{"as_of":"2026-08-18T14:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:78d31fb1cfb3324d0a02dc31b032b7fc49fc69ee13fe42a9bb628913a6734b92","coverage":[{"denominator":121,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T00:21:57.318142Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2608.12100/citation-record","integrity":"/paper/2608.12100/integrity","json":"/paper/2608.12100/citation-record.json","paper":"/paper/2608.12100"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:21:56.760203Z","title":"Conformal prediction: A gentle introduction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.760203Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:2c54e723da6ca2d2fbe00482779686ad1a8e21f3c9f1c11a55721b31f3c6a45f","observation_id":"8cdbcfdd-aeb0-4bce-aa8f-4066c286ce8b","resolution":{"observed_at":"2026-08-16T00:21:56.760203Z","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":"2026-08-16T00:21:56.767520Z","title":"Uncertainty sets for image classifiers using conformal prediction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.767520Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:1586ecb6bd31f0a32f2f05c1cac92996fb047f354160317c3a99f32a574bf01b","observation_id":"35815592-93e4-4624-9dfe-918e013cd8a8","resolution":{"observed_at":"2026-08-16T00:21:56.767520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.06202","last_updated":"2024-03-03T06:47:19Z","snapshot_observed_at":"2026-08-18T09:36:04.875290Z","submitted_at":"2021-02-11T18:59:11Z","title":"Private Prediction Sets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.06202","snapshot_observed_at":"2026-08-16T00:21:56.777942Z","title":"Private prediction sets","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.777942Z"},"links":{"cited_paper":"/paper/2102.06202","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:c5c014361687e072770588d55e457237c144b25441c70a688eb526afd4ff45bc","observation_id":"c1992653-9f8d-4b8d-a05f-d4f69b561042","resolution":{"observed_at":"2026-08-16T00:21:56.777942Z","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":"2026-08-16T00:21:56.784944Z","title":"Learning with privacy at scale, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.784944Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:bc93b8d4873391d8c0259369d6607925f5e235956b094da388b59132f203b679","observation_id":"92c3d1df-a4e1-4201-8436-19822f1c9bf3","resolution":{"observed_at":"2026-08-16T00:21:56.784944Z","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":"2026-08-16T00:21:56.791206Z","title":"Private learning and sanitization: Pure vs","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.791206Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:269c29aa0ceb52ee7859d9f3d21998fabd71bbd96aff0b59dbc5a305589283a7","observation_id":"7789e54d-e31c-4b33-a1a6-2e42149a2acf","resolution":{"observed_at":"2026-08-16T00:21:56.791206Z","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":"2026-08-16T00:21:56.797370Z","title":"Training deep neural-networks based on unreli- able labels","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.797370Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:337ba04232d20f579a167e2fd972b32b79bcb2c2f5ed25c203aab166a91d2728","observation_id":"a79dffea-a79d-410d-bd04-1f3ffa8ee948","resolution":{"observed_at":"2026-08-16T00:21:56.797370Z","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":"2026-08-16T00:21:56.803005Z","title":"Verification of forecasts expressed in terms of probability.Monthly Weather Review, 78(1):1–3, 1950","venue":null,"work_id":null,"year":1950},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.803005Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:8dff1db5313eb5939ff195ce1fdb1bd81d742c11e38b4379515e8d66b79430f7","observation_id":"073c2d31-6ec5-4dae-8312-3a6f731baede","resolution":{"observed_at":"2026-08-16T00:21:56.803005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.02822","last_updated":"2023-03-27T11:53:17Z","snapshot_observed_at":"2026-08-18T12:12:05.056885Z","submitted_at":"2022-01-08T12:49:27Z","title":"AnomMAN: Detect Anomaly on Multi-view Attributed Networks","version":2},"cited_work":{"arxiv_id":"2201.02822","doi":null,"metadata_source":"pith","pith_arxiv_id":"2201.02822","snapshot_observed_at":"2026-08-16T00:21:57.719865Z","title":"AnomMAN: Detect Anomaly on Multi-view Attributed Networks","venue":"cs.SI","work_id":"09510526-ea05-44f8-8131-4be2524fcf5c","year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.808527Z"},"links":{"cited_paper":"/paper/2201.02822","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:dd601668999a1d77aa1202e6c531aac7a2b3b1c94e255edaeac14590a466dd1d","observation_id":"2dad4406-c6d8-425f-8092-7977137a975c","resolution":{"observed_at":"2026-08-16T00:21:57.731183Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:21:56.814569Z","title":"Noise against noise: stochastic label noise helps combat inherent label noise","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.814569Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:4998af46d2c1799b0cdb7da117388bd07d517059ef8b645e06cea2f2c6eb48bf","observation_id":"b75caa72-faf9-4386-a8ee-7eb477d37f51","resolution":{"observed_at":"2026-08-16T00:21:56.814569Z","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":"2026-08-16T00:21:56.818987Z","title":"Instance-dependent label-noise learning with manifold-regularized transition matrix estimation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.818987Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:d233f1a5d0a5229bda4115ed768c9f8096de319a345df095c549eeb9ef5488bf","observation_id":"26cc1e37-59ef-440c-8085-419705859bf2","resolution":{"observed_at":"2026-08-16T00:21:56.818987Z","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":"2026-08-16T00:21:56.823993Z","title":"Learning with instance-dependent label noise: A sample sieve approach","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.823993Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:15b03c82f8139cd7729c410a28a6db45e15346fb4c176a6c90dc80b30edfa71f","observation_id":"1c033d79-f0ed-4e84-84b3-da61acaafd39","resolution":{"observed_at":"2026-08-16T00:21:56.823993Z","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":"2026-08-16T00:21:56.828276Z","title":"Differential privacy in the shuffle model: A survey of separations, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.828276Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:8360e624cea2b87eb4e038da87cd8c3387fc134491a991376dfca636862b649e","observation_id":"2465f15e-5bfd-4c75-9c4d-d876ddf2f147","resolution":{"observed_at":"2026-08-16T00:21:56.828276Z","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":"2026-08-16T00:21:56.832417Z","title":"Split