4505-84cd-15f0ffec3e06","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.677480Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:329566a0689ae35a795711cc255f1accd83e682ccb86c4eb438773aafc08ca28","observation_id":"452f3cac-db79-4e0e-818c-db57c754c481","resolution":{"observed_at":"2026-08-12T11:16:08.480698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.463611Z","title":"Scalable marginal likelihood estimation for model selection in deep learning","venue":null,"work_id":"a24e71f9-6d06-4e82-afae-9722608519ec","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.681435Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:5aa047fe5e3ebaa85b80b6a8ba47d484927fb5f3d946742ec4c6ca51aa167e40","observation_id":"60777dae-9b2d-4c30-b65f-1547367dbd8c","resolution":{"observed_at":"2026-08-12T11:16:08.467329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.451120Z","title":"Improving predictions of B ayesian neural nets via local linearization","venue":null,"work_id":"3116cd6f-b4b9-4ce1-b97c-117c010062bf","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.685956Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:8bc55b89845505452d2513a601c4ad9ee775147388ef91ec89e638f22b1f358d","observation_id":"09c70b19-1669-4566-911d-121e5d559957","resolution":{"observed_at":"2026-08-12T11:16:08.455776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.439453Z","title":"Towards scalable B ayesian transformers: Investigating stochastic subset selection for nlp","venue":null,"work_id":"16cf5822-e92d-4e9c-bb67-427de0c2920c","year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.689895Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:7657add25c89e765275769c4947dde139cf11847414da92dd56a0d474df28d89","observation_id":"65d2e54f-5a05-4fd8-9e0f-9bc971116490","resolution":{"observed_at":"2026-08-12T11:16:08.443768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.426750Z","title":"From moments of sum to moments of product","venue":null,"work_id":"3e019970-6a2c-4aff-a916-7493d82a790a","year":2008},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.693726Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:0a09659107495478947898b1bf0bf0f294fef5a9c31f176549b1f1cb25b32362","observation_id":"353e1950-3981-4a30-a692-0d1399a56a5b","resolution":{"observed_at":"2026-08-12T11:16:08.431274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.414189Z","title":"The UCI machine learning repository, 2023","venue":null,"work_id":"ddfb0480-6de1-459f-bc09-347654ea1349","year":2023},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.698619Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:652fb23a655b91c988eb0ff80cd867aa0fd79d3107237ac1e561100d52f87707","observation_id":"1b0549f0-b291-46cb-9d0b-cf3fb5d6d359","resolution":{"observed_at":"2026-08-12T11:16:08.417987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.401207Z","title":"Being bayesian, even just a bit, fixes overconfidence in relu networks","venue":null,"work_id":"6e8ed83e-13d4-40a5-8445-107d08050148","year":2020},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.701841Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:1c876af3b02af89b542c8350c388aaff3738234ae85c7f2ab8e0c5f479a38ebc","observation_id":"e6330644-3785-463f-8ec1-0e429db9dd93","resolution":{"observed_at":"2026-08-12T11:16:08.405394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.389214Z","title":"Promises and pitfalls of the linearized L apkace in B ayesian optimization","venue":null,"work_id":"fb56fab2-eca0-48dd-a5c5-e79eca78ee91","year":2023},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.705783Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:9269fedb5d2ee56c62dd69eb51fdcce209fd50e48463e27038b903ccd3cd99b6","observation_id":"b1bddcfc-81ce-4787-9b5a-4228fa332239","resolution":{"observed_at":"2026-08-12T11:16:08.393551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.376565Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"06a058cb-3fe8-47b7-a06c-a8cad3e123d2","year":2009},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.709203Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:810b2ca7af4d14c41edba225436d9fc7cab6743d23a6e3e90a57194548e50b23","observation_id":"30c3a585-e993-46b1-a4b0-d91fcc86001e","resolution":{"observed_at":"2026-08-12T11:16:08.380716Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.364015Z","title":"Simple and scalable predictive uncertainty estimation using deep ensembles","venue":null,"work_id":"07d0a402-4161-41e8-b764-7dee8909e981","year":2017},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.713447Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:2b476537ba9766d579d6e6ae08ec8d7f00dc5de2b89102c5e94bdb7332fa7bbf","observation_id":"0e5c3aaf-0d88-485a-b9e3-f86823f78bbe","resolution":{"observed_at":"2026-08-12T11:16:08.368583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:07.718056Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.718056Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:853cdedf3cdc314c9e610660b2c26580292350f6b97af3d759ef3e238b8d37a5","observation_id":"a940ee36-75de-44f0-800e-081aed410849","resolution":{"observed_at":"2026-08-12T11:16:07.718056Z","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":"2026-08-12T11:16:08.344076Z","title":"Soft: