{"as_of":"2026-08-19T01:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d61153a6f0e3d73bd707b672306977b05f51db6cbd63d1a43eec3746a804398b","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T19:08:30.067696Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T14:55:15.877147Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T11:26:03.159725Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"cited_work":{"arxiv_id":"2412.07169","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.07169","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Staib, and John A","venue":null,"work_id":"786372cf-47d2-4c62-9c03-e4f8ac7036f0","year":2025},"citing_paper":{"arxiv_id":"2604.12719","last_updated":"2026-04-14T13:33:40Z","snapshot_observed_at":"2026-07-06T23:00:51.385974Z","submitted_at":"2026-04-14T13:33:40Z","title":"Monte Carlo Stochastic Depth for Uncertainty Estimation in Deep Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-10T14:55:15.877147Z"},"links":{"cited_paper":"/paper/2412.07169","citing_paper":"/paper/2604.12719"},"observation_digest":"sha256:add509dc7f86544c372fe6ab96833542633d328bff79a2eb99013f5214860711","observation_id":"12c7e482-65f4-4f0f-b506-c3e3cddd69db","resolution":{"observed_at":"2026-05-11T11:26:03.169344Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.07169/citation-record","integrity":"/paper/2412.07169/integrity","json":"/paper/2412.07169/citation-record.json","paper":"/paper/2412.07169"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:08:32.630811Z","title":"Information dropout: Learning optimal representations through noisy computa- tion.IEEE transactions on pattern analysis and machine intelligence, 40(12):2897–2905, 2018","venue":null,"work_id":"4a300b9c-9df0-43d3-8786-fcb7da0a39f2","year":2018},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:28.851123Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:89d84f6fed8530042c5083eaea16eb175015bacb5727760808b4fbebe04857d6","observation_id":"899d722b-151e-4ac7-80fc-90eb7754fa90","resolution":{"observed_at":"2026-08-11T19:08:32.704171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:32.475816Z","title":"The medical segmentation decathlon.Nature communications, 13(1):4128, 2022","venue":null,"work_id":"222292c3-e9df-47c6-bf3e-6868ff4a1f70","year":2022},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:28.924281Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:4c5adf8c45f54f456526a869209f9894fbb9676efa7984674c43b1ccc4e3de95","observation_id":"69177c54-b898-461f-b3ae-388bfee9ada3","resolution":{"observed_at":"2026-08-11T19:08:32.540096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:32.450453Z","title":"Adaptive dropout for training deep neural networks.Advances in neural information pro- cessing systems, 26, 2013","venue":null,"work_id":"c402544c-3c31-4a2c-ac70-e6a4575a1ca3","year":2013},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:28.928991Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:c11e98e1826ee7598a0814694eb8cda9e097a50bbb777223725d366c14e5832f","observation_id":"421d21d3-ad54-48e9-a94f-27d08e703cac","resolution":{"observed_at":"2026-08-11T19:08:32.455580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:32.435140Z","title":"The need for uncertainty quantification in machine- assisted medical decision making.Nature Machine Intelli- gence, 1(1):20–23, 2019","venue":null,"work_id":"11581183-cc98-4146-abb5-3671eecada39","year":2019},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:28.933870Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:2d638c5ecaf05da664908d9bb6ac896c5a2d663fd824a964dfd997dcc9220215","observation_id":"e99bc180-c72b-4178-b18b-524ceeabd3c5","resolution":{"observed_at":"2026-08-11T19:08:32.440056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.04062","last_updated":"2021-08-14T18:35:05Z","snapshot_observed_at":"2026-08-14T19:55:44.931753Z","submitted_at":"2018-01-12T05:42:58Z","title":"MINE: Mutual Information Neural Estimation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.04062","snapshot_observed_at":"2026-08-11T19:08:28.939691Z","title":"Mine: mutual information neural estimation.arXiv