{"as_of":"2026-08-17T01:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:243688ad31101f079e4ff3271b2593f5339c4b93ca476a0527fb3edd7ee184e0","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T12:25:48.507194Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.07235/citation-record","integrity":"/paper/1908.07235/integrity","json":"/paper/1908.07235/citation-record.json","paper":"/paper/1908.07235"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1606.06565","last_updated":"2016-07-25T17:23:29Z","snapshot_observed_at":"2026-07-06T05:00:46.434335Z","submitted_at":"2016-06-21T13:37:05Z","title":"Concrete Problems in AI Safety","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.06565","snapshot_observed_at":"2026-08-14T12:25:48.353988Z","title":"Concrete Problems in AI Safety","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.353988Z"},"links":{"cited_paper":"/paper/1606.06565","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:335f73f365f56ead1837d886269f322622cacfb793dfc430aa5b11affc285ac5","observation_id":"50573c5a-d27c-46a2-b6b0-3a0eaccaa4b9","resolution":{"observed_at":"2026-08-14T12:25:48.353988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.07397","last_updated":"2018-06-07T16:25:12Z","snapshot_observed_at":"2026-08-14T20:45:49.587140Z","submitted_at":"2017-07-24T04:17:33Z","title":"Synthesizing Robust Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.07397","snapshot_observed_at":"2026-08-14T12:25:48.359575Z","title":"Synthesizing Robust Adversarial Examples","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.359575Z"},"links":{"cited_paper":"/paper/1707.07397","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:d6277a54901cc99de4ea6caf354d6bf53a08adc1ff14ffbb9e6b112d747ffc86","observation_id":"29d27c3f-0078-40cc-a837-39b32378faf8","resolution":{"observed_at":"2026-08-14T12:25:48.359575Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.04865","last_updated":"2018-02-13T21:31:36Z","snapshot_observed_at":"2026-08-14T19:46:10.262380Z","submitted_at":"2018-02-13T21:31:36Z","title":"Learning Confidence for Out-of-Distribution Detection in Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.04865","snapshot_observed_at":"2026-08-14T12:25:48.364649Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.364649Z"},"links":{"cited_paper":"/paper/1802.04865","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:f738d008506a5087a3744235a45bd9b5fdc33498e4265a13cceb8a5f7c1ea70d","observation_id":"06739f99-d675-4c41-8498-2756e0090a56","resolution":{"observed_at":"2026-08-14T12:25:48.364649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.00410","last_updated":"2017-11-15T23:31:59Z","snapshot_observed_at":"2026-08-14T21:14:04.215100Z","submitted_at":"2017-03-01T17:43:10Z","title":"Detecting Adversarial Samples from Artifacts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.00410","snapshot_observed_at":"2026-08-14T12:25:48.370065Z","title":"Curtin, Saurabh Shintre, and Andrew B","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.370065Z"},"links":{"cited_paper":"/paper/1703.00410","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:11485d9d9d1b2124ddbcfdad284eeb90e3fbf8c4a0259db5398e8ca0c737a027","observation_id":"4551c657-727c-4e52-9829-e1e427d1144e","resolution":{"observed_at":"2026-08-14T12:25:48.370065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.02142","last_updated":"2016-10-04T16:50:26Z","snapshot_observed_at":"2026-08-14T22:45:32.724093Z","submitted_at":"2015-06-06T12:30:43Z","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.02142","snapshot_observed_at":"2026-08-14T12:25:48.375495Z","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.375495Z"},"links":{"cited_paper":"/paper/1506.02142","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:a63dc5c3519e62a0cbc5630a18ec897604a66986657bd023ba92ad2e2c546608","observation_id":"11697c3a-a43b-4783-aaaf-fcf596f32b50","resolution":{"observed_at":"2026-08-14T12:25:48.375495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.01613","last_updated":"2018-07-04T14:36:15Z","snapshot_observed_at":"2026-08-14T18:55:45.164749Z","submitted_at":"2018-07-04T14:36:15Z","title":"Conditional Neural Processes","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.01613","snapshot_observed_at":"2026-08-14T12:25:48.380791Z","title":"Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo J","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.380791Z"},"links":{"cited_paper":"/paper/1807.01613","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:5fe529880a84519b585cf0f2deeb5d758e6914ecf89aa3f4e84866f0a16e1767","observation_id":"1bca10cb-8b8a-4ac3-97de-2266585eb916","resolution":{"observed_at":"2026-08-14T12:25:48.380791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.04599","last_updated":"2017-08-03T13:29:46Z","snapshot_observed_at":"2026-08-15T12:29:38.248604Z","submitted_at":"2017-06-14T17:33:50Z","title":"On Calibration of Modern Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.04599","snapshot_observed_at":"2026-08-14T12:25:48.386540Z","title":"Weinberger","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.386540Z"},"links":{"cited_paper":"/paper/1706.04599","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:db3d9d6c757764dea19750a3ddfebda61d4347a22a2207db0570f40d3387e20a","observation_id":"3573f5ea-398b-4d77-b925-9bcb5af7aaa3","resolution":{"observed_at":"2026-08-14T12:25:48.386540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.09289","last_updated":"2019-07-01T00:18:00Z","snapshot_observed_at":"2026-08-14T18:48:10.764497Z","submitted_at":"2018-07-24T18:08:45Z","title":"Noise Contrastive Priors for Functional Uncertainty","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.09289","snapshot_observed_at":"2026-08-14T12:25:48.391422Z","title":"Reliable uncertainty estimates in deep neural networks using noise contrastive priors","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.391422Z"},"links":{"cited_paper":"/paper/1807.09289","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:1db314f2701d03e8ae916487b83557e88da86becae53b299bc53df9730934685","observation_id":"218204a0-b82a-4154-a03f-4b9734854546","resolution":{"observed_at":"2026-08-14T12:25:48.391422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.09460","last_updated":"2019-02-27T19:27:58Z","snapshot_observed_at":"2026-08-14T19:11:46.564833Z","submitted_at":"2018-05-24T00:17:24Z","title":"Cautious Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.09460","snapshot_observed_at":"2026-08-14T12:25:48.396402Z","title":"Cautious Deep Learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.396402Z"},"links":{"cited_paper":"/paper/1805.09460","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:fcee636e106943e6829179825b967d06b9278b9915a42a574169505f5723d0fb","observation_id":"fc187e0d-95d6-460b-8a6f-d635b9084b2c","resolution":{"observed_at":"2026-08-14T12:25:48.396402Z","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":"2026-08-14T12:25:48.401415Z","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.401415Z"},"links":{"cited_paper":"/paper/1903.12261","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:e2bb7aac893263be0dcbd20f7e74a876fe05d4d9bdd477f0fa2078d56c29a87e","observation_id":"2929d2bf-4900-4cab-9ae4-ff8e901d28db","resolution":{"observed_at":"2026-08-14T12:25:48.401415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.02136","last_updated":"2018-10-03T07:32:57Z","snapshot_observed_at":"2026-08-02T06:41:33.803920Z","submitted_at":"2016-10-07T04:06:01Z","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02136","snapshot_observed_at":"2026-08-14T12:25:48.406185Z","title":"A Baseline for Detecting Misclassified and Out-of- Distribution Examples in Neural Networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.406185Z"},"links":{"cited_paper":"/paper/1610.02136","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:1d609dd20fd1cda6a82f86b9c9a1eaf4c874c02dc7db9a03344fc78baa14d1c6","observation_id":"893f9fc7-be3d-475d-8e7b-db7caffa5e2a","resolution":{"observed_at":"2026-08-14T12:25:48.406185Z","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":"2026-08-14T12:25:49.049022Z","title":"Adversarial Attacks on Neural Network Policies","venue":null,"work_id":"45b0e908-b86b-42f6-b3fe-6434a7dd07c2","year":2017},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.411140Z"},"links":{"citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:cb61831276b131cf55d137b813f56d8799eb84706c804f320233b0b0256838cf","observation_id":"cc834ae8-cd89-438e-b625-ce0e78038a8c","resolution":{"observed_at":"2026-08-14T12:25:49.054549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.11783","last_updated":"2018-10-26T20:32:21Z","snapshot_observed_at":"2026-08-14T19:09:40.184047Z","submitted_at":"2018-05-30T02:48:58Z","title":"To