Softmax-free transformer with linear complexity","venue":null,"work_id":"6a9d5ab8-cb52-469c-8b51-d1895835b346","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.721386Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:9e064b80a8e0a43da593760b14b87662a64efa52af493f2d5364067a9b8dfe90","observation_id":"22631dff-e657-4ee4-837f-44f8f029c4f6","resolution":{"observed_at":"2026-08-12T11:16:08.348130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.332865Z","title":"Information-based objective functions for active data selection","venue":null,"work_id":"23c0e2c8-fb31-4219-a475-5d4205449a96","year":1992},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.725661Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:384b22b9d64a57f0fc0a19de5c2b14883cc75fe5a3443142641962cdde1fc95d","observation_id":"ce5bff86-e0ce-40b9-821c-be5251bef8b9","resolution":{"observed_at":"2026-08-12T11:16:08.336788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.321752Z","title":"B ayesian interpolation","venue":null,"work_id":"39d2fc5e-733d-485e-9bd2-6aba75763ab2","year":1992},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.729303Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:f7e0c5a2623f67a91dc9e947d339f17532bda5fb83887374e777a69ad7a6528d","observation_id":"9530454c-df7b-4e34-ba43-8d07f9026d0f","resolution":{"observed_at":"2026-08-12T11:16:08.325282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.310011Z","title":"B ayesian methods for backpropagation networks","venue":null,"work_id":"d5c49759-276f-4e39-bf41-3f9c50b9c59b","year":1996},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.732674Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:442eef1461a2d7c705fb6da4172ae49418005d15e78bc7fcca756a2851ebc4b9","observation_id":"56311995-4e6c-45ac-bf8d-f9210d4240a7","resolution":{"observed_at":"2026-08-12T11:16:08.314644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.299748Z","title":"Maddox, Pavel Izmailov, Timur Garipov, Dmitry P","venue":null,"work_id":"55e7eff9-88fb-4fe7-92bd-f8ba72e182fd","year":2019},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.737239Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:0fe3e09a78c63dfa9b1ec4ed06858dfb856683c2e962fada8e447194a8b6df59","observation_id":"32012479-5039-485c-b984-a3b33a7374dd","resolution":{"observed_at":"2026-08-12T11:16:08.303222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.288932Z","title":"Optimizing neural networks with K ronecker-factored approximate curvature","venue":null,"work_id":"64fabfb8-d496-47fc-8371-a9905199587e","year":2015},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.741865Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:27a03a5b6b99e03efd5260abddc7a1185274dcaab0b42bd328343cab6890b87f","observation_id":"2d19a20a-e37e-4b30-9278-98f0c61718a3","resolution":{"observed_at":"2026-08-12T11:16:08.292863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.277412Z","title":"Periodic activation functions induce stationarity","venue":null,"work_id":"85f4b628-ad5f-4e38-ab87-deb55da513af","year":2021},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.746293Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:2ac8111dbb9cab0af8e99e59ee4b7051bee19249481605295b2a38c7aef4b3a3","observation_id":"d5fb0ae5-1429-485d-bac2-d540cf4bb267","resolution":{"observed_at":"2026-08-12T11:16:08.281016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.266549Z","title":"Fixing overconfidence in dynamic neural networks","venue":null,"work_id":"d383466b-a614-479e-ae63-4361bcbd6e0b","year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.749800Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:e42c77751bdc67f46f991d116e2de060e1cfcaae3b077477fbf95c391ff84a43","observation_id":"07cf5c76-341e-44fc-a8e8-efdd9389f22a","resolution":{"observed_at":"2026-08-12T11:16:08.270490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.254687Z","title":"Uncertainty quantification with statistical guarantees in end-to-end autonomous driving control","venue":null,"work_id":"8c2758a1-42c4-4167-a000-da854706842c","year":2020},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.753254Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:b97ba574a43a92d31b9e804edd711a6e7b80cb5f9208cbc6a92b72c270f5b210","observation_id":"06f7f882-32ba-4626-a20c-30e1816da56b","resolution":{"observed_at":"2026-08-12T11:16:08.258780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.241461Z","title":"On the distribution of the product of correlated normal random