conformal prediction under data contamination","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.832417Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:56b01d6da74f9d9152065d5855eb33a91fe5ca5fc69913a42f2b57f74f33fb97","observation_id":"5d4c7da8-cc9d-435b-a996-bd29d759b644","resolution":{"observed_at":"2026-08-16T00:21:56.832417Z","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":"2026-08-16T00:21:56.837165Z","title":"Towards discriminability and diversity: Batch nuclear-norm maximization under label insufficient situa- tions","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.837165Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:dbc1e33a3e1e2016fbe0e422d452fa3b9653f78def0056e3fb8a03a6d44a1d58","observation_id":"a6d94616-50ac-4bd9-ab89-0ad1b0fd2d56","resolution":{"observed_at":"2026-08-16T00:21:56.837165Z","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":"2026-08-16T00:21:56.843434Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.843434Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:49c6c7f941c03f34487adf4448aba254c7c2a52659631f9969ef1abec60e2c73","observation_id":"78d0afca-da10-4135-86ef-7ecbc2e10e26","resolution":{"observed_at":"2026-08-16T00:21:56.843434Z","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":"2026-08-16T00:21:56.847913Z","title":"Are labels always necessary for classifier accuracy evaluation? In Proc","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.847913Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:f9f47a2d3c78ea16124e727a7ff1900144ca1f121340a26f0f2e6a33e49f2486","observation_id":"077222a3-c620-40d9-9289-a4d9a13e92c8","resolution":{"observed_at":"2026-08-16T00:21:56.847913Z","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":"2026-08-16T00:21:56.852523Z","title":"Training a neural network based on unreliable human annotation of medical images","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.852523Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:9c0f5b4eda176416eecc6f3f7d53e897cc4e66788f240114ab4af105a1b7a61a","observation_id":"08c0701d-40fd-4264-b3b0-d603ae8cb66f","resolution":{"observed_at":"2026-08-16T00:21:56.852523Z","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":"2026-08-16T00:21:56.857416Z","title":"Dowson and B","venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.857416Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:638f6c3253a35cd7a0d25f4f354e6630a08f86e23cbea27833aa5fcb4c779a58","observation_id":"97c551c3-03d6-4c41-bfc3-ce68d74fac17","resolution":{"observed_at":"2026-08-16T00:21:56.857416Z","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":"2026-08-16T00:21:56.862268Z","title":"Local privacy and statistical minimax rates","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.862268Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:9cef6d5452beeb9f36939be0ccc346ac3b7f5cebd8e360726b574b587102803f","observation_id":"cc205d19-6032-40a6-9f4d-8f80766d11e8","resolution":{"observed_at":"2026-08-16T00:21:56.862268Z","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":"2026-08-16T00:21:56.867270Z","title":"Differential privacy","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.867270Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:bea9beb8c3fd6bff0a2461f5bd56a443f80d7618ae6dc69312600fd99bb40a8b","observation_id":"1ef2f4e9-e98a-4054-a3c4-c59cefab937f","resolution":{"observed_at":"2026-08-16T00:21:56.867270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.14295","last_updated":"2024-11-26T07:18:47Z","snapshot_observed_at":"2026-08-16T16:29:08.438226Z","submitted_at":"2022-09-28T17:59:35Z","title":"Label Noise Robustness of Conformal Prediction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.14295","snapshot_observed_at":"2026-08-16T00:21:56.871626Z","title":"Conformal prediction is robust to label noise","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.871626Z"},"links":{"cited_paper":"/paper/2209.14295","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:98ca3cae47915baac1f33d457005451d075e3ee351d2d8a25c5070b8f201f8a0","observation_id":"07b52af0-1b32-4283-86af-abbe6defc2f3","resolution":{"observed_at":"2026-08-16T00:21:56.871626Z","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":"2026-08-16T00:21:56.877951Z","title":"Rappor: Randomized aggregatable privacy-preserving ordinal response","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.877951Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:aa05c62ab55e6e30058c9cfdd9faf04a13c25e2daa0d40ade5e613efc75f23d3","observation_id":"efeaeecb-1d15-472a-8dc2-448be803ea43","resolution":{"observed_at":"2026-08-16T00:21:56.877951Z","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":"2026-08-16T00:21:56.883472Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.883472Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:24b8d21ee41d122c2683f89066d5e35481894bb97e2cd875ef8f3e5eb49557ab","observation_id":"70670268-a672-4577-86ef-92d60d835151","resolution":{"observed_at":"2026-08-16T00:21:56.883472Z","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":"2026-08-16T00:21:56.889260Z","title":"The limits of distribution-free conditional predictive inference.Information and Inference: A Journal of the IMA, 10(2):455–482, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.889260Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:48e89bcf5ec1cb04084c0c5662f6058c52cd3bc87d175f660788ead960e4046f","observation_id":"83c90485-39b4-4c85-9901-9c54344b7a9f","resolution":{"observed_at":"2026-08-16T00:21:56.889260Z","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":"2026-08-16T00:21:56.895560Z","title":"Calibration of medical imaging classification systems with weight scaling","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.895560Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:a59ef3801b178b4002111c39f2992798943065ddd2f10f2e6841c6c906f59a66","observation_id":"4b885a0a-ccf3-49b8-8526-9a7a0034ad39","resolution":{"observed_at":"2026-08-16T00:21:56.895560Z","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":"2026-08-16T00:21:56.901374Z","title":"Locally private mean estimation: Z-test and tight confidence intervals, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.901374Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:bcdb13a77a401475fba15552a756ffe4300c4d8c259f658219ef2b6ebdc832d4","observation_id":"114bb003-8890-45b7-9389-0caf59bc10f8","resolution":{"observed_at":"2026-08-16T00:21:56.901374Z","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":"2026-08-16T00:21:56.907117Z","title":"Domain-adversarial