{"as_of":"2026-08-17T12:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:43b2251ebc5e39ef853084b8e54212a6e475e7f5e5be3a309c0461a2795debf4","coverage":[{"denominator":63,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":63,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:39:08.850441Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.18280/citation-record","integrity":"/paper/2505.18280/integrity","json":"/paper/2505.18280/citation-record.json","paper":"/paper/2505.18280"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:39:21.044104Z","title":"A systematic comparison of bayesian deep learning robustness in diabetic retinopathy tasks","venue":null,"work_id":"4de41d7a-9144-4417-a0cc-4ee1a0648590","year":2019},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:00.916750Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:cb9c1ef0529d08b78318d728318f53ae2d3a9afacb89988cdc89672ddaa41b5e","observation_id":"7e8cfd63-be48-45b4-85ec-1e66d91c24ed","resolution":{"observed_at":"2026-08-07T14:39:21.174970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:20.772622Z","title":"Posterior consistency in linear models under shrinkage priors.Biometrika, 100 (4):1011–1018, 2013","venue":null,"work_id":"825ae1ef-bae2-438f-ab8c-74e59c75908a","year":2013},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:00.998538Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:0c9146ee3623356a9893d0df89072dee4a7d4a3bfe308949c060fc8adfe66892","observation_id":"5b3eb237-b1d8-4ca8-9514-522de8239ff3","resolution":{"observed_at":"2026-08-07T14:39:20.920527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:20.580732Z","title":"The horseshoe+ estimator of ultra-sparse signals.Bayesian Analysis, 12(4):1105–1131, 2017","venue":null,"work_id":"7c4d6864-c601-4262-b68b-8ef4926a2a02","year":2017},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:01.114332Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:9f0998794ba0e6f4871e30a36988a63b52ba7985d871bd99df8d920b00d989b8","observation_id":"09a4b233-1aa7-473a-a702-d7edfece8820","resolution":{"observed_at":"2026-08-07T14:39:20.676985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:20.307626Z","title":"Dirichlet–laplace priors for optimal shrinkage.Journal of the American Statistical Association, 110(512):1479–1490, 2015","venue":null,"work_id":"c12e6ae3-ee2e-4c6b-a185-6dc80b1079e4","year":2015},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:01.230577Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:3992bc4c06d6239d33fe2887da8564cc40a4ca73ffb9f426cab03456ed3f207c","observation_id":"5be8963b-1ae3-4fa8-bd16-2e90ed979dac","resolution":{"observed_at":"2026-08-07T14:39:20.448501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:20.065848Z","title":"Graph neural networks with convolutional arma filters.IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(7):3496–3507, 2021","venue":null,"work_id":"ba6efd02-214c-4d9a-806c-12ad2e4346da","year":2021},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:01.397065Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:6f1084af6c2a00bbbd1b48d5ae1d684e6eeac6ccc9479716d5b2d3b261575595","observation_id":"8e54322f-d6f8-44f3-b0af-1fcebb9362ea","resolution":{"observed_at":"2026-08-07T14:39:20.131863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:01.497457Z","title":"Optimal approximation with sparsely connected deep neural networks.SIAM Journal on Mathematics of Data Science, 1(1):8–45, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:01.497457Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:625e9952ae041e5eb6263903d2474f696f346ab23dd876a0ba836ea1ecdaed93","observation_id":"e694ee73-d3ce-423d-b56f-e6f18d0ad18e","resolution":{"observed_at":"2026-08-07T14:39:01.497457Z","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":"2026-08-07T14:39:19.812522Z","title":"Triple the gamma—a unifying shrinkage prior for variance and variable selection in sparse state space and tvp models.Econometrics, 8(2):20, 2020","venue":null,"work_id":"5a1da986-7b3e-46ed-a774-3e4c39c6d4ef","year":2020},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:01.586791Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:3077d5b2e34f23ae9299fe9c5320cb5e005986c9479e06fd9d78d34c41b52c65","observation_id":"07f81906-c357-436d-9b6c-f6f6793b827e","resolution":{"observed_at":"2026-08-07T14:39:19.926528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:19.581811Z","title":"Handling