Trust Or Not To Trust A Classifier","version":2},"cited_work":{"arxiv_id":"1805.11783","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.11783","snapshot_observed_at":"2026-08-14T12:25:48.715808Z","title":"To Trust Or Not To Trust A Classifier","venue":"stat.ML","work_id":"ac2f8763-6908-4afa-9ac4-3bf0aed6c018","year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.416048Z"},"links":{"cited_paper":"/paper/1805.11783","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:a36ff44a8e1a2f994fda8423dad506f1bf78da90f715a4309971ddbbb3877b1a","observation_id":"70f81c6c-3ebd-453b-8438-fa0b67906b1c","resolution":{"observed_at":"2026-08-14T12:25:48.721111Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:25:48.421062Z","title":"Imagenet classification with deep convolutional neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.421062Z"},"links":{"citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:67ca29e29ef025cb11df7785c8536bf983c87a1d56b8a74582d89a9d2e8e15eb","observation_id":"5d121341-ea24-4082-ade2-af6d3d5bd8b5","resolution":{"observed_at":"2026-08-14T12:25:48.421062Z","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":"2026-08-14T12:25:48.425515Z","title":"Simple and scalable predictive uncertainty estimation using deep ensembles","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.425515Z"},"links":{"citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:de4c468add77a13cf0e2b63a3a1737af175c1c727c1a2d60f2b129a1301f0b8a","observation_id":"6b941225-1a46-4612-a604-33ceacc05b50","resolution":{"observed_at":"2026-08-14T12:25:48.425515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.09325","last_updated":"2018-02-23T19:42:15Z","snapshot_observed_at":"2026-08-14T20:10:11.251346Z","submitted_at":"2017-11-26T02:50:39Z","title":"Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.09325","snapshot_observed_at":"2026-08-14T12:25:48.430239Z","title":"Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.430239Z"},"links":{"cited_paper":"/paper/1711.09325","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:c6c21528f038de8e164ec97f0a6d9d7162351c68bfd6d55fa6d53bc2939fa962","observation_id":"bf457e21-c82b-4998-94e0-9c93db6559cf","resolution":{"observed_at":"2026-08-14T12:25:48.430239Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03888","last_updated":"2018-10-27T08:47:18Z","snapshot_observed_at":"2026-08-14T18:53:30.254816Z","submitted_at":"2018-07-10T22:14:04Z","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03888","snapshot_observed_at":"2026-08-14T12:25:48.435367Z","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.435367Z"},"links":{"cited_paper":"/paper/1807.03888","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:f85b6b02b037d3d24b0e281ff9c3ca9248e429a6f69c6e61d6cc01dbd5219020","observation_id":"bd20fe0f-6048-4b31-96a1-cd1841c4842e","resolution":{"observed_at":"2026-08-14T12:25:48.435367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.02690","last_updated":"2020-08-30T16:50:36Z","snapshot_observed_at":"2026-08-16T10:30:22.334775Z","submitted_at":"2017-06-08T17:43:56Z","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.02690","snapshot_observed_at":"2026-08-14T12:25:48.440135Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.440135Z"},"links":{"cited_paper":"/paper/1706.02690","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:374f6a36b360494e03010e43ee2860db8604157a03eaaf060ea0932e4ba650c1","observation_id":"466cf5a4-a635-4b92-a765-1cf3bb11e0cf","resolution":{"observed_at":"2026-08-14T12:25:48.440135Z","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":"2026-08-14T12:25:49.010037Z","title":"Predictive uncertainty estimation via prior networks","venue":null,"work_id":"1f93be47-a772-4301-925e-d4d90463cabe","year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.444945Z"},"links":{"citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:cb2932af9ebbcf7fbcb8ea70f108cf23e5e7cb6627e090c2be7a34c7f39fded1","observation_id":"a7e8c525-2735-4402-8b2e-6d6278fc659b","resolution":{"observed_at":"2026-08-14T12:25:49.015274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.09136","last_updated":"2019-02-24T11:57:32Z","snapshot_observed_at":"2026-08-15T00:45:03.614274Z","submitted_at":"2018-10-22T08:32:02Z","title":"Do Deep Generative Models Know What They Don't Know?