{"as_of":"2026-08-06T18:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e1adbb8de887197077e7b6c758e217d7715dc694ba69d14cc02904210d9e23e1","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T06:33:44.301617Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+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/2606.04656/citation-record","integrity":"/paper/2606.04656/integrity","json":"/paper/2606.04656/citation-record.json","paper":"/paper/2606.04656"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1909.12358","last_updated":"2019-09-26T19:48:16Z","snapshot_observed_at":"2026-07-06T08:25:01.425019Z","submitted_at":"2019-09-26T19:48:16Z","title":"Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving","version":1},"cited_work":{"arxiv_id":"1909.12358","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1909.12358","snapshot_observed_at":"2026-07-02T07:56:47.231786Z","title":"Can we trust you? on calibration of a probabilistic object detector for autonomous driving,","venue":null,"work_id":"bdd00dd3-c984-49f0-b26b-e51d67ba1283","year":1909},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"cited_paper":"/paper/1909.12358","citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:d6e2703a31cf84bf1f2f9e9684c9ed7f55016637e0994311f3ef7471e0d53e4a","observation_id":"0a555014-7bc9-48b0-b67c-14f2b2f596dc","resolution":{"observed_at":"2026-07-02T07:56:47.233780Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07263","last_updated":"2024-07-30T11:31:31Z","snapshot_observed_at":"2026-08-06T02:46:03.050629Z","submitted_at":"2024-03-12T02:45:24Z","title":"Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction","version":2},"cited_work":{"arxiv_id":"2403.07263","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.07263","snapshot_observed_at":"2026-07-02T07:56:47.225518Z","title":"Adaptive bounding box uncertainties via two-step conformal prediction,","venue":null,"work_id":"4eb0a429-b146-4db4-a1c2-d53fcda7b51d","year":2024},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"cited_paper":"/paper/2403.07263","citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:b8221d167b90112e20ce39298a002d30c140818b4cb8df5fd11807fc0821d6d2","observation_id":"3a60323e-3dc9-488c-a711-3fea56c78680","resolution":{"observed_at":"2026-07-02T07:56:47.227055Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-28T06:33:44.301617Z","title":"Estimating and evaluating regression predictive uncertainty in deep object detectors,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:9391fdab9f9b64337920a66e3c1680b33621cdce7cada5d0244c8aa12040de86","observation_id":"fd6e2fba-5dfe-47f9-aa7e-9fb7ee216050","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Laplace approximation based epistemic uncertainty estimation in 3d object detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:8e7a10a1d9d01a93e572d56a8f7769531072d745469f0b6d80e5a75dad257cbd","observation_id":"78dfea7a-3f4c-436f-a7c6-da83e81c10b4","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Improving predictions of bayesian neural nets via local linearization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:404aff28b5eb38b90fd4cb2f95d0090acc1b566bb4bf6656dee5cfe08c3799a6","observation_id":"e55c6018-ad35-442c-8606-2ad30d1c87db","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"A survey of uncertainty in deep neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:d1e9bec2693f7d496b47aaa9996b03ecde22bf0864bf47410f2f5e5bfd89d6e7","observation_id":"da74bc4b-daa6-4429-8c96-fe847dd9af3a","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.02158","last_updated":"2016-01-18T20:42:07Z","snapshot_observed_at":"2026-07-06T04:20:07.263346Z","submitted_at":"2015-06-06T14:43:40Z","title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","version":6},"cited_work":{"arxiv_id":"1506.02158","doi":null,"metadata_source":"pith","pith_arxiv_id":"1506.02158","snapshot_observed_at":"2026-07-02T07:56:47.223364Z","title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","venue":"stat.ML","work_id":"9f3dac92-e7cd-4795-8405-f418b37cec31","year":2015},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"cited_paper":"/paper/1506.02158","citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:aa3c04200e4d39a0b6ed74f8c7a02c4ea11d42bee3d636071d4c41e206247352","observation_id":"d9fd8968-975e-468f-b8e7-92f2db0319bb","resolution":{"observed_at":"2026-07-02T07:56:47.224467Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-28T06:33:44.301617Z","title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:9f898b4b60c17aca41b0e151ca84c03b589e1e7e390fd0080991dbc708b609cd","observation_id":"4e977e68-00c6-41d9-9a96-7c02acc39a5d","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Practical