preprint arXiv:1801.04062, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:28.939691Z"},"links":{"cited_paper":"/paper/1801.04062","citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:16c6f35641ecb2a8f6cfba0e242c859e775095efb2619e18b22480706de0259b","observation_id":"158b29c9-8098-4a12-8a11-34fec6220292","resolution":{"observed_at":"2026-08-11T19:08:28.939691Z","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":"2026-08-11T19:08:28.944835Z","title":"Weight uncertainty in neural network","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:28.944835Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:0d233126c058095172a505c2ff875c1b5ae6e91b024d03461a8182e7e2184c5f","observation_id":"96b7cf7e-380d-4321-a88b-c11cf8bc65ce","resolution":{"observed_at":"2026-08-11T19:08:28.944835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.09037","last_updated":"2023-03-30T22:42:38Z","snapshot_observed_at":"2026-08-15T21:41:08.949853Z","submitted_at":"2019-02-24T23:41:54Z","title":"Adaptive Estimators Show Information Compression in Deep Neural Networks","version":2},"cited_work":{"arxiv_id":"1902.09037","doi":null,"metadata_source":"pith","pith_arxiv_id":"1902.09037","snapshot_observed_at":"2026-08-11T19:08:30.257889Z","title":"Adaptive Estimators Show Information Compression in Deep Neural Networks","venue":"cs.LG","work_id":"c21a1a20-2cd5-4c16-8a03-c8fd6860a93f","year":2019},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:28.949911Z"},"links":{"cited_paper":"/paper/1902.09037","citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:8a0b0ae8c07d2d9c2e6a022b1532bc71b5e4b6292042a04e742c361f7c008701","observation_id":"46763820-6f99-4b62-b8c6-ccfe2f52b33a","resolution":{"observed_at":"2026-08-11T19:08:30.265484Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:32.382430Z","title":"John Wiley & Sons, 1999","venue":null,"work_id":"71193c22-ce61-4010-a944-0e92f1538106","year":1999},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:28.955476Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:2e1881849e2f4f535c3d64ae30bc3fafb57375b20267bfa6fce4980d184faa0f","observation_id":"fe157901-6837-44c0-81ec-cc79886148b3","resolution":{"observed_at":"2026-08-11T19:08:32.415915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.17536","last_updated":"2024-07-23T12:23:10Z","snapshot_observed_at":"2026-08-17T05:15:44.402201Z","submitted_at":"2024-06-25T13:20:39Z","title":"MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.17536","snapshot_observed_at":"2026-08-11T19:08:28.959760Z","title":"Medmnist-c: Comprehensive benchmark and im- proved classifier robustness by simulating realistic image corruptions.arXiv preprint arXiv:2406.17536, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:28.959760Z"},"links":{"cited_paper":"/paper/2406.17536","citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:4140f85e69e20447327147769782190933a2fbb202e37a57836c4f9a4dae17ab","observation_id":"06bc36d6-1ae0-4243-b028-8a111aa76ba7","resolution":{"observed_at":"2026-08-11T19:08:28.959760Z","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":"2026-08-11T19:08:32.166133Z","title":"Masksembles for uncertainty estimation","venue":null,"work_id":"f5c21f4d-e368-4fd6-99e2-32d03a9e18e4","year":2021},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:28.963826Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:7a73b46f9c9d7bd619c85fae9433fdb5cf64e4843defb46278b87fa40be96380","observation_id":"7801702d-414c-457f-8b63-61fb006fe92e","resolution":{"observed_at":"2026-08-11T19:08:32.274112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:32.152205Z","title":"Mc layer normalization for calibrated uncertainty in deep learn- ing.Transactions on Machine Learning Research, 