sparsity via the horseshoe","venue":null,"work_id":"a4a1dc1b-6a43-49c9-91b6-4ccdcb8fe420","year":2009},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:01.747379Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:db69cbe3b302c6b41e2641a74087c2ba362e135a019b2c9abfc7c252b29644e1","observation_id":"119b40fe-36df-411e-97a4-5429f498ff05","resolution":{"observed_at":"2026-08-07T14:39:19.694998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:19.358951Z","title":"Fastgcn: Fast learning with graph convolu-tional networks via impor- tance sampling","venue":null,"work_id":"477cf698-5b60-4057-8660-2b3b3cbf9542","year":2018},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:01.903430Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:4fed871f35a99b4e2dd415438eabb17c021bcc2bdc521ca08bacfed9c52af9e2","observation_id":"827bf352-720b-4a42-98c6-bc3750a144d6","resolution":{"observed_at":"2026-08-07T14:39:19.451458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:19.131552Z","title":"Stochastic gradient hamiltonian monte carlo","venue":null,"work_id":"3d6c674b-6dd0-4e87-8fbd-e2a75f04c63b","year":2014},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:02.021035Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:ef58902af9c9e1363d4fc2728b977ccc8b169aa09d4f8a7606bbbe792bcb37ca","observation_id":"df8b6c7f-7f7f-4d5d-9d29-707565652922","resolution":{"observed_at":"2026-08-07T14:39:19.213076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:18.885432Z","title":"Diffusive gibbs sampling","venue":null,"work_id":"2ecbbfcf-b9ac-4032-b22f-878a0472cc47","year":null},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:02.128776Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:3dfe6e0beb3d518ea17ee63541776f081374aaa90f38c39b60107157615e0d27","observation_id":"6ed898b4-b2a8-4385-aa9b-26480e82a99a","resolution":{"observed_at":"2026-08-07T14:39:18.999402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:18.631858Z","title":"Learning graph convolutional networks for multi- label recognition and applications.IEEE Transactions on JOURNAL OF LATEX CLASS FILES, VOL","venue":null,"work_id":"9f5df6a4-42a9-4ad9-985b-db85e4526dac","year":2015},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:02.399738Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:f165a09684e41ab1637aade6ce76b613750e10a5ded6b175b7273e4c500e7595","observation_id":"6b635f94-7a99-4803-922e-0bf69739dda8","resolution":{"observed_at":"2026-08-07T14:39:18.759679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:18.441920Z","title":"Efficient and scalable bayesian neural nets with rank-1 factors","venue":null,"work_id":"6d70d3a9-381f-4d76-8976-1f2cdcf8e580","year":2020},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:02.506799Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:37802861bfb933b58c65a3dd4453fd882887b13a09662af20f32bf09efdb56a6","observation_id":"20c81972-739b-458c-b5e9-36ae4b9fd1e2","resolution":{"observed_at":"2026-08-07T14:39:18.510481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:18.186065Z","title":"Radial bayesian neural networks: Beyond discrete support in large-scale bayesian deep learning","venue":null,"work_id":"78a67f6d-d6e2-4860-b040-75dbf380665f","year":2020},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:02.618044Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:ab50a4edd4ae64cde8f8e07c29754f06330967325aa219d2084b214fcfec09ff","observation_id":"8dec3aeb-bfb7-43ad-b8b6-829e7da8f28c","resolution":{"observed_at":"2026-08-07T14:39:18.292027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:17.985300Z","title":"Encoding the latent posterior of bayesian neural networks for uncertainty quantification.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023","venue":null,"work_id":"6388b62f-1ad2-402d-b9fa-fd778361bfff","year":2023},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:02.725000Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:1ca84f4b2d5f0e08fadc36dc082babeee6b24f194ae7ac06ca174f14f12f050f","observation_id":"8b91d567-a155-4e80-9688-d6bebe874130","resolution":{"observed_at":"2026-08-07T14:39:18.100077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:17.769836Z","title":"Dropout as a bayesian approximation: Representing model uncer- tainty in deep