variables","venue":null,"work_id":"348d7e24-d0da-4c0c-87c9-5197b562c806","year":2016},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.756756Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:3836989573a2b45485b6a1050c2deb24c9a9c3509d01572e112e8df5eb40d09a","observation_id":"ee3eebca-f957-439b-960f-e1d559a99d35","resolution":{"observed_at":"2026-08-12T11:16:08.245552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.229718Z","title":"On priors for B ayesian neural networks","venue":null,"work_id":"d1f9cd2c-1c38-49a6-8c12-e57278c5cd90","year":2018},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.760844Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:faefe33958fe3a1115c688386b1d7fa47e8317adb225caf506c8188a97d5bda0","observation_id":"639d4725-cf7d-4e53-9dfe-5b1d1de1d4b7","resolution":{"observed_at":"2026-08-12T11:16:08.233619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.218082Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"07095ce6-21d0-4efe-ba62-779d40d659f5","year":2011},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.764121Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:fa60befc9a9558da9137b657bccfd9a426827808c5eb38d991f40d3847b18baa","observation_id":"67c1685b-e045-4a79-ad5b-f63273cabd2c","resolution":{"observed_at":"2026-08-12T11:16:08.222460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.206706Z","title":null,"venue":null,"work_id":"eac63470-0581-42d2-92e3-351c052aa4e3","year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.768692Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:275aa543d85f407fdb898a5cd7c9f4e9e52d6d0524053369d9f37c08b0b4a5cb","observation_id":"c9bd1d38-2ec5-4e1b-a9af-adc21134c300","resolution":{"observed_at":"2026-08-12T11:16:08.210620Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.194556Z","title":"Uncertainty quantification via stable distribution propagation","venue":null,"work_id":"2d416191-96be-4974-8ae2-c311965b3626","year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.773413Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:972c5885e40c55ab26004251b79ef59a5c8a9183af539ac482a76d582df9208b","observation_id":"bbf75867-c169-4c61-a22e-e662573a557d","resolution":{"observed_at":"2026-08-12T11:16:08.199533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:07.777339Z","title":"Uncertainty quantification in scientific machine learning: Methods, metrics, and comparisons","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.777339Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:6ebf178857647e6569728b86fec6540da97fcbe9f9194c115c14e1929d00c879","observation_id":"441b4920-2bd5-496f-8d43-61a6af6f7455","resolution":{"observed_at":"2026-08-12T11:16:07.777339Z","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":"2026-08-12T11:16:08.176998Z","title":"Language models are unsupervised multitask learners","venue":null,"work_id":"d81dbfff-2c78-4aad-8a18-0bcce1e32149","year":2019},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.780607Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:c2f1103d683df1293a1394262af534b09bfe9a3ac84e66dcbf8483ab133bc7ab","observation_id":"3e69d980-58a3-4def-9f83-9b91d771cc07","resolution":{"observed_at":"2026-08-12T11:16:08.180987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.165158Z","title":"A scalable L aplace approximation for neural networks","venue":null,"work_id":"46309002-6be8-4df0-b7ad-11186b06d452","year":2018},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.785051Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:5d496c0cb1b751cc0998164d98e8f9aa2c8ff77377cce79ed7607b07a3039418","observation_id":"fea3f811-0b46-4618-b263-bf03e355c9ad","resolution":{"observed_at":"2026-08-12T11:16:08.168598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.154446Z","title":"B ayesian Filtering and Smoothing","venue":null,"work_id":"d0b1ce6b-9c94-4a1c-a3c4-f93ddf9e44d8","year":2023},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.788580Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:b4593ff6c3c0b4d3c8612f4613c9244f6512bc61b550c9725debd8010d50361d","observation_id":"a716494f-9263-434c-a4f6-e9529fb7abf5","resolution":{"observed_at":"2026-08-12T11:16:08.157996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.142712Z","title":"Function-space parameterization of neural networks for sequential learning","venue":null,"work_id":"df47d6a8-b621-4399-a0d7-7ff17aaaa1f1","year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.791720Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:642877821e13b3a95006b8953076740a08f92e97ac596f664f99ba9660e43e73","observation_id":"0e2453f0-4852-436b-8981-26c57144f62e","resolution":{"observed_at":"2026-08-12T11:16:08.146261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.132538Z","title":"Variational learning is effective for large deep networks","venue":null,"work_id":"340278e3-ff6d-4523-8665-a6f93af4e515","year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.795186Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:23e201400b396cb5dc0f9d3c6c533e1e53d01e986c58018f30cdebfe5cc21513","observation_id":"3aedffae-5d73-495c-a870-ab26f92295a2","resolution":{"observed_at":"2026-08-12T11:16:08.136208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.121548Z","title":"Prediction-oriented