variational inference for neural networks,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:fef2e895a841ed7e0e28ea2ffff62fb0e6d90c131e7fed634f3d1da9a070c673","observation_id":"d9d2510a-baa4-4c29-9e7e-d2fb77c956e4","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Structured and efficient variational deep learning with matrix gaussian posteriors,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:bb568e1f6d165b6b5d6ac7d7e5e2667c397c43eac0aa24ed6840d22e5535aedb","observation_id":"2c78d205-f6c3-428a-be85-6bfc2b5933b3","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Learning structured weight uncertainty in bayesian neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:35c093290cd2a6352551bd71e645aa7f77b263c248ab04c91b086eba5e48915f","observation_id":"d1bede56-21b8-4abe-be1c-7da3e13264da","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12565","last_updated":"2018-11-30T01:12:51Z","snapshot_observed_at":"2026-08-04T22:57:46.047329Z","submitted_at":"2018-11-30T01:12:51Z","title":"Eigenvalue Corrected Noisy Natural Gradient","version":1},"cited_work":{"arxiv_id":"1811.12565","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.12565","snapshot_observed_at":"2026-07-02T07:56:47.227715Z","title":"Eigenvalue Corrected Noisy Natural Gradient","venue":"cs.LG","work_id":"0ecc399e-9c8c-4169-afda-b7829ea9b32f","year":2018},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"cited_paper":"/paper/1811.12565","citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:c90c18b25c64216b350b9162936690da6957069c76c10fbf971a321276267058","observation_id":"5858052f-7d7e-4a21-8449-4b72ed32f04d","resolution":{"observed_at":"2026-07-02T07:56:47.230383Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-28T06:33:44.301617Z","title":"Practical deep learning with bayesian principles,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:e56fa56370f8def135a61648550009df9391c8bdb3226d3027b1ea1d8c1af707","observation_id":"4675ad83-09ea-4ef3-b014-087269956405","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Bayesian model comparison and backprop nets,","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:5761e2e35d4b48209db7dca6c21ac2513bd8da810bc8bcd1adfb0463bcd99f97","observation_id":"dac14744-5ebf-485d-97be-323e74f76e95","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Optimizing neural networks with kronecker-factored ap- proximate curvature,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:c9dd9c5e6326bc8f81724cd20cfdd6f0708f784b7bc2751e35305f85fdcf156c","observation_id":"9762496d-8c50-49b1-bab1-1ab233ca4e22","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Fast approximate natural gradient descent in a kronecker factored eigenbasis,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:5dea82f2b57f0d88c0a46c08fea3c0a46517920a15a6169066be674ead3509d9","observation_id":"0c6c267f-694a-4599-a352-4d32c40f68eb","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Estimating model uncertainty of neural networks in sparse information form,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:d26eb47bfe9caa0d991974d92133b4cc4ef2c34b8fdf3593b31770389911f663","observation_id":"cde27b5a-571d-41ff-960c-7ea43f0b0d41","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Simple and scalable predictive uncertainty estimation using deep ensembles,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:524022180318b5886b4b82a8bf76fa300421ed3cdfa699262b4299ba26af780f","observation_id":"ab23f1b7-bc58-4b57-b6d2-63acfa6a0dc7","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Hyperparameter ensembles for robustness and uncertainty quantification,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:b33ea875ef3186eef270be1c098c1e650337223d5866f1132006d7838b56749c","observation_id":"f6c0c0c2-55f6-43ed-b421-f7d224efc4b0","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Autoregressive uncertainty modeling for 3d bounding box