training of neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.907117Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:58224acad968302a18c5c2f0374ddb1b18bf5bdc6482a7b98b0b6434f243c14d","observation_id":"e4bd1b57-d51b-4266-bfb4-7e9c71b82356","resolution":{"observed_at":"2026-08-16T00:21:56.907117Z","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":"2026-08-16T00:21:56.912157Z","title":"Leveraging unlabeled data to predict out-of- distribution performance","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.912157Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:0869c6f63389139821ae8966182df45024496f3b06a0e50c9e546014570ef127","observation_id":"aa15c0d5-4a6e-426b-a33c-dfb2ac318e21","resolution":{"observed_at":"2026-08-16T00:21:56.912157Z","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":"2026-08-16T00:21:56.917611Z","title":"Deep learning with label differential privacy.Advances in Neural Information Processing Systems (NeurIPs), 34:27131–27145, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.917611Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:7f7012e81b8e2c4cd555b17b32c7bbc82a7d8429955cbd055c838c2393499b0c","observation_id":"9d2af7c9-96ea-430b-9cd3-9709394a94a0","resolution":{"observed_at":"2026-08-16T00:21:56.917611Z","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":"2026-08-16T00:21:56.922380Z","title":null,"venue":null,"work_id":null,"year":1919},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.922380Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:6c60d82c76386c4cc12f6bd2aa67ed75a6f064f9e209da6ebd140ff772267733","observation_id":"fef20b20-0e62-49c4-bef6-90782f9bcb0c","resolution":{"observed_at":"2026-08-16T00:21:56.922380Z","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":"2026-08-16T00:21:56.927386Z","title":"Training deep neural-networks using a noise adap- tation layer","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.927386Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:19282c5ceae363621f49fc9fc15fc41f6c6eb0f337bd9e489d18ae228d36c44a","observation_id":"6563ee15-062b-4e0c-ae16-41078b0f5479","resolution":{"observed_at":"2026-08-16T00:21:56.927386Z","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":"2026-08-16T00:21:56.932464Z","title":"Pre- dicting with confidence on unseen distributions","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.932464Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:57d18907d5552ad7e45b9da6ac9090d06ecab0acda45db4a7221bcb8ddbe50d8","observation_id":"3ce1931c-db32-411f-92f5-daec16f08dd0","resolution":{"observed_at":"2026-08-16T00:21:56.932464Z","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":"2026-08-16T00:21:56.937032Z","title":"On calibration of modern neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.937032Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:198f7ef975b8947a00e04942eac7b79ca0975cd1b339dc5dd1d92aa787812981","observation_id":"3d48323f-868b-47ab-a87b-2a549794a765","resolution":{"observed_at":"2026-08-16T00:21:56.937032Z","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":"2026-08-16T00:21:56.941912Z","title":"Deep self-learning from noisy labels","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.941912Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:1b9dd9f11c4d31e6707587c07c2c7a0a9a55bdef0346485a663bf35edbc5cf6e","observation_id":"08103340-aa45-4142-940a-c19ec982ec85","resolution":{"observed_at":"2026-08-16T00:21:56.941912Z","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":"2026-08-16T00:21:56.947829Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.947829Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:71d9148e6b580459c0c4275af30f88b7ddbeb8e179d443fc379b6a40221f0b5f","observation_id":"a4fd0e05-6491-49b2-95e8-9249100f2404","resolution":{"observed_at":"2026-08-16T00:21:56.947829Z","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":"2026-08-16T00:21:56.952705Z","title":"Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.952705Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:33e38951bafbffd7f28f6c9b6460922eb2d3f75807decf6eef15147ed3773262","observation_id":"06be17e7-9e68-4170-b0c6-c7a6296b4559","resolution":{"observed_at":"2026-08-16T00:21:56.952705Z","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":"2026-08-16T00:21:56.957496Z","title":"Using trusted data to train deep networks on labels corrupted by severe noise","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.957496Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:f0065c88e723566cf70e1b582c40f887b0ae74811c4cff8a932eb131740a265f","observation_id":"6a3273ff-14a8-4aba-9631-aaa47488b5f8","resolution":{"observed_at":"2026-08-16T00:21:56.957496Z","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":"2026-08-16T00:21:56.962531Z","title":"Simple and effective regularization methods for training on noisily labeled data with generalization guarantee","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.962531Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:99833d88d5b7fe3f85aaab103c95de83610e3efc60f3593b1152318c325da93f","observation_id":"5d337606-8931-4421-b9a6-1417e6289030","resolution":{"observed_at":"2026-08-16T00:21:56.962531Z","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":"2026-08-16T00:21:56.967769Z","title":"Densely con- nected convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.967769Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:3b538b94a67f81054a934e48ea5d67ae783b02392a6d90cc9e33c1186eb396e5","observation_id":"06978f0f-194d-4fce-bf8b-987d410c8d8b","resolution":{"observed_at":"2026-08-16T00:21:56.967769Z","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":"2026-08-16T00:21:56.973666Z","title":"O2u-net: Asimplenoisylabeldetection approachfordeepneuralnetworks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.973666Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:948123fa17c959013e4816e2ea438125b30b49b4c27d658d7de8b4f877f600aa","observation_id":"9f047908-eb9d-4824-97c9-c3b293b233ac","resolution":{"observed_at":"2026-08-16T00:21:56.973666Z","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":"2026-08-16T00:21:56.978985Z","title":"Uncertainty-aware learning against label noise on imbalanced