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.09136","snapshot_observed_at":"2026-08-14T12:25:48.449564Z","title":"Do Deep Generative Models Know What They Don’t Know? arXiv:1810.09136 [cs, stat] , October 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.449564Z"},"links":{"cited_paper":"/paper/1810.09136","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:ac9b7a570e2440d6e44407d64a0f22e8d7a35969695a4f23e5a2009c2405a52c","observation_id":"1f90fcfe-582a-4b1b-a228-1f7605f9a889","resolution":{"observed_at":"2026-08-14T12:25:48.449564Z","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":"2026-08-14T12:25:48.993580Z","title":null,"venue":null,"work_id":"6a7d0a85-8973-4c41-b053-c61114be6f9c","year":2011},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.454813Z"},"links":{"citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:04d45f6832ebab7ed4e97d3d62ffdb0dc383223084d9abec68adc01414cfc0f6","observation_id":"148f44fc-2117-4478-b536-d761572546da","resolution":{"observed_at":"2026-08-14T12:25:48.999157Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:25:48.977046Z","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","venue":null,"work_id":"46f8d131-98a8-4487-88a5-97bf652c6de4","year":2014},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.459337Z"},"links":{"citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:8fa44a590c1cf22d0286189e53cac10b4f8b4ca1f8f6dd27c908121a1e740832","observation_id":"723d866a-d6bc-41dc-9a98-fd8bc13d4b30","resolution":{"observed_at":"2026-08-14T12:25:48.982280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.08440","last_updated":"2018-07-26T10:37:11Z","snapshot_observed_at":"2026-08-14T19:12:38.095663Z","submitted_at":"2018-05-22T08:07:14Z","title":"Classification Uncertainty of Deep Neural Networks Based on Gradient Information","version":2},"cited_work":{"arxiv_id":"1805.08440","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.08440","snapshot_observed_at":"2026-08-14T12:25:48.627081Z","title":"Classification Uncertainty of Deep Neural Networks Based on Gradient Information","venue":"cs.LG","work_id":"79acf698-b102-4dd4-81e8-31cac2fbb442","year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.463719Z"},"links":{"cited_paper":"/paper/1805.08440","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:e20416efb946d354dc3389b1154de3d317e49d91b43f6d570ad3b909cd34ef53","observation_id":"5d74092b-d117-48ea-bda8-d28ea15d522a","resolution":{"observed_at":"2026-08-14T12:25:48.634322Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.03335","last_updated":"2018-11-15T17:53:47Z","snapshot_observed_at":"2026-08-14T19:05:52.758018Z","submitted_at":"2018-06-08T19:47:54Z","title":"Randomized Prior Functions for Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.03335","snapshot_observed_at":"2026-08-14T12:25:48.468296Z","title":"Randomized Prior Functions for Deep Reinforcement Learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.468296Z"},"links":{"cited_paper":"/paper/1806.03335","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:e2f3de3e84dc579e8d27b57128d856126bc3fe0e4ceeac2803074eab1952d962","observation_id":"788a3d0b-ca6e-46c8-a1f7-8ca721d6b06d","resolution":{"observed_at":"2026-08-14T12:25:48.468296Z","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":"2026-08-14T12:25:48.960848Z","title":"Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning","venue":null,"work_id":"458b9d91-6eae-44e9-9857-d98d0819a434","year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.472688Z"},"links":{"citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:2615cc91444b6c7f2335d7b5ea55e3676dcbf52a4cbca5b837e3d4ea770cd721","observation_id":"d3436dad-647b-460a-95ca-3202c3b3c916","resolution":{"observed_at":"2026-08-14T12:25:48.966007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.10811","last_updated":"2019-06-12T17:42:33Z","snapshot_observed_at":"2026-08-14T17:16:40.613707Z","submitted_at":"2019-02-13T20:35:44Z","title":"Do ImageNet Classifiers Generalize to ImageNet?