learning","venue":null,"work_id":"48be5fde-16c8-4213-80e2-c7e125fc6e38","year":2016},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:02.867986Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:28bfa4889c7f08f39971137978ee687c273b7605b36aa5e6686bf9cf1b5b7da6","observation_id":"6af9e4b8-f92c-42de-97f4-98501f726e9e","resolution":{"observed_at":"2026-08-07T14:39:17.861577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:17.536857Z","title":"The gr2d2 estimator for the precision matrices.Briefings in Bioinformatics, 23(6):bbac426, 2022","venue":null,"work_id":"384c9968-c38c-48eb-b672-455cbd3c6997","year":2022},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:03.004438Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:dcb29e22249ae8bfbc1e3a089c5cb5b9b15e462b08d5a003effa2849d07af2c9","observation_id":"bce207ba-2241-47cc-80b8-6c18362641ee","resolution":{"observed_at":"2026-08-07T14:39:17.621159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:17.320612Z","title":"Topology- aware graph pooling networks.IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(12):4512– 4518, 2021","venue":null,"work_id":"327507e2-ec65-4a1f-bc4b-002032676e70","year":2021},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:03.094762Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:3890fe4c0de0615021d1414ee0cb4b0bcd91a06b4f76fab51a2f25ee5ee6f2ed","observation_id":"6400aa56-a10f-4998-b434-ceb7f5aba5d1","resolution":{"observed_at":"2026-08-07T14:39:17.409060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:17.101367Z","title":"A bayesian approach to recurrence in neural networks.IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(8):2527–2537, 2020","venue":null,"work_id":"f9937af5-9a07-4bcf-9ae6-9a82282f9297","year":2020},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:03.222003Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:241a115905f0407185d3b3f982bd0e8a63e94af238fd81182bc0a88b64d6041a","observation_id":"5fb0a1ce-7729-4437-844e-f098d50821b0","resolution":{"observed_at":"2026-08-07T14:39:17.196631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:16.895990Z","title":"Model selection in bayesian neural networks via horse- shoe priors.J","venue":null,"work_id":"13eb5587-fe28-4f64-92cd-c7b38f52e53e","year":2019},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:03.389545Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:d0739ac75767a4837f4936298e4dd2b29ef42b5b3ea4455b0e35850a478f1a39","observation_id":"97c80378-21e4-44d6-9391-1cbd6e9a588d","resolution":{"observed_at":"2026-08-07T14:39:16.975673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:16.693288Z","title":"Riemann mani- fold langevin and hamiltonian monte carlo methods","venue":null,"work_id":"dfae84c3-b321-41bf-9da1-c021e22ad4ce","year":2011},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:03.503056Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:eec3501b45518341cbc6183844317fb0f782e72b4724575c82eeebc4a0d7a3e3","observation_id":"7555a0af-bd38-466c-bf53-1490c9602ce9","resolution":{"observed_at":"2026-08-07T14:39:16.813935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:16.499289Z","title":"Structured shrink- age priors.Journal of Computational and Graphical Statis- tics, 33(1):1–14, 2024","venue":null,"work_id":"e2083f44-b9e7-45cf-a180-db9dc0a46097","year":2024},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:03.612286Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:9cfa435b7e91a617c5033018381450a606f8463d73317096a5361f8b27a267db","observation_id":"7baf30f7-13bc-4d86-8d6d-cc2ef344a762","resolution":{"observed_at":"2026-08-07T14:39:16.567882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:03.735006Z","title":"Forecasting macroe- conomic data with bayesian vars: Sparse or dense? it depends!International Journal of Forecasting, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:03.735006Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:af07cb07aab5bf7b3400c629eeca5aa573ff49184c7a8580fdf1fe283b0da036","observation_id":"72b7e839-2014-4751-932a-cefaf29982c0","resolution":{"observed_at":"2026-08-07T14:39:03.735006Z","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":"2026-08-07T14:39:16.346039Z","title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","venue":null,"work_id":"80df9a99-2740-469d-9d02-96c98cf88e30","year":2016},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:03.815705Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:d706087822c7481848971b3aff04dbe6dcb3117b33f87300f5ac67bb1f48bd28","observation_id":"6d79c57e-749d-4dc7-af99-d2ef0d6bab73","resolution":{"observed_at":"2026-08-07T14:39:16.398921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:16.129850Z","title":"Stochastic