datasets","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.978985Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:407afbd431ce527b1e518a727ccf1d6af33f95f32f9c5d232a30b41d8c135ddf","observation_id":"47abc4dd-8002-47d4-bd2e-63096a8cd80c","resolution":{"observed_at":"2026-08-16T00:21:56.978985Z","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":"2026-08-16T00:21:56.983818Z","title":"Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.983818Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:03aa4e7af19ff21249f0091cf4c9ecc414e6ebc520a17529ce79f9afde55c26e","observation_id":"0e749943-0d39-4ddc-a8fe-e9ee1f089428","resolution":{"observed_at":"2026-08-16T00:21:56.983818Z","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":"2026-08-16T00:21:56.988884Z","title":"Delving into sample loss curve to embrace noisy and imbalanced data","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.988884Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:03e2a1f5da5eb7e1d8169e1ab631ae5b212e93c9c7f192a9e809af1495587eaf","observation_id":"a85a1763-db89-41df-98c3-461a63b13ec8","resolution":{"observed_at":"2026-08-16T00:21:56.988884Z","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":"2026-08-16T00:21:56.992782Z","title":"Minimum class confusion for ver- satile domain adaptation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.992782Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:777a07c558af98e5391ce64890438efd5a1365c75674d51d108bc26da4aea8f1","observation_id":"c30158e3-f4af-4866-a100-ffab326ea9e2","resolution":{"observed_at":"2026-08-16T00:21:56.992782Z","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":"2026-08-16T00:21:59.012156Z","title":"Discrete distribution estimation under local privacy","venue":null,"work_id":"7650c2b9-0124-49a5-aee2-f8e5bf978d23","year":2016},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:56.996999Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:3e04042ce1ca080277ac6030297a9f7c0bf01b64ac392269ae7d5041afad7164","observation_id":"99862c7e-7289-4396-8898-ba0a8990c726","resolution":{"observed_at":"2026-08-16T00:21:59.017000Z","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":"2026-08-16T00:21:58.995992Z","title":"What can we learn privately?SIAM Journal on Computing , 40(3):793–826, 2011","venue":null,"work_id":"edf17c32-618c-49c0-bb90-7e31fadda7b4","year":2011},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.001564Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:1c21041626c57db5aaf31f011717ade1161c55cf94f6ac71d93d9fba18ba29ef","observation_id":"ceef08ae-235b-4df8-ad84-01664a31c3b2","resolution":{"observed_at":"2026-08-16T00:21:59.001547Z","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":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-16T00:21:57.007985Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.007985Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:e8d97a2714bb3b7a361ff4f25450b48b45e4a187157d733eaea88c733ae405ab","observation_id":"c6c741a9-55f1-4de4-a499-226766d93265","resolution":{"observed_at":"2026-08-16T00:21:57.007985Z","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":"2026-08-16T00:21:57.013625Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.013625Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:d54e46a977bd43c0e907c20962640249f7bc4b24007b575fb99eaaf64e0c3ca0","observation_id":"62ba38f7-540f-4e73-88dc-c0d50a475ee5","resolution":{"observed_at":"2026-08-16T00:21:57.013625Z","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":"2026-08-16T00:21:58.966037Z","title":"Simple and scalable pre- dictive uncertainty estimation using deep ensembles","venue":null,"work_id":"5433e5e2-1360-402e-a7d4-c6f847a65151","year":2017},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.020703Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:9cc8993fbb701b7cf0e1cf050bd06811dcc7cecf9ccbca745e2f21b2c8e6030e","observation_id":"a8bb66c5-d3d0-4bdb-aa1c-67053688f8b4","resolution":{"observed_at":"2026-08-16T00:21:58.970702Z","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":"2026-08-16T00:21:58.947405Z","title":"Coupled-view deep classifier learning from multiple noisy annotators","venue":null,"work_id":"d51d1c54-3193-4e33-a1b2-1263181ef2cd","year":2020},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.025893Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:1446ead30d3f46380ad6ecf9a4a9c4be23218e8a0bcab02568b7f6c9e3d532c2","observation_id":"df84e6e9-546a-478f-8630-8a4819b4e0dd","resolution":{"observed_at":"2026-08-16T00:21:58.953113Z","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":"2026-08-16T00:21:58.929608Z","title":"Trustable co-label learning from multiple noisy annotators.IEEE Transactions on Multimedia , 25:1045–1057, 2021","venue":null,"work_id":"ffc1c9d6-82b7-43e9-b8af-ebd548edb46e","year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.031658Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:c87d1d5237bf4ae9eeb0e23a3572f7bd4e4b552f06f2b5afc8122126aba31d14","observation_id":"4abcec2f-5523-4d89-8563-0ff9e6f72368","resolution":{"observed_at":"2026-08-16T00:21:58.935734Z","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":"2026-08-16T00:21:58.910412Z","title":"Provably end-to-end label-noise learning without anchor points","venue":null,"work_id":"ddfbf508-fe9a-4bca-9a67-044c2112aab0","year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.038495Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:6e4ac4deaa3ce4f8cd305add7bc09c451663e8a040babecabc53ae6d6b79fb2b","observation_id":"5efeca0c-3787-480d-a88d-51081aa7726c","resolution":{"observed_at":"2026-08-16T00:21:58.915713Z","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":"2026-08-16T00:21:58.891336Z","title":"Domain adaptation with auxiliary target domain- oriented classifier","venue":null,"work_id":"b0f285c4-c99d-49fa-9624-57897b32e593","year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.043183Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:c28bba7bbc100a1127b51fa07412fced653f6cee050b5db1996f991afbe7693c","observation_id":"29cce41a-ab31-456d-b65b-d0b22f5a2c90","resolution":{"observed_at":"2026-08-16T00:21:58.897885Z","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":"2026-08-16T00:21:58.866065Z","title":"A holistic view of label noise transition matrix in deep learning and beyond","venue":null,"work_id":"76171c2e-987c-4bc4-bf6d-84c1285a7818","year":2023},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.048726Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:0478428e1d527b10b37e3e197db72c204cbeb5f3fff91e80f521989c30cf50ab","observation_id":"d46f2699-13a2-4696-8f34-5fb22c06d565","resolution":{"observed_at":"2026-08-16T00:21:58.872899Z","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":"2026-08-16T00:21:58.843847Z","title":"Classification