bayesian active learning","venue":null,"work_id":"7c33d3ba-69ae-448d-ba2d-451ffa16ce86","year":2023},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.799090Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:03f5e73898fe8c2fd3b044f191feb55c4df3b6a8b7dad3b3a53efca5ec04b583","observation_id":"6b95179b-9d73-4c20-8628-0132f41aca3e","resolution":{"observed_at":"2026-08-12T11:16:08.125032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.110243Z","title":"All you need is a good functional prior for B ayesian deep learning","venue":null,"work_id":"e08087a7-0c97-4f27-bf39-2e6c2ee1b369","year":2022},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.802725Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:9e58f76cb6b4ddd14ec8ee4897161de8baa93e2f38cbf650321d2d4bf6117572","observation_id":"c01e68a5-9658-44cc-8f69-f4ea711b9137","resolution":{"observed_at":"2026-08-12T11:16:08.114099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.098192Z","title":"Attention is all you need","venue":null,"work_id":"d4d604bb-0e32-42b8-8d68-900117dd5d4c","year":2017},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.806808Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:1ea14f80e893d39d1d945d86fc2c216f1d219cd0c8b3aaf19b837af54670a57e","observation_id":"f4a27e6f-9998-4950-a535-ada52e716c72","resolution":{"observed_at":"2026-08-12T11:16:08.101827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.085882Z","title":"High-dimensional G aussian sampling: a review and a unifying approach based on a stochastic proximal point algorithm","venue":null,"work_id":"a9cecc7d-5cfc-445c-86a9-81f1562d17f9","year":2022},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.810342Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:dcb87fb2eedf9b685059ba7c2600f940e93f3b48f32c35a855f381c524556f59","observation_id":"cf633de5-b5f0-42b9-801f-b3284881f6c0","resolution":{"observed_at":"2026-08-12T11:16:08.090158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.074271Z","title":"Superglue: A stickier benchmark for general-purpose language understanding systems","venue":null,"work_id":"b5914533-07be-4829-ad07-572df5952c13","year":2019},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.813700Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:acb87d8e20c41d59b6b808e18e9c5ccddfab39e41198ca5a5661dd67e50bd88e","observation_id":"b79b4f62-4481-49f2-bace-0ab20f18f80d","resolution":{"observed_at":"2026-08-12T11:16:08.078678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.061368Z","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":"efdd69a3-007a-4f30-8bbe-82251bf63b60","year":2019},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.816853Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:3bd4350b6087beddca4514f8d4efa1130f657e9fe762d03c00a0d93b07e9fe68","observation_id":"dbd0daf9-d3a9-417e-892e-9b6a2ec8e5a8","resolution":{"observed_at":"2026-08-12T11:16:08.065915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.047831Z","title":null,"venue":null,"work_id":"7274517f-87b0-4734-9a1a-c377ea8b6d16","year":2020},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.820484Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:50c59dc6fc07e00147e81d20588017c9053e7933640c53fdb104f5c6cd1deef6","observation_id":"78bf5183-35ce-40c3-a568-37ce1a8f28e1","resolution":{"observed_at":"2026-08-12T11:16:08.051662Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.10995","last_updated":"2020-01-29T18:08:52Z","snapshot_observed_at":"2026-08-13T00:36:23.003754Z","submitted_at":"2020-01-29T18:08:52Z","title":"The Case for Bayesian Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.10995","snapshot_observed_at":"2026-08-12T11:16:07.823873Z","title":"The case for B ayesian deep learning","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.823873Z"},"links":{"cited_paper":"/paper/2001.10995","citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:57715e1e93135ae1e163e7b3a5d066a69130d48be88a18d88394c9e1958d71bd","observation_id":"a928a52d-7fb8-4d8b-be5e-22ba9b889330","resolution":{"observed_at":"2026-08-12T11:16:07.823873Z","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":"2026-08-12T11:16:08.034369Z","title":"B ayesian deep learning and a probabilistic perspective of generalization","venue":null,"work_id":"05ff9b4f-27fc-4cd0-abe4-5c1ef350d2d4","year":2020},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.829038Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:ce777955ddea27121d5e26f5fd44c1458f55a942f7e667e705ec83ee60f95acc","observation_id":"b071c43a-4c1a-4433-a3bd-9f0aecf45602","resolution":{"observed_at":"2026-08-12T11:16:08.038942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.03771","last_updated":"2020-07-14T03:42:34Z","snapshot_observed_at":"2026-07-06T08:27:58.343233Z","submitted_at":"2019-10-09T03:23:22Z","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.03771","snapshot_observed_at":"2026-08-12T11:16:07.832395Z","title":"Huggingface's