variational inference.Journal of Machine Learning Research, 2013","venue":null,"work_id":"76941b5c-2295-4697-b95f-8c755354ee85","year":2013},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:03.920348Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:23530194abff2eacda1c805ca6613482a9c1da109d7be0a2ef460d84fb1c5c45","observation_id":"4ee5e2cd-30c1-4f2e-b83b-a52280d7ec09","resolution":{"observed_at":"2026-08-07T14:39:16.235571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:15.952686Z","title":"Hands-on bayesian neural networks-a tutorial for deep learning users","venue":null,"work_id":"d1440897-e5cd-4270-86d2-2fea1f9b216b","year":2020},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:04.046633Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:e7721a145477787dec9fa2cdb53bab5a09999f9ac0b4dc94def8389993b90005","observation_id":"f195ebbf-dd1b-45b4-8156-46f6d0130128","resolution":{"observed_at":"2026-08-07T14:39:16.016204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:04.175541Z","title":"What uncertainties do we need in bayesian deep learning for computer vision? Advances in Neural Information Processing Systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:04.175541Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:04c1998e5b8ee5d68a40c116e486c4f622ac29ac1ca97b2a9d7734294df2e382","observation_id":"fa5cbe1d-4526-4cf5-bde7-00c6e625bfb6","resolution":{"observed_at":"2026-08-07T14:39:04.175541Z","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":"2026-08-07T14:39:04.312964Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:04.312964Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:c21c589330496199edd69ca6ebaae6b103f2cf9bdaed3e5b10253aa840ea2ac1","observation_id":"6e45ccad-5ee5-4d83-9d07-97de42bd24c7","resolution":{"observed_at":"2026-08-07T14:39:04.312964Z","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":"2026-08-07T14:39:04.428939Z","title":"Imagenet classification with deep convolutional neural networks.Advances in Neural Information Processing Systems, 25, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:04.428939Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:c3c97499668487d0f72c01362334971a9506b632c01b21c6d7795b422faae62b","observation_id":"8b0f8e7f-4753-4c1e-a750-4d8f04eef6d4","resolution":{"observed_at":"2026-08-07T14:39:04.428939Z","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":"2026-08-07T14:39:15.685225Z","title":"Simple and scalable predictive un- certainty estimation using deep ensembles.Advances in Neural Information Processing Systems, 30, 2017","venue":null,"work_id":"81dfeb8d-dd05-4520-a768-333bd36f6a85","year":2017},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:04.555703Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:a26d9ab809aa7c75e90a52aa98a31646e0fa17302c20cc7878fb594baba655af","observation_id":"c28cf0d9-f16c-4c9d-910d-b1c54dd7ae5c","resolution":{"observed_at":"2026-08-07T14:39:15.795640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:15.508618Z","title":"Handwritten digit recognition with a back-propagation network.Advances in Neural Informa- tion Processing Systems, 2, 1989","venue":null,"work_id":"889a3bbd-9a42-4416-8109-e9c08b0569c1","year":1989},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:04.689097Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:3cdb550bd1586045c8c6fe19cf022aba9a6fb359664bfbe3ff6235bd83afa653","observation_id":"3d974bcd-402f-434b-9a89-416e6f2563e8","resolution":{"observed_at":"2026-08-07T14:39:15.588412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:15.255715Z","title":"Graphmax for text genera- tion.Journal of Artificial Intelligence Research, 78:823–848, 2023","venue":null,"work_id":"6fe7ac5f-965a-4d09-b55b-826b027c53d3","year":2023},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:04.822858Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:3e5450bf9d02605e92a6fad6115dd43731b78c26f5345236f051e51b706d6f94","observation_id":"22a7a76d-90e2-4b66-bf2c-30f473e0b3c1","resolution":{"observed_at":"2026-08-07T14:39:15.397389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:15.027819Z","title":"Bayesian compression for deep learning.Advances in Neural Information Processing Systems, 30, 