with noisy labels by importance reweighting","venue":null,"work_id":"9aabd0c5-8b8a-4a9a-8849-bf1528602ecc","year":2015},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.054410Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:5e5d18d5e5865a1209f7dfb8448cd41f4f20a3bb202b43bcfa761ca1b046c002","observation_id":"42f2a3c2-c3de-41dd-9153-cdb5c4e6437e","resolution":{"observed_at":"2026-08-16T00:21:58.849626Z","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":"2026-08-16T00:21:58.824210Z","title":"Conditional adversarial domain adaptation","venue":null,"work_id":"6aa90f97-b412-4a65-828f-23a24f34d631","year":2018},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.060651Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:49e13ae5f0b5a5d1b83f2902dab2bc99fe3d5e2d3f3b2e1cc65738309ec1a309","observation_id":"e8f8d84b-a28b-42f3-9ee0-b2b7ece868dc","resolution":{"observed_at":"2026-08-16T00:21:58.829800Z","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":"2026-08-16T00:21:58.805327Z","title":"Improving trustworthiness of AI disease severity rating in medical imaging with ordinal conformal prediction sets","venue":null,"work_id":"ce18c7a2-055b-46e3-922f-188608e31223","year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.066363Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:9923a3f4e4c0f2c761bc5cb968e3231cc7beabdad50831175ccdbabf38bec6e6","observation_id":"88a7c63c-a34f-4c9a-b77d-64a016e2b9dc","resolution":{"observed_at":"2026-08-16T00:21:58.812677Z","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":"2026-08-16T00:21:58.787970Z","title":"Fair conformal predictors for applications in medical imaging","venue":null,"work_id":"97b01e48-085e-4697-b901-89a0951ac876","year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.071865Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:2eb04cd0a6a8a8ca20d1868310b09539b0f2690a5627f8e9824e4ab639974d08","observation_id":"2d5e2459-b4d6-41ee-b050-18fa20d659e3","resolution":{"observed_at":"2026-08-16T00:21:58.792812Z","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":"2026-08-16T00:21:58.772117Z","title":"Label-noise learning with intrinsically long-tailed data.arXiv e-prints, pages arXiv–2208, 2022","venue":null,"work_id":"b63613fc-5954-4ac4-bb77-a151adb9b9e7","year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.077543Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:a03869be31edc424152b36c71f2aab5de92a68639a8bda58fc70e6feef14d1a6","observation_id":"5e76b7a0-5d16-4408-aa98-02b5025467ae","resolution":{"observed_at":"2026-08-16T00:21:58.777306Z","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":"2026-08-16T00:21:57.084370Z","title":"The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality.The Annals of Probability, pages 1269–1283, 1990","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.084370Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:f1bfca6521757c8c591fc1c7037881fcb829f3b60df0c996bfd44872e21f5e45","observation_id":"dd562fb1-447f-465e-9f3a-870a162ef804","resolution":{"observed_at":"2026-08-16T00:21:57.084370Z","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":"2026-08-16T00:21:58.746288Z","title":"Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization","venue":null,"work_id":"7e4f1bcf-6baa-486f-b59a-4def19de6e6e","year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.090808Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:d88673092e4a52f4401b570e1415f09de4e35bcbcdaba5b93a1dbb3d595d565b","observation_id":"89098c72-8e08-40cb-b5e0-d4f6d4f7a9f3","resolution":{"observed_at":"2026-08-16T00:21:58.750734Z","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":"2026-08-16T00:21:58.729383Z","title":"Revisiting the calibration of modern neural net- works","venue":null,"work_id":"689bdbe2-964e-44da-99cc-5e74a1868f2c","year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.096436Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:8dd9ea73ef14cf66cb85c9e69ebbb740fad7365866aa504be7b839b306d6ab52","observation_id":"c93014b4-f8a4-465e-a6b9-5b89cd8fd0ac","resolution":{"observed_at":"2026-08-16T00:21:58.733804Z","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":"2026-08-16T00:21:58.712261Z","title":"Calibrating deep neural networks using focal loss.Advances in Neural Information Processing Systems (NeurIPs), 33:15288–15299, 2020","venue":null,"work_id":"193e0c77-e98e-47ed-aa76-c1263b7d4488","year":2020},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.101382Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:64ec3436a2a00b7cbe3195b3e5ded667be82a44077afec9c578145a61423153b","observation_id":"e55f47ef-97f0-44cf-a9e4-b3a4a6659c35","resolution":{"observed_at":"2026-08-16T00:21:58.718544Z","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":"1906.02629","last_updated":"2020-06-10T18:18:17Z","snapshot_observed_at":"2026-08-15T04:00:53.429768Z","submitted_at":"2019-06-06T15:03:11Z","title":"When Does Label Smoothing Help?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.02629","snapshot_observed_at":"2026-08-16T00:21:57.106643Z","title":"When does label smoothing help?arXiv preprint arXiv:1906.02629, 2019","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.106643Z"},"links":{"cited_paper":"/paper/1906.02629","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:ca6ea4555e44b65663d0b8927b79105679fe5c98ac1ca14f7c566ac063048659","observation_id":"9ed33c88-dcd4-46a4-9ffa-6a8556c53c6b","resolution":{"observed_at":"2026-08-16T00:21:57.106643Z","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":"2026-08-16T00:21:57.112238Z","title":"Obtaining well calibrated probabilities using bayesian binning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.112238Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:85dfd47bf5b5d901212b5410cffbcb313bb9d88184382e0d7fe68ad59ea0163b","observation_id":"b2ee5c37-0783-4919-9c9a-15d0cc69259e","resolution":{"observed_at":"2026-08-16T00:21:57.112238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1508.05154","last_updated":"2015-09-02T17:26:24Z","snapshot_observed_at":"2026-08-18T01:32:54.390073Z","submitted_at":"2015-08-21T00:25:51Z","title":"Posterior calibration and exploratory analysis for natural language processing models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1508.05154","snapshot_observed_at":"2026-08-16T00:21:57.117726Z","title":"Posterior calibration and exploratory analysis for natural language processing models.arXiv preprint arXiv:1508.05154 , 