2024","venue":null,"work_id":"ee68ec3b-4998-44a4-8598-9785f02114a6","year":2024},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.036150Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:bfbfea99fb9d3e8aa00354a612de21a62ed0749789170348a545b781c722d127","observation_id":"7c6b1472-e23a-4f63-a22b-682596a393ed","resolution":{"observed_at":"2026-08-11T19:08:32.156434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:32.138648Z","title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","venue":null,"work_id":"60c508d6-5a5e-4766-8dae-15c119f94e52","year":2016},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.142680Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:7942bf6a5e16d816121280d11380dc070f1d2f7ca33bee2347a124f79ca95ec0","observation_id":"1b4e4f83-e8f8-4c40-9e85-4425e8656249","resolution":{"observed_at":"2026-08-11T19:08:32.142706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:32.123327Z","title":"Concrete dropout","venue":null,"work_id":"ef30010e-3a26-4cad-a94e-269f72cbf338","year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.248377Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:efe5cd887306199bb3a985e25524f513cdceb25d4c285d0e1f4a2604649887a6","observation_id":"899fbaf8-89bc-4e1a-a30e-094dadb5c2b9","resolution":{"observed_at":"2026-08-11T19:08:32.129056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:32.015333Z","title":"Uncertainty in deep learning.phd thesis,","venue":null,"work_id":"79b80a2c-7e5c-4e09-9e16-129510a0f442","year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.346288Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:bf3effffc33934a199c26571a154eeadb8cf8d3cd87e04901659b51bffc14bc7","observation_id":"75fddebe-35db-48e5-acc1-e594bb5c29da","resolution":{"observed_at":"2026-08-11T19:08:32.111847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.08206","last_updated":"2019-04-24T13:00:42Z","snapshot_observed_at":"2026-08-14T19:12:51.551739Z","submitted_at":"2018-05-21T17:59:59Z","title":"Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.08206","snapshot_observed_at":"2026-08-11T19:08:29.351237Z","title":"Bias- reduced uncertainty estimation for deep neural classifiers","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.351237Z"},"links":{"cited_paper":"/paper/1805.08206","citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:f09e674400a77df30e6c71772f257be1eaad8481ba560e8d396714f5e832742a","observation_id":"30d06853-d850-4094-9417-ce158ad02305","resolution":{"observed_at":"2026-08-11T19:08:29.351237Z","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":"2026-08-11T19:08:29.356321Z","title":"On calibration of modern neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.356321Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:7cf0a8d99fafa0eb4bae710256c7152a1f96d5ddfc8ede82cf02d471f7653f17","observation_id":"39c2cc54-1259-42b1-bdd3-8fbe58efff6b","resolution":{"observed_at":"2026-08-11T19:08:29.356321Z","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":"2026-08-11T19:08:29.361044Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.361044Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:d0c34fc96c404ac63f1f052599bb2975dd7195596dfc3df5c94300ca86825a75","observation_id":"3b5e2dec-569a-4123-95c7-814c7a5923dc","resolution":{"observed_at":"2026-08-11T19:08:29.361044Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.12261","last_updated":"2019-03-28T20:56:37Z","snapshot_observed_at":"2026-08-15T10:34:34.836991Z","submitted_at":"2019-03-28T20:56:37Z","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.12261","snapshot_observed_at":"2026-08-11T19:08:29.366078Z","title":"Benchmarking neu- ral network robustness to common corruptions and perturba- tions.arXiv preprint arXiv:1903.12261, 2019","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.366078Z"},"links":{"cited_paper":"/paper/1903.12261","citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:7b57058e1fc535167c4bdee0884849bbdd0e0d06c4a6e799bda8e43d5c9a499e","observation_id":"73588f86-220b-4c7a-a9e4-b70a1931adfd","resolution":{"observed_at":"2026-08-11T19:08:29.366078Z","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":"2026-08-11T19:08:31.881600Z","title":"Imagenet object localization challenge.Kaggle","venue":null,"work_id":"3cb1e054-fe0e-4625-8aee-2bcc88ded7ae","year":2018},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.370366Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:73636824f0d1df3cb6063892a2892c3bb71f01ba29b786135972554f23959eb9","observation_id":"b958ac11-0af4-4a17-b557-72ae011f9269","resolution":{"observed_at":"2026-08-11T19:08:31.885708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:31.860351Z","title":"nnu-net: a self-configuring method for deep learning-based biomedical image segmen- tation.Nature methods, 18(2):203–211, 2021","venue":null,"work_id":"aea7f95f-84e4-4606-91e2-8d086c555b52","year":2021},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.374754Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:30ac8fe6b5f01b53c4fbf0c1a236bfe189101464cb42445b6859e1e49ce50071","observation_id":"ec814c79-f0a9-41b3-b5f6-891a2eb6ba0b","resolution":{"observed_at":"2026-08-11T19:08:31.865735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:29.379303Z","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":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.379303Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:45d5524bcd7f4fe9917118ed8d9910b23e0ebfa671096dd4c0b0b9531bcfa772","observation_id":"734a97f0-482e-4c96-b86c-c9a81348f1c3","resolution":{"observed_at":"2026-08-11T19:08:29.379303Z","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":"2026-08-11T19:08:31.829825Z","title":"Varia- tional dropout and the local reparameterization trick.Ad- vances in neural information processing systems, 28, 2015","venue":null,"work_id":"da5883e7-6329-46b9-85c3-1819d94f6b32","year":2015},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.385662Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:973fb31fdc8f9843e9454645cb5841debf14a0ebcfcde1891b899e02195b00e8","observation_id":"6614401f-71c8-418f-9dad-6e8aacb34483","resolution":{"observed_at":"2026-08-11T19:08:31.840390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:31.634763Z","title":"Improving model calibration with accuracy versus uncertainty optimization","venue":null,"work_id":"9342ce98-f5a0-4b35-8bc2-d3ba0550a36b","year":2020},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.389679Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:680e57ee7c6753ac66fbb9976ddfd018325cf5dc94cca089b3af4824402f5661","observation_id":"acbb01b3-3dea-48c9-883b-1d30f5f6b8a0","resolution":{"observed_at":"2026-08-11T19:08:31.717626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:31.621248Z","title":"Simple and scalable predictive uncertainty estima- tion using deep ensembles.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":"2ef179db-0755-4d22-abf3-47f9089620c2","year":2017},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.393472Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:b0247c4c83b104b756a46f383095c567c790c10ab491ac087aad8500591295b3","observation_id":"6b84cd5a-e4b0-4729-932d-2a1a96468ecc","resolution":{"observed_at":"2026-08-11T19:08:31.625545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.13550","last_updated":"2019-11-18T16:49:58Z","snapshot_observed_at":"2026-08-15T02:40:27.175888Z","submitted_at":"2019-09-30T09:29:44Z","title":"Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.13550","snapshot_observed_at":"2026-08-11T19:08:29.397257Z","title":"Well-calibrated model uncertainty with temperature scaling for dropout variational inference.arXiv preprint arXiv:1909.13550, 2019","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.397257Z"},"links":{"cited_paper":"/paper/1909.13550","citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:81998c62103b7722861effa6c34ce301dc2b98cba6f483aa8a2818e96106e5ee","observation_id":"9dda301a-96b7-4b6c-a36e-fdac7b24ab30","resolution":{"observed_at":"2026-08-11T19:08:29.397257Z","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":"2026-08-11T19:08:31.607755Z","title":"Dropout injection at test time for post hoc uncertainty quantifica- tion in neural networks.Information Sciences, 645:119356,","venue":null,"work_id":"b72a38fe-fc8a-4abf-8746-a79cb3f33c31","year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.401798Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:97f007f89f524b166984ef4272cc03439a58b3dd7f3d4746bf89cc54aeeb5faa","observation_id":"df8ee1ca-cd0b-40bf-aa6e-631f92f782f8","resolution":{"observed_at":"2026-08-11T19:08:31.612363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:31.486822Z","title":"Boundary-aware