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.10811","snapshot_observed_at":"2026-08-14T12:25:48.477109Z","title":"Do imagenet classifiers generalize to imagenet? arXiv preprint arXiv:1902.10811, 2019","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.477109Z"},"links":{"cited_paper":"/paper/1902.10811","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:b20c9a859ea5061d5e19d1e3d868f6aaabc6cc251c746024ef05a892db158fd6","observation_id":"de9aadba-2a74-45fc-8973-55aea3623196","resolution":{"observed_at":"2026-08-14T12:25:48.477109Z","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":"2026-08-14T12:25:48.482072Z","title":"Berg, and Li Fei-Fei","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.482072Z"},"links":{"citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:9c346e6ac7821c61714bfa5fdb82a7c681f348762b884b5d27076e7047d07ae7","observation_id":"8b3b037b-bf29-4057-b421-fd5c252882a3","resolution":{"observed_at":"2026-08-14T12:25:48.482072Z","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":"2026-08-14T12:25:48.934267Z","title":"Evidential deep learning to quantify classification uncertainty","venue":null,"work_id":"95c91a67-2b7c-4b16-8e98-7dd395d9e62b","year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.486780Z"},"links":{"citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:a8fd326613d05a14f0b9e996428c1341e0a026c5c77c1999cc825eb90f4b50ab","observation_id":"d760329a-7707-43ae-85a2-f80a58349283","resolution":{"observed_at":"2026-08-14T12:25:48.939258Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.05175","last_updated":"2017-06-19T22:48:54Z","snapshot_observed_at":"2026-08-16T08:14:11.802331Z","submitted_at":"2017-03-15T14:31:55Z","title":"Prototypical Networks for Few-shot Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.05175","snapshot_observed_at":"2026-08-14T12:25:48.491783Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.491783Z"},"links":{"cited_paper":"/paper/1703.05175","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:df5086fdc346b7f4d27ac6c5c2b6a49b6b208eabe728f18ea8017b0e16b64b7e","observation_id":"e73a04e4-6777-46c8-9c8f-58711f949089","resolution":{"observed_at":"2026-08-14T12:25:48.491783Z","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":"2026-08-14T12:25:48.917871Z","title":"Inception-v4, Inception- ResNet and the Impact of Residual Connections on Learning","venue":null,"work_id":"e6f16eac-4101-45ad-a433-88583c65d08b","year":2016},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.496750Z"},"links":{"citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:d6da592bff2464b9cd9555d4acaf4a84968bee584fc1191ec7ddec6d9e3f2dbc","observation_id":"e3085aa5-056d-4364-9ac5-687dcb943c8f","resolution":{"observed_at":"2026-08-14T12:25:48.923582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.05666","last_updated":"2018-06-12T14:20:27Z","snapshot_observed_at":"2026-08-14T19:45:29.044910Z","submitted_at":"2018-02-15T17:13:18Z","title":"Adversarial Risk and the Dangers of Evaluating Against Weak Attacks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.05666","snapshot_observed_at":"2026-08-14T12:25:48.502540Z","title":"Adversarial Risk and the Dangers of Evaluating Against Weak Attacks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.502540Z"},"links":{"cited_paper":"/paper/1802.05666","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:ea4cdb8bd93412de7492f61a99a66f47f7083204482deac6e1c3b3f0eaafcf86","observation_id":"290c5cf4-68ba-456f-9787-7d9ba520f866","resolution":{"observed_at":"2026-08-14T12:25:48.502540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.06114","last_updated":"2018-04-14T18:54:19Z","snapshot_observed_at":"2026-08-15T19:29:25.073045Z","submitted_at":"2017-03-10T21:02:53Z","title":"Deep Sets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.06114","snapshot_observed_at":"2026-08-14T12:25:48.507194Z","title":"Deep Sets","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T12:25:48.507194Z"},"links":{"cited_paper":"/paper/1703.06114","citing_paper":"/paper/1908.07235"},"observation_digest":"sha256:a2843e204d2815ab056335b4bafa3ff37468c703f547e50fb455acae8694486d","observation_id":"f413e7a3-02b5-4185-a5e0-2958e3e527f1","resolution":{"observed_at":"2026-08-14T12:25:48.507194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.07235","last_updated":"2019-10-03T06:27:40Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T20:35:12.069244Z","submitted_at":"2019-08-20T09:21:14Z","title":"Density estimation in representation space to predict model uncertainty"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":24,"verified_exact":1,"verified_fuzzy":6},"total_outbound_references":32},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:1908.07235."}