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.117726Z"},"links":{"cited_paper":"/paper/1508.05154","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:93bd8a39a2d27eaa26448068867bdc27a4e9134582cf73ed8e7b3834bd31c1b5","observation_id":"77cbb9e6-634f-40e7-b5bb-1d4e90fa95ff","resolution":{"observed_at":"2026-08-16T00:21:57.117726Z","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":"2026-08-16T00:21:58.686531Z","title":"Estimating diagnostic uncertainty in artificial intelligence assisted pathology using conformal prediction.Nature Communications, 13(1):7761, 2022","venue":null,"work_id":"121dcd0e-9f3b-4c99-a72b-b6a1e9e0cc5a","year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.124183Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:3edd632f311d72932c2620324a878fe1d3c2a74b3e3fe7b064a76aa4baad1a21","observation_id":"b9953bf5-438c-4c40-ab5b-34dbcf16b913","resolution":{"observed_at":"2026-08-16T00:21:58.691534Z","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":"2006.16405","last_updated":"2020-06-29T21:50:07Z","snapshot_observed_at":"2026-07-06T09:33:50.133351Z","submitted_at":"2020-06-29T21:50:07Z","title":"Unsupervised Calibration under Covariate Shift","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.16405","snapshot_observed_at":"2026-08-16T00:21:57.130342Z","title":"Unsupervised calibration under covariate shift.arXiv preprint arXiv:2006.16405, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.130342Z"},"links":{"cited_paper":"/paper/2006.16405","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:1da119656627819520217beff4a72c0c7aafaedbf4ac72ee2ba57d880ab36189","observation_id":"64808eae-729a-4791-93fc-38caee6ca979","resolution":{"observed_at":"2026-08-16T00:21:57.130342Z","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":"2026-08-16T00:21:58.668767Z","title":"Calibrated prediction with covariate shift via unsupervised domain adaptation","venue":null,"work_id":"f39b332e-d01d-4e0d-a2f8-281e0bcedab9","year":2020},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.140748Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:6007703ddd94a811a4308ce1d4f8cb58b571f1427e3efb436ef2b5d8652cb816","observation_id":"1bda673c-411d-4f69-95b8-0cb74ebcf0a2","resolution":{"observed_at":"2026-08-16T00:21:58.674750Z","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":"2026-08-16T00:21:58.650756Z","title":"Making deep neural networks robust to label noise: A loss correction approach","venue":null,"work_id":"906ce948-8577-4ce6-b133-57548335c4d9","year":1944},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.145680Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:5e84652e5a83bc338ae3302f5f8408f4ef1d420dbcd849a7f872da362e29600f","observation_id":"5d6d6c6e-7261-47a9-8286-a4350a21d0ca","resolution":{"observed_at":"2026-08-16T00:21:58.656464Z","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":"2026-08-16T00:21:58.634068Z","title":"Moment matching for multi-source domain adaptation","venue":null,"work_id":"5e4f3345-cbe3-46df-89ee-6da4ee48c8b3","year":2019},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.150941Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:df8181430b5e719fcd7da1320c7b64c54ca82cdce9c24dade899f169281c5ba7","observation_id":"6830d369-df86-4ac8-81ab-80cfb3891ceb","resolution":{"observed_at":"2026-08-16T00:21:58.638529Z","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":"1710.06924","last_updated":"2017-11-29T04:04:18Z","snapshot_observed_at":"2026-08-16T06:32:04.347989Z","submitted_at":"2017-10-18T20:20:49Z","title":"VisDA: The Visual Domain Adaptation Challenge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06924","snapshot_observed_at":"2026-08-16T00:21:57.157931Z","title":"Visda: The visual domain adaptation challenge.arXiv preprint arXiv:1710.06924 , 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.157931Z"},"links":{"cited_paper":"/paper/1710.06924","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:d39027e37af553deafd13fef4022df932025eac717817c2e4f06d4bb94985eab","observation_id":"45b98941-1f2d-467f-9cda-07afd771d67b","resolution":{"observed_at":"2026-08-16T00:21:57.157931Z","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":"2026-08-16T00:21:58.619260Z","title":"Privacy-preserving confor- mal prediction under local differential privacy","venue":null,"work_id":"2795ff0d-7b39-4275-86ce-a789d4af8b3a","year":2025},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.165086Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:ac6acee1f08de87805fcc4b666b77bc163dd4a5dcc73b40557526f421cb934ae","observation_id":"125ab980-dc21-432d-b79d-657b702d72c8","resolution":{"observed_at":"2026-08-16T00:21:58.623468Z","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":"2026-08-16T00:21:58.603943Z","title":"Confidence calibration of a medical imaging classification system that is robust to label noise","venue":null,"work_id":"c8bd9ba2-9f93-4d5e-bd53-86f234fd2af5","year":2024},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.170593Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:d28fcef70957ac3faefc3e22d0cdbed001f453f1f4b0e4746eedb7e7eba734f7","observation_id":"edf92e43-4de2-4f5f-a203-705f064440c0","resolution":{"observed_at":"2026-08-16T00:21:58.608920Z","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":"2026-08-16T00:21:58.587439Z","title":"Calibration of network confidence for unsupervised domain adaptation using estimated accuracy","venue":null,"work_id":"438a9fc4-ef37-403e-b7a5-9a9512d42aa9","year":2024},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.176359Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:7d70ce215be9f8f7f0778c8b46120c0e9d6c153ff786ca895e4b22b0ffaa67b3","observation_id":"da6cfc48-b992-44b8-bc17-98badf259110","resolution":{"observed_at":"2026-08-16T00:21:58.592376Z","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":"2026-08-16T00:21:58.572858Z","title":"A conformal prediction score that is robust to label noise","venue":null,"work_id":"ffb12b4e-033f-4f0e-aae6-95915706f237","year":2024},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.181020Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:cd78393042028948ceee7a5e0bf303055bc909f9df6dc0623c42ead52afa2205","observation_id":"30087cd9-91bb-4f85-ac61-bdfaaa8b9c32","resolution":{"observed_at":"2026-08-16T00:21:58.577586Z","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":"2026-08-16T00:21:58.550847Z","title":"A joint training and confidence calibration procedure that is robust to label