uncertainty suppression for semi-supervised medical image segmenta- tion.IEEE Transactions on Artificial Intelligence, 5(8): 4074–4086, 2024","venue":null,"work_id":"9852a047-3007-4c0b-8678-c5052aa7430b","year":2024},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.526806Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:4bde3e26e06e22d8d24ef530be86c5604209b2209c35176c9677b50669dbf566","observation_id":"13e6c5c5-0897-4649-81a3-58a10dbaa133","resolution":{"observed_at":"2026-08-11T19:08:31.545831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:31.356946Z","title":"Confidence calibration and predictive uncertainty estimation for deep medical im- age segmentation.IEEE transactions on medical imaging, 39(12):3868–3878, 2020","venue":null,"work_id":"a4a1604d-3a78-4e62-a8a0-510369ad35ae","year":2020},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.606631Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:3f8957c9fe4d66e9b05358c401e4a4ba10fe530bca9e126751b127a044d41b3e","observation_id":"ba16efba-3323-401c-b04b-1f522c356d2b","resolution":{"observed_at":"2026-08-11T19:08:31.362269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:31.306781Z","title":"Training-free uncertainty estimation for dense re- gression: Sensitivity as a surrogate","venue":null,"work_id":"284d750e-6b11-4630-af20-3fa0cc61a3d6","year":2022},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.725384Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:93ac3237085843a26f3608671db7f8e6153cefaf7905df0b9f8ca5f762d6d172","observation_id":"68876716-dd0f-4757-b8a0-4e045c03a59c","resolution":{"observed_at":"2026-08-11T19:08:31.346049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:31.126253Z","title":"Dropconnect is effective in modeling uncertainty of bayesian deep networks","venue":null,"work_id":"def1839b-6bc0-46ef-bcc9-be3c1f158b5d","year":2021},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.793504Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:4bbc89c71fd5ef191f6fe798ba8952b7bc1a504a001c0cd5504375267fa686d5","observation_id":"661d1d80-3f71-4818-9c58-dd8f1248f6e8","resolution":{"observed_at":"2026-08-11T19:08:31.209932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12709","last_updated":"2019-03-23T17:00:28Z","snapshot_observed_at":"2026-08-17T12:24:05.854671Z","submitted_at":"2018-11-30T10:41:31Z","title":"Evaluating Bayesian Deep Learning Methods for Semantic Segmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.12709","snapshot_observed_at":"2026-08-11T19:08:29.798937Z","title":"Evaluating bayesian deep learning methods for semantic segmentation.arXiv preprint arXiv:1811.12709, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.798937Z"},"links":{"cited_paper":"/paper/1811.12709","citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:3c894a4d122d31f4456fe107aaf481b27525ccdb3e123c36ec0b9312e0d8d0ff","observation_id":"a83774e6-d1ca-4b94-bd3d-27bf670e3b9a","resolution":{"observed_at":"2026-08-11T19:08:29.798937Z","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":"2026-08-11T19:08:31.111678Z","title":"Accuracy-rejection curves (arcs) for com- paring classification methods with a reject option","venue":null,"work_id":"e4b5c37f-0f80-4c4d-9d93-64b6e1704120","year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.803821Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:e604203943952d90d412d65cb102d32c8057154f4cc9aa5c56e5c2a8de6bb797","observation_id":"84698426-6d20-45fb-af2d-2616428f5a7e","resolution":{"observed_at":"2026-08-11T19:08:31.116134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:31.097110Z","title":"Risk versus uncertainty in deep learning: Bayes, bootstrap and the dangers of