2017","venue":null,"work_id":"3991f15e-3580-4198-acd4-304a6151ccb4","year":2017},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:04.969151Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:d235dd4d4c14c2029ae7ff7b48deff2a224f8ea93e41a9219f5173151f0bd5bc","observation_id":"ab38cab7-491d-4c11-afb9-d0885e36d4c8","resolution":{"observed_at":"2026-08-07T14:39:15.140199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:05.085104Z","title":"Predictive uncertainty estimation via prior networks.Advances in Neural Information Processing Systems, 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:05.085104Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:d8a621f733b1534ba2287bd0d4971a519fb8bcf0ca0822fe48bb2ed1bd8b4051","observation_id":"fa0e45f5-07f1-4e89-ae1f-4ba6fd54d769","resolution":{"observed_at":"2026-08-07T14:39:05.085104Z","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":"2026-08-07T14:39:14.765360Z","title":"The ridgelet prior: A covariance function ap- proach to prior specification for bayesian neural net- works.Journal of Machine Learning Research, 22(157):1–57, 2021","venue":null,"work_id":"a73a34ae-65a5-45e1-913d-1c7a0f633ddf","year":2021},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:05.225343Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:69ba8f97bddafd6b965c82460d8d9d83c961cdd3eaa4c52923ddc68232dde396","observation_id":"43d1eac6-d6a4-499f-b4e5-f7da6627b62b","resolution":{"observed_at":"2026-08-07T14:39:14.889426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:14.595875Z","title":"Variational dropout sparsifies deep neural networks","venue":null,"work_id":"be6345af-aa2a-4c09-9b9e-34eb6d3fa4a9","year":2017},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:05.334386Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:ad1db2a8c71115a162a58089418764bf7a2aca2b6f06aedd18f46447d2054c44","observation_id":"464ad3ea-4d9a-422e-8b38-03dd4c5268a6","resolution":{"observed_at":"2026-08-07T14:39:14.666735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:05.450305Z","title":"Stochastic gradient markov chain monte carlo.Journal of the American Statistical Association, 116(533):433–450, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:05.450305Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:7fe32bb74f0b19c722d9312d366a13e20771a425acef53b3d2c0c93602fd58ba","observation_id":"9e69fbfd-00ae-4248-b233-cc9570bb6bd3","resolution":{"observed_at":"2026-08-07T14:39:05.450305Z","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":"2026-08-07T14:39:05.580298Z","title":"Sparsity information and regularization in the horseshoe and other shrinkage priors.Electronic Journal of Statistics, 11(2):5018–5051, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:05.580298Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:0308b6a345563d9c8f6c3234d730fc53514667f0b8994c0b6e2921fe42dd8ac3","observation_id":"49aaaa97-d2f8-45ba-8f25-9d68aa5caf34","resolution":{"observed_at":"2026-08-07T14:39:05.580298Z","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":"2026-08-07T14:39:14.325546Z","title":"Posterior concentration for sparse deep learning.Advances in Neural Information Processing Systems, 31, 2018","venue":null,"work_id":"d8d5b9bc-b797-4e8c-942c-4abae2a0d193","year":2018},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:05.720972Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:2089a70f69cc53d5fc9abdce1b16d3fd624e07bb382dcabaded693e38a916cbe","observation_id":"93c5d1b8-af4b-4ed0-98d4-3c01f555a4e5","resolution":{"observed_at":"2026-08-07T14:39:14.474668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.02599","last_updated":"2019-09-09T14:59:46Z","snapshot_observed_at":"2026-08-17T00:21:58.059250Z","submitted_at":"2019-05-07T14:16:04Z","title":"Interpretable Outcome Prediction with Sparse Bayesian Neural Networks in Intensive Care","version":2},"cited_work":{"arxiv_id":"1905.02599","doi":null,"metadata_source":"pith","pith_arxiv_id":"1905.02599","snapshot_observed_at":"2026-08-07T14:39:09.367241Z","title":"Interpretable Outcome Prediction with Sparse Bayesian Neural Networks in Intensive Care","venue":"cs.LG","work_id":"f08d2170-0b57-4b0c-8d29-55fcfaa010f9","year":2019},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:05.890124Z"},"links":{"cited_paper":"/paper/1905.02599","citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:d5d52ec047778102776985bff87eb99f31c2522bb056cf2423752397b51c3e79","observation_id":"9c94514e-6872-437c-be6a-cd30ac809d9b","resolution":{"observed_at":"2026-08-07T14:39:09.461668Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:14.133000Z","title":"Tractable