noise","venue":null,"work_id":"21a9cec2-328c-48f0-bb9b-397e79ad2445","year":2024},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.186745Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:b8e04d96cc30ba3c9dc2422b0b1e41976dd4305621c3c0b260316f98594df0ec","observation_id":"027648a6-e8b0-4437-8876-b965bbda4a2d","resolution":{"observed_at":"2026-08-16T00:21:58.557457Z","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":"2501.12749","last_updated":"2025-08-13T16:54:25Z","snapshot_observed_at":"2026-08-14T19:22:55.350848Z","submitted_at":"2025-01-22T09:35:58Z","title":"Conformal Prediction of Classifiers with Many Classes based on Noisy Labels","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12749","snapshot_observed_at":"2026-08-16T00:21:57.191524Z","title":"Estimatingtheconformalpredictionthresh- old from noisy labels.arXiv preprint arXiv:2501.12749 , 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.191524Z"},"links":{"cited_paper":"/paper/2501.12749","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:335389d2cf75968d11eeb8094d139aa2f8004a3b4a765321edc0c5da3e784b6b","observation_id":"61de6896-52d5-4f96-a08a-24432a7b5a09","resolution":{"observed_at":"2026-08-16T00:21:57.191524Z","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":"2026-08-16T00:21:58.529398Z","title":"Conformal prediction of classifiers with many classes based on noisy labels","venue":null,"work_id":"48117386-84eb-4ed5-aa4e-6bbeca363795","year":2025},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.197597Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:37201ba8154e1a5aa2d9844dae098277c9a608744ab51737f9eb23d4f01c4629","observation_id":"766c1f85-a7e8-46a1-b55e-abc97597af47","resolution":{"observed_at":"2026-08-16T00:21:58.535089Z","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":"2026-08-16T00:21:58.509501Z","title":"Probabilistic outputs for support vector machines and comparisons to regu- larized likelihood methods","venue":null,"work_id":"bd3d2dfc-1153-4101-a5a0-680f195e90b8","year":1999},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.202950Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:25cb11a26b972c35173f24c9338cb36433d2d564bde81df24ad0a8c1d016715b","observation_id":"34e1f52a-73ec-4357-bcee-96922365834b","resolution":{"observed_at":"2026-08-16T00:21:58.516018Z","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":"2026-08-16T00:21:58.490649Z","title":"Learning to reweight examples for robust deep learning","venue":null,"work_id":"d3c0e910-64e3-4626-94a2-9c59d0aa803b","year":2018},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.208154Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:bb6119a5a3191cc90851245f69408fddbefc4430082b0f4be887a722afcf82a8","observation_id":"b341e812-8840-4a2b-95f3-8f0f0e7b598b","resolution":{"observed_at":"2026-08-16T00:21:58.496821Z","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":"2026-08-16T00:21:58.470059Z","title":"Classification with valid and adaptive coverage","venue":null,"work_id":"a4e458a5-c340-456b-94b3-a9c1fb5bf426","year":2020},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.214176Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:1cd3a473a1538ac512766afbc8b221f24930657a8fa15389c95aaf6858e21436","observation_id":"7954ae42-16c0-41cb-96b2-c3a51504e165","resolution":{"observed_at":"2026-08-16T00:21:58.476342Z","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":"2026-08-16T00:21:58.452037Z","title":"Post training uncertainty calibration of deep networks for medical image segmentation","venue":null,"work_id":"6498fd8a-0b48-410f-9ecd-6173d153f6e6","year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.221998Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:e901d311e1898293d56fde93099ea08ee641349c819b86280cc6164f0003ee17","observation_id":"d72de517-d060-45f3-bd8d-ff161375ebed","resolution":{"observed_at":"2026-08-16T00:21:58.458784Z","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":"2026-08-16T00:21:58.433754Z","title":"Adapting visual category models to new domains","venue":null,"work_id":"3658331b-194c-4ead-9c56-a2bcdf897d8a","year":2010},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.228281Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:3153de69b80da5e6199f5d5e3cc296d8b9fa2915c16705f6aa3ee2543af38e6b","observation_id":"7bfda177-4449-4a56-9c5e-a7d3a72c548f","resolution":{"observed_at":"2026-08-16T00:21:58.440327Z","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":"2026-08-16T00:21:58.416555Z","title":"Improved pre- dictive uncertainty using corruption-based calibration.Stat, 1050:7, 2021","venue":null,"work_id":"35af8a6a-8b64-446f-aceb-295040f6fb5f","year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.233745Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:0b9ddbaa83fc3d988337d48fd3cfdd2e10c406dd01c775806a92151ef1559189","observation_id":"05a93f30-4d91-4875-9e04-a952bf8c3c5a","resolution":{"observed_at":"2026-08-16T00:21:58.422230Z","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":"2309.05092","last_updated":"2024-02-22T01:33:11Z","snapshot_observed_at":"2026-08-16T15:01:55.248434Z","submitted_at":"2023-09-10T17:35:43Z","title":"Adaptive conformal classification with noisy labels","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.05092","snapshot_observed_at":"2026-08-16T00:21:57.242428Z","title":"Adaptive conformal classification with noisy labels","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.242428Z"},"links":{"cited_paper":"/paper/2309.05092","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:ee2fa7f6dbc6bb3db3b4a7ad094c9f944dfab384a09869599651db8e9868eb94","observation_id":"a21cf5a3-a0fe-4445-859e-538e7cacff04","resolution":{"observed_at":"2026-08-16T00:21:57.242428Z","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":"2026-08-16T00:21:58.398400Z","title":"Meta- weight-net: Learning an explicit mapping for sample weighting","venue":null,"work_id":"83daafab-afdf-4926-8f2c-83ab2778fbd9","year":1917},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.248773Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:503bbcaecb5d3050e46ea89627d658a8c4cacfbd0a9cb053b6d7ba463f8f2905","observation_id":"36192aa7-da50-4e22-a07e-9f0c76ccdda5","resolution":{"observed_at":"2026-08-16T00:21:58.404351Z","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":"2026-08-16T00:21:57.255094Z","title":"Learning from noisy labels with deep neural networks: A survey.IEEE transactions on neural networks and learning systems, 