transformers: State-of-the-art natural language processing","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.832395Z"},"links":{"cited_paper":"/paper/1910.03771","citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:1764fde81d76345c97e5f70be8e2e54d0a5d12798c9e3b890d7b358c483e1c9b","observation_id":"1058be98-742b-441b-af98-7d8deb7ce7f6","resolution":{"observed_at":"2026-08-12T11:16:07.832395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12379","last_updated":"2025-04-29T06:18:59Z","snapshot_observed_at":"2026-07-06T13:13:37.143547Z","submitted_at":"2022-05-24T21:52:23Z","title":"Gaussian Pre-Activations in Neural Networks: Myth or Reality?","version":4},"cited_work":{"arxiv_id":"2205.12379","doi":null,"metadata_source":"pith","pith_arxiv_id":"2205.12379","snapshot_observed_at":"2026-08-12T11:16:07.913604Z","title":"Gaussian Pre-Activations in Neural Networks: Myth or Reality?","venue":"cs.LG","work_id":"c3e358f8-0922-4f45-90a2-5ecce22c123c","year":2022},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.836984Z"},"links":{"cited_paper":"/paper/2205.12379","citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:044afa2541b0bb3a5796de2e42473ddffbc662e22c163d589a47692b995097f7","observation_id":"41a27bf8-48e7-4803-b8dc-0f74f5491cd6","resolution":{"observed_at":"2026-08-12T11:16:07.919420Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:08.022810Z","title":"Turner, Jos \\' e Miguel Hern \\' a ndez - Lobato, and Alexander L","venue":null,"work_id":"aca6306a-02fc-4f05-966d-8b69cc6bce15","year":2019},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.840678Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:bc040e239c93f65a26d66886d8f1fc951ea611f24b8ab51b0138def58ebd3c38","observation_id":"ee6ee670-f19e-449d-8fc3-1d8e8a4f70e5","resolution":{"observed_at":"2026-08-12T11:16:08.026647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:07.844903Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.844903Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:2e0a52946bac5185415ad7774e169461d3b4b1571439d2e1792466714fa49d6a","observation_id":"9696c489-f21b-41b2-81f6-e403767902c4","resolution":{"observed_at":"2026-08-12T11:16:07.844903Z","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":"2026-08-12T11:16:08.009481Z","title":"B ayesian low-rank adaptation for large language models","venue":null,"work_id":"c7701a1a-a74e-4da9-9bb0-4c916f57f921","year":2024},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.849529Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:4f031500a185f00d9dc679a1be5d5e0c57a13741dba1410f441a2482f9ba9977","observation_id":"6ffc4205-2e1e-4b6d-bb57-851145eaa553","resolution":{"observed_at":"2026-08-12T11:16:08.013838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/s41597-023-02552-1","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T11:16:07.886475Z","title":"Rubin, and Holger R","venue":null,"work_id":"9dc56ecc-983a-4af5-bfda-7204b07fdea2","year":2023},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.853731Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:e1039dd7928491b23c91fea800670a2d901ac09898042ab4b8bde697c4b00cd5","observation_id":"3901859e-c9ff-4013-97c9-56807c13287a","resolution":{"observed_at":"2026-08-12T11:16:07.891699Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:07.991392Z","title":"u tepage, Hedvig Kjellstr \\","venue":null,"work_id":"24389165-afb9-4571-a7fc-d2c32b5672b0","year":2008},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.857401Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:c721a02c24ebde73568ba2c16b47896b30f4559cb3585e02f2accee60e92fd4d","observation_id":"0027b04f-863e-44b7-8ef3-57f1c7eaa1a3","resolution":{"observed_at":"2026-08-12T11:16:07.995070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:16:07.861480Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning","version":4},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-12T11:16:07.861480Z"},"links":{"citing_paper":"/paper/2411.18425"},"observation_digest":"sha256:953dc0e209b4f39c66834993ea37fd4b5fc7e19a5f4450b3dfdd4cc5add0df88","observation_id":"526957b5-fe5b-4705-8304-8a68c63a9ad6","resolution":{"observed_at":"2026-08-12T11:16:07.861480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.18425","last_updated":"2025-07-22T08:42:17Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T00:27:47.186387Z","submitted_at":"2024-11-27T15:07:44Z","title":"Streamlining Prediction in Bayesian Deep Learning"},"reference_resolution":{"displayed":72,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":2,"verified_fuzzy":56},"total_outbound_references":72},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 72 of 72 outbound references and 1 inbound Pith citation observation for arXiv:2411.18425."}