dropout","venue":null,"work_id":"f5e5e857-b087-4657-8265-11dc9f03fafb","year":2016},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.808642Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:78bc55fee2d18bec8f31ea25ffa2ea394b2a8242e806e6a5d74cef683a970d78","observation_id":"277f7330-87e8-4e61-91a5-9a1b80d26ece","resolution":{"observed_at":"2026-08-11T19:08:31.101876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:30.930019Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":"5c1c4b43-29f2-410e-bd19-7fa232f00e26","year":2019},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.813175Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:98e76ebd9289868417374c4eea9ff0181159b3ea784a1bd2cd02bfd41db0d968","observation_id":"63c750cf-d58d-484e-a13d-bebf99eb0a44","resolution":{"observed_at":"2026-08-11T19:08:31.002992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:30.865568Z","title":"An- nealed dropout training of deep networks","venue":null,"work_id":"20d3f23f-7a13-46ac-bf31-5c524948b26e","year":2014},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.817048Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:bd154b73bedc033dfb333c47dbad097596dda5887932f9159464077fd440e5e2","observation_id":"f5211286-3615-47f4-b3d5-b0ae27fccf74","resolution":{"observed_at":"2026-08-11T19:08:30.870167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.06749","last_updated":"2022-02-21T15:42:01Z","snapshot_observed_at":"2026-08-16T17:22:07.772427Z","submitted_at":"2022-02-10T23:32:26Z","title":"Information Flow in Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.06749","snapshot_observed_at":"2026-08-11T19:08:29.821082Z","title":"Information flow in deep neural net- works.arXiv preprint arXiv:2202.06749, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.821082Z"},"links":{"cited_paper":"/paper/2202.06749","citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:407de40d1f8b35acef3b843c883866dcb7920ef8ae7e22764b8e20ff753c5f23","observation_id":"4e6516ec-23c9-4a4d-83ee-856ad90f38ee","resolution":{"observed_at":"2026-08-11T19:08:29.821082Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.00810","last_updated":"2017-04-29T17:32:47Z","snapshot_observed_at":"2026-08-14T21:13:52.487817Z","submitted_at":"2017-03-02T14:53:14Z","title":"Opening the Black Box of Deep Neural Networks via Information","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.00810","snapshot_observed_at":"2026-08-11T19:08:29.850930Z","title":"Opening the black box of deep neural networks via information.arXiv preprint arXiv:1703.00810, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.850930Z"},"links":{"cited_paper":"/paper/1703.00810","citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:597ec9bcb326de784900e9221e95a649028588ac68ea3a0f383c440fd128b3d2","observation_id":"b3a3264b-9ca4-4b35-9fb8-d14bfd7c484e","resolution":{"observed_at":"2026-08-11T19:08:29.850930Z","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":"2026-08-11T19:08:30.849176Z","title":"Dropout: a simple way to prevent neural networks from overfitting.The journal of machine learning research, 15(1):1929–1958, 2014","venue":null,"work_id":"d045c8f1-411a-41c3-ad5a-c79e739b45af","year":1929},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:29.892733Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:d75a02be6674f84e723b8590599b8b551246a1259137afc963ffb84eac826a1a","observation_id":"7b278b0d-2a59-4ac5-906a-11e9e86de5d3","resolution":{"observed_at":"2026-08-11T19:08:30.854665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:30.827900Z","title":"Bayesian uncertainty estimation for batch normalized deep networks","venue":null,"work_id":"66fbea71-e304-4c09-b52b-0ec53be28eae","year":2018},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:30.017685Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:f9b1764b76ed7cd84f23505619277029f4c78c9a128c53de9e3697347c881774","observation_id":"6d207527-599c-4d21-a2d4-43a61fdac1da","resolution":{"observed_at":"2026-08-11T19:08:30.838215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:30.609056Z","title":"Regularization of neural networks using drop- connect","venue":null,"work_id":"662b3bd7-e808-4cd4-b090-017d80dfc799","year":2013},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:30.033270Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:33a7945fc106e2bc909e638b6bf41aa7d7129c439b9e4bcd5e52d1891bac0c10","observation_id":"ab118919-c660-4252-a2c8-6df7939fc1d1","resolution":{"observed_at":"2026-08-11T19:08:30.738220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:30.590112Z","title":"Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600–612, 