function-space variational infer- ence in bayesian neural networks.Advances in Neural Information Processing Systems, 35:22686–22698, 2022","venue":null,"work_id":"dc15b16f-7898-4e86-8c99-933e000790ac","year":2022},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:06.034743Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:720e2204f676b7015342d156b391b0859a72d5eb8cc668efe2c36f7d6d52833d","observation_id":"86179116-a79b-47ea-bdeb-d4c93433ca30","resolution":{"observed_at":"2026-08-07T14:39:14.236387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:13.922649Z","title":"Evidential deep learning to quantify classification uncer- tainty.Advances in Neural Information Processing Systems, 31, 2018","venue":null,"work_id":"274add2c-9086-4f80-b0b3-2b98e973955b","year":2018},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:06.152225Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:3cf788bf041a40a4ab9c659c987d7527824583ed9e366b954ad1c4e5fdac1986","observation_id":"c42c1bd9-86bf-4f53-9715-d0506b680ddb","resolution":{"observed_at":"2026-08-07T14:39:14.035300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.02731","last_updated":"2019-01-08T13:03:14Z","snapshot_observed_at":"2026-08-17T02:26:02.710532Z","submitted_at":"2019-01-08T13:03:14Z","title":"A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.02731","snapshot_observed_at":"2026-08-07T14:39:06.273575Z","title":"A comprehensive guide to bayesian convolutional neural network with variational inference.arXiv preprint arXiv:1901.02731, 2019","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:06.273575Z"},"links":{"cited_paper":"/paper/1901.02731","citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:63ccd8c1eb864aca734e76cce35a856b3094e46d5536e50629020912d217c3b3","observation_id":"ec9629bf-848a-40de-8f9b-68eb714ab875","resolution":{"observed_at":"2026-08-07T14:39:06.273575Z","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":"2026-08-07T14:39:13.698600Z","title":"Understanding measures of uncertainty for adversarial example detection","venue":null,"work_id":"6b4c1265-9275-4af3-9832-eb291f4d3d87","year":2018},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:06.385141Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:2cacab44c0a15496d74435dd26593cb79a6c3962ac16facc64746999355dd5ab","observation_id":"4abdf994-e6fc-4063-b75a-e148d717a274","resolution":{"observed_at":"2026-08-07T14:39:13.841562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.06791","last_updated":"2016-11-21T14:06:48Z","snapshot_observed_at":"2026-08-17T08:01:17.533473Z","submitted_at":"2016-11-21T14:06:48Z","title":"Generalized Dropout","version":1},"cited_work":{"arxiv_id":"1611.06791","doi":null,"metadata_source":"pith","pith_arxiv_id":"1611.06791","snapshot_observed_at":"2026-08-07T14:39:09.037010Z","title":"Generalized Dropout","venue":"cs.LG","work_id":"4efb27c9-cc78-471a-879c-5dd434ae7c2f","year":2016},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:06.523251Z"},"links":{"cited_paper":"/paper/1611.06791","citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:9b22c76f0c19feb82e03be79ff61e359ace2aa43da7aedc16b06eda77a9d35a4","observation_id":"987476f4-b8d0-4103-acdc-6df9b35829f6","resolution":{"observed_at":"2026-08-07T14:39:09.170918Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:13.413979Z","title":"Consistent sparse deep learning: Theory and computation.Journal of the American Statistical Association, 117(540):1981–1995, 2022","venue":null,"work_id":"cee795c8-e226-4b77-97cc-4cc5b9ee439b","year":1981},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:06.729620Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:5065b7c07251fd3f3306843417b38ea794ec4618118826717dfadf5270bc12a2","observation_id":"6b4b7b9a-46de-4b18-9dd2-f6842ba89efd","resolution":{"observed_at":"2026-08-07T14:39:13.547844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:13.156435Z","title":"Learning sparse deep neural networks with a spike-and-slab prior","venue":null,"work_id":"82ca12e9-424a-492b-9849-0dffd064567b","year":2022},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:06.855679Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:ee1fcf5cd7978d84101bf3975abb8d3a0647dfa416dfc96ad523554e17a08045","observation_id":"e64b5a9d-77d0-4487-8b8b-0c9a0cda71da","resolution":{"observed_at":"2026-08-07T14:39:13.319853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:12.944591Z","title":"Collapsed