prediction,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:c2685ffcd49a8a0a3b0280882500d57a599bbf6b03bb6dfbe03a6b5fdff1a0bf","observation_id":"f16363ed-2764-4c61-b68b-c762658274c1","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Bayesod: A bayesian approach for uncertainty estimation in deep object detectors,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:c06471dd849133607e203e3e38834d592cce4e47531542773d2dbcf31a741792","observation_id":"6e4b1c71-5756-46fb-b164-e8556d5aee5c","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.03614","last_updated":"2021-08-08T11:34:37Z","snapshot_observed_at":"2026-08-03T19:18:06.840997Z","submitted_at":"2021-08-08T11:34:37Z","title":"Monte Carlo DropBlock for Modelling Uncertainty in Object Detection","version":1},"cited_work":{"arxiv_id":"2108.03614","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.03614","snapshot_observed_at":"2026-07-02T07:56:47.215167Z","title":"Monte carlo dropblock for modelling uncertainty in object detection,","venue":null,"work_id":"a62aaaf8-ad73-4027-98dc-a36cb3a8beee","year":2021},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"cited_paper":"/paper/2108.03614","citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:0b13e592481f822749bb4da8faa1bec3c246fa4f0595f71e7ed80dbd4113ca45","observation_id":"228c05c5-82d3-4ed7-8b08-f738426d91da","resolution":{"observed_at":"2026-07-02T07:56:47.218820Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-28T06:33:44.301617Z","title":"Probabilistic object detection via deep ensembles,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:c6d63f71951caea223e61ea5b6bae6898e8e885a35398890b6f08a96809863bd","observation_id":"97b402c9-cb5d-4947-a038-1cca7d6c40a2","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Laplace approximation for real-time uncertainty estimation in object detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:563bbfdc79244309399bdb7cbaee856b802f4bc4a2993ba3ee3da7d6c8fef9c0","observation_id":"388b90dd-7a36-4861-83c6-3077ca080fe1","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"Deep evidential regression,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:c8dab4894382b3558d7cc3cd37f81cd284c708729763690e1a80287fc4ac85ad","observation_id":"37b9a5e0-d66a-419c-b7c3-310a7f843e8f","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12709","last_updated":"2019-03-23T17:00:28Z","snapshot_observed_at":"2026-07-06T07:18:12.164021Z","submitted_at":"2018-11-30T10:41:31Z","title":"Evaluating Bayesian Deep Learning Methods for Semantic Segmentation","version":2},"cited_work":{"arxiv_id":"1811.12709","doi":null,"metadata_source":"pith","pith_arxiv_id":"1811.12709","snapshot_observed_at":"2026-07-02T07:56:47.220366Z","title":"Evaluating Bayesian Deep Learning Methods for Semantic Segmentation","venue":"cs.CV","work_id":"707f59f9-82fa-4f91-a9c6-ff3d35481329","year":2018},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"cited_paper":"/paper/1811.12709","citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:197a3788f7b1ef2b2cfac16cf6a2bba5ed968f11b5096d0f0ee085a8c1143f73","observation_id":"1236640d-9096-4130-8273-8af782759188","resolution":{"observed_at":"2026-07-02T07:56:47.221587Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-06-28T06:33:44.301617Z","title":"Center-based 3d object detection and tracking,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:d8f7af7ac07095911d924ff30cd910c8e092acbe45479bfd951386c712eecf23","observation_id":"9e6091ff-72a9-464f-8c98-f2975dc9e81b","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","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":"2026-06-28T06:33:44.301617Z","title":"nuscenes: A multimodal dataset for autonomous driving,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-28T06:33:44.301617Z"},"links":{"citing_paper":"/paper/2606.04656"},"observation_digest":"sha256:bf5964152e595334e174530dbe11d01487bfb18ff82bc930c2fff8fb4a123304","observation_id":"0e50a8e6-1643-4d2a-9ba2-5e30d3d86fd4","resolution":{"observed_at":"2026-06-28T06:33:44.301617Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.04656","last_updated":"2026-06-03T09:26:13Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T16:47:39.058636Z","submitted_at":"2026-06-03T09:26:13Z","title":"Instance-Level Post Hoc Uncertainty Quantification in Object Detection"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":6,"verified_fuzzy":0},"total_outbound_references":28},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2606.04656."}