2004","venue":null,"work_id":"05f5dd65-d032-443a-b3e4-0df5f57d59a0","year":2004},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:30.038710Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:86725b0a9f19a348a34e4cd7f81ab8922f6d95ac99204f3bc10e7637dc826100","observation_id":"9f10e1fb-dcfe-49fe-8ef4-2b3a9154996a","resolution":{"observed_at":"2026-08-11T19:08:30.598164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:30.043146Z","title":"Medm- nist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification.Scientific Data, 10(1):41,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:30.043146Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:30c947d94b17d3180760b35943e17ed7e07dc905f6b9c5d0dc1961011556d0b8","observation_id":"10dd2c4d-3341-4d29-a31d-8284285923e6","resolution":{"observed_at":"2026-08-11T19:08:30.043146Z","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":"2026-08-11T19:08:30.541589Z","title":"Boundary un- certainty aware network for automated polyp segmentation","venue":null,"work_id":"1bbf25e6-9381-4091-bb14-c367834e536a","year":2024},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:30.048488Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:b2cee8beb6e5c6cb57f1046dd56098ee8d2e8c07e9387076634f6da0ad25ad2e","observation_id":"458ecf88-f973-4437-9b2b-8464d76f9136","resolution":{"observed_at":"2026-08-11T19:08:30.568050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:30.466789Z","title":"Reproducibility Statement The Rate-In algorithm code and implementation examples are available in theGitHub repository 1","venue":null,"work_id":"5386a4fa-6c44-4b2c-9b2f-d5f6e19e02fd","year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:30.052785Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:b458a6f221bae503ecbcba5e623678b173f5e2601eb296f310ff712b94339d8d","observation_id":"f6bc9dee-0190-470d-adbd-291e9013a161","resolution":{"observed_at":"2026-08-11T19:08:30.471812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:30.437465Z","title":"Synthetic Data Figures 8 and 9 evaluate Rate-In dropout’s performance","venue":null,"work_id":"947b2988-426e-4131-acd5-071caa7d7b8c","year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:30.062975Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:5bbc1bfcfc3c7fb44ee66c9d4f3a971c0f2e21cdd8ada46ec134f2f510009a55","observation_id":"f6ae8a0c-759e-44ce-b240-6fe481fecba4","resolution":{"observed_at":"2026-08-11T19:08:30.442674Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:30.290127Z","title":"This perspective shift allows us to examine how dropout affects network representations in task-specific contexts","venue":null,"work_id":"a091d1e8-bfa0-4f9c-b938-cca07f075090","year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:30.067696Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:930169baa1bf42edadd3186e5c5e0e80ec3bf8f8a5923962b605ba9fb4d04666","observation_id":"ab5faa3e-3494-4930-865b-1548cd82ce3e","resolution":{"observed_at":"2026-08-11T19:08:30.388182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T19:08:30.452693Z","title":"Figure 5","venue":null,"work_id":"352fc533-e0e3-4455-bdfd-15514d2e1cef","year":null},"citing_paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","version":4},"reference_index":123,"source":"pdf_text","source_observed_at":"2026-08-11T19:08:30.057213Z"},"links":{"citing_paper":"/paper/2412.07169"},"observation_digest":"sha256:55145039c9af27cb8ed1a92415954b4e6fcc601f2b9c233c44fc36fb37af374a","observation_id":"c993d19f-b1c1-416e-a669-ca4d211e7dff","resolution":{"observed_at":"2026-08-11T19:08:30.457094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.07169","last_updated":"2025-06-04T03:01:01Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T12:30:08.970697Z","submitted_at":"2024-12-10T04:03:46Z","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":1,"verified_fuzzy":32},"total_outbound_references":47},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 1 inbound Pith citation observation for arXiv:2412.07169."}