variational bounds for bayesian neural networks.Advances in Neural Information Processing Systems, 34:25412–25426, 2021","venue":null,"work_id":"79f3cacf-1284-4bfe-a527-fe930e1fde90","year":2021},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:06.984829Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:82d5ef5023beee9b269578278299eb986022097fd88640dcaafa88788172d34c","observation_id":"d9cb7113-b539-4186-b84c-d6cde543b6d0","resolution":{"observed_at":"2026-08-07T14:39:13.019338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:12.708314Z","title":"All you need is a good functional prior for bayesian deep learning.Journal of Machine Learning Research, 23(74):1–56, 2022","venue":null,"work_id":"6899fa40-f075-4685-ac2a-d43eba09f316","year":2022},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:07.101848Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:0f2fae4292c30e3508d0bdacc94eb4f2dbf91ee119094ea84e5f039c4d2c47ca","observation_id":"1bcb5d2a-e8b6-46ea-bc26-04a6945128c8","resolution":{"observed_at":"2026-08-07T14:39:12.844135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:12.491314Z","title":"Graph attention networks","venue":null,"work_id":"d64cb668-31c2-4e2d-a4a0-dff2d24e6957","year":2018},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:07.224736Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:e8acc2baa9406589610e5741f86d9a725a8dc361e3d0b98f3b30751e669be31a","observation_id":"243c6c1a-df95-4af1-b884-9ee09c62238c","resolution":{"observed_at":"2026-08-07T14:39:12.589632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:12.229803Z","title":"Sparse bayesian learning for end-to-end eeg decoding","venue":null,"work_id":"6a1b6ada-8bc4-48ab-a0fa-0e545cd6c815","year":2023},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:07.363212Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:798490704e0890309cd06be9d216f39eaff96dfedfe9261c7c7b224b49278724","observation_id":"b9363898-621f-4f8e-8cc0-cd3b71428834","resolution":{"observed_at":"2026-08-07T14:39:12.352819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:11.967977Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":"93a6bfb5-c4e0-4caf-b413-c13dacefe3c1","year":2017},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:07.466858Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:d8135371f9149d0f3e6a6c74564077a7eee15df6d1feb82c43344bdbd76153e5","observation_id":"689685af-22e1-4802-900a-4f9a7815b626","resolution":{"observed_at":"2026-08-07T14:39:12.091390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:11.670987Z","title":"Bayesian learning via stochastic gradient langevin dynamics","venue":null,"work_id":"1e4cdd8c-54ae-4710-b25d-beb02f409ec8","year":2011},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:07.722641Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:0c6d5dd7e782f7441f0c46cc01236fab55411f6efa7790fb86ba2ee0a684bbbe","observation_id":"5281d5d3-48b0-4d18-85fe-ed6209d2c5bb","resolution":{"observed_at":"2026-08-07T14:39:11.795804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:11.417729Z","title":"Fashion- mnist: a novel image dataset for benchmarking machine learning algorithms, 2017","venue":null,"work_id":"3c243acc-229d-41e4-b454-1deacd3d5c25","year":2017},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:07.853879Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:a907211d5898e904486a3f0d6f1bba61d9150449ec72db70f85037e612b3a91e","observation_id":"8d57bacd-58d0-467e-80c8-3c72355af63a","resolution":{"observed_at":"2026-08-07T14:39:11.525812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:07.964161Z","title":"How powerful are graph neural networks? In International Conference on Learning Representations, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:07.964161Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:139749605d03ac4a3bf139002925bd010ed61ef0bf36670a8a96543c76118670","observation_id":"fc1bddfd-12e3-410c-a970-82fc1ef9be57","resolution":{"observed_at":"2026-08-07T14:39:07.964161Z","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":"2026-08-07T14:39:11.096980Z","title":"Scalable stochastic gradient riemannian langevin dynamics in non-diagonal metrics.Transactions on machine learning research, 2023(8), 2023","venue":null,"work_id":"b184fef1-ed1a-4f0c-8cf5-d357771a0f68","year":2023},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:08.120603Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:8a7ad0a8af13a0f3c2d86d8db4b2ad6f9230632a222534a33c249d1c9afaea37","observation_id":"5d5a56ef-e876-4745-ab05-e8257d9fc1fe","resolution":{"observed_at":"2026-08-07T14:39:11.229249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:10.783752Z","title":"Scalable stochastic gradient riemannian langevin dynamics in non-diagonal metrics.Transactions on Machine Learning Research, 2023","venue":null,"work_id":"7b841b66-1769-4ed1-a81e-64031479b205","year":2023},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:08.247587Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:9cac3a129aa7db0a6b68b8cb4165320a46804a8d885fb540d92aacd2c900c7b8","observation_id":"f0f7aa82-c06b-4dc9-889c-9dee066d1bcf","resolution":{"observed_at":"2026-08-07T14:39:10.933984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:10.522619Z","title":"Bayesian regression using a prior on the model fit: The r2-d2 shrinkage prior.Journal of the American Statistical Association, pages 1–13, 2020","venue":null,"work_id":"130619f5-ac9c-4619-97e4-7d6095e7d04b","year":2020},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:08.359833Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:00660a2f0225c7a39865e270c4480b7a290fd0e08280d7df79d9c77bf84168da","observation_id":"465e5606-08d0-48b4-b0bc-24be19fd859e","resolution":{"observed_at":"2026-08-07T14:39:10.656294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:10.321607Z","title":"Robust graph representation learning via neural sparsification","venue":null,"work_id":"b0ec10cc-57a4-4dd3-a482-7e495bb063de","year":2020},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:08.475538Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:db9d8c1f43fe19dd23a957be7a1e861577a1c8ee0a30edfcf3df33618facf9ba","observation_id":"9d5deeec-7f32-4d0d-9eb0-c6ce43149a3a","resolution":{"observed_at":"2026-08-07T14:39:10.433018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:09.856601Z","title":null,"venue":null,"work_id":"3f19a1f1-9fd3-4f0d-b6c9-7cd6006a8b80","year":null},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:08.755474Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:f62a2978d8aaf2e2eb7f36ff939fa4f501ca9bb223c2741dd35d4307d91b71dc","observation_id":"7c9262ca-578f-4a76-9fd5-e9c9ff0b5b2c","resolution":{"observed_at":"2026-08-07T14:39:09.969015Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:09.622961Z","title":"log 1 ψjl √ 2π exp (1−µψ jl)2 2ψjlµ !# −E q(ψjl |·) log 1 2 e− 1 2 ψjl =Eq(Y|·)","venue":null,"work_id":"b001fabe-62de-477f-8f0c-3848c4bc9830","year":2015},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:08.850441Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:154262e810893b2619b2148fca33857b53aa75b6fd5f40bbc24dd97333295d8e","observation_id":"9a175f70-3a6b-4248-a83d-e33536b6e6fe","resolution":{"observed_at":"2026-08-07T14:39:09.741901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:10.069778Z","title":"His research focuses on medical image analysis, computer vision, machine learning and AI in healthcare","venue":null,"work_id":"94707d90-f3e7-402d-b8ee-6bea158ba1a3","year":2015},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:08.616598Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:cac0dc82e4b162eb56cb3aa14838f6bb84012923257354934739dac1c1e36ca8","observation_id":"5140cecf-2395-4a84-aa70-85bd18a0d236","resolution":{"observed_at":"2026-08-07T14:39:10.196477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T14:39:02.271901Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T14:39:02.271901Z"},"links":{"citing_paper":"/paper/2505.18280"},"observation_digest":"sha256:4ce56e51222c6bcc20a288dd467b94c917aaa965b2cedf1ee0426cacbd53c1b7","observation_id":"ed12eeba-254c-455c-b5a2-66d66e12a20a","resolution":{"observed_at":"2026-08-07T14:39:02.271901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.18280","last_updated":"2025-05-23T18:15:44Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T03:19:23.271505Z","submitted_at":"2025-05-23T18:15:44Z","title":"Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior"},"reference_resolution":{"displayed":63,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":2,"verified_fuzzy":49},"total_outbound_references":63},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:2505.18280."}