34(11):8135–8153, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.255094Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:18376f717ead2febca5cf26e111316a6fbe39a11914592748e62c8dcadd633ca","observation_id":"7a31a58b-d98e-45ed-a25c-f58b59dac709","resolution":{"observed_at":"2026-08-16T00:21:57.255094Z","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":"2026-08-16T00:21:58.366551Z","title":"Joint optimization framework for learning with noisy labels","venue":null,"work_id":"1469987e-305d-4de2-9b15-da00e245d5e9","year":2018},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.260186Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:b4f35ae1e1430913443f7883435c384c393cdb3082f18cfb7559f20e77681e6f","observation_id":"fc8fa04e-87e9-4c75-a1fa-cfa059be29ed","resolution":{"observed_at":"2026-08-16T00:21:58.373540Z","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":"2026-08-16T00:21:58.346336Z","title":"Post-hoc uncertainty calibration for domain drift scenarios","venue":null,"work_id":"13418768-9a11-46b0-af53-4de289b41341","year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.267031Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:c33f51fff784232be2aa19c56dcbbc117893ceaa38e3f37db00e1d8bc5c8f66f","observation_id":"cbe96b34-9073-4870-93aa-933a06366cae","resolution":{"observed_at":"2026-08-16T00:21:58.352586Z","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":"2026-08-16T00:21:58.331483Z","title":"The HAM10000 dataset, a large collec- tion of multi-source dermatoscopic images of common pigmented skin lesions.Scientific data, 5(1):1–9, 2018","venue":null,"work_id":"1eadf616-b28c-4490-90ee-150fb0111f7b","year":2018},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.273649Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:40daff1ac5598be36173ed72bd04585b208b47218f58d1fd99b019a61b4c470f","observation_id":"19be5904-a966-4be9-978f-1b069616f650","resolution":{"observed_at":"2026-08-16T00:21:58.336449Z","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":"2026-08-16T00:21:58.316084Z","title":"Deep hashing network for unsupervised domain adaptation","venue":null,"work_id":"9017bcec-233e-4898-b02b-033faa2402e1","year":2017},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.278742Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:8ac6e3fb687a0d451188e7032ff8cecc2a7019195d6291496e1c016e7cf67b38","observation_id":"03cd96dd-e0cb-4d92-a6f6-d0384ab9a629","resolution":{"observed_at":"2026-08-16T00:21:58.320529Z","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":"2026-08-16T00:21:57.284097Z","title":"Springer, 2005","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.284097Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:5b7e2ad4d2a977101a8bea3f927481c088f3cf74adca2eab63a51425eb41a0c0","observation_id":"69c7a617-e39d-48d3-b103-1fdbda634c4e","resolution":{"observed_at":"2026-08-16T00:21:57.284097Z","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":"2026-08-16T00:21:58.287577Z","title":"Graph structure estimation neural networks","venue":null,"work_id":"c72b761a-c3b9-492d-937a-6cddb712614a","year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.288980Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:5aa3e6b52fab3abb32cae212d35962481e5de1828c61653aa18e487b90260c94","observation_id":"bc590cf8-4822-45df-b73b-3ce556d1f580","resolution":{"observed_at":"2026-08-16T00:21:58.293717Z","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":"2026-08-16T00:21:57.293561Z","title":"Locally differentially private protocols for frequency estimation","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.293561Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:e7ab2722ede3cffdbc3f03a1087090505c68f57da829bd188cdcf97721b188f9","observation_id":"9be0591e-58ba-4d0b-8663-46a5da22ee1c","resolution":{"observed_at":"2026-08-16T00:21:57.293561Z","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":"2026-08-16T00:21:58.258444Z","title":"Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases","venue":null,"work_id":"f92129bc-0074-425d-b14d-20511c25b073","year":2017},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.299004Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:348a9c81f78445e3e297fb9976562a997e4017a2c1c5eea38d90fac9db732b29","observation_id":"25fa4197-fe79-403f-9191-1dbdf045e69f","resolution":{"observed_at":"2026-08-16T00:21:58.264419Z","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":"2026-08-16T00:21:58.238870Z","title":"Transferable calibra- tion with lower bias and variance in domain adaptation","venue":null,"work_id":"ff11d498-a96f-4d7e-bf04-e07a9a66861e","year":2020},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.303771Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:d6eb5005c9db9103e6ebdf3406ae0a8e5ccb2e082a1bb7f681b44f1be4baa412","observation_id":"f54f210c-8272-487f-b86e-4b1e1574aa6f","resolution":{"observed_at":"2026-08-16T00:21:58.245391Z","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":"2026-08-16T00:21:58.220584Z","title":"Randomized response: A survey technique for eliminating evasive answer bias","venue":null,"work_id":"ec9fd41d-be2f-44a8-b27c-2a60a9edbe70","year":1965},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.308428Z"},"links":{"citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:701bcc007a6560eb09eff75386e4ae6a553edb33b0436acf96653852c4fae40d","observation_id":"14f78754-230a-4133-afd5-afac0d977d0a","resolution":{"observed_at":"2026-08-16T00:21:58.225701Z","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":"2110.12088","last_updated":"2022-03-27T06:51:57Z","snapshot_observed_at":"2026-08-16T20:37:56.916414Z","submitted_at":"2021-10-22T22:42:11Z","title":"Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.12088","snapshot_observed_at":"2026-08-16T00:21:57.313395Z","title":"Learning with noisy labels revisited: A study using real-world human annotations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.313395Z"},"links":{"cited_paper":"/paper/2110.12088","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:465888ecb92c3fbeed9eec06dc4cffca80fb609c7924e4ceb30de5f8cda49ed3","observation_id":"013785d3-129f-4b7e-a202-b6abcb644ee4","resolution":{"observed_at":"2026-08-16T00:21:57.313395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.11569","last_updated":"2021-08-26T03:45:00Z","snapshot_observed_at":"2026-08-16T18:00:53.400004Z","submitted_at":"2021-08-26T03:45:00Z","title":"Robust Long-Tailed Learning under Label Noise","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.11569","snapshot_observed_at":"2026-08-16T00:21:57.318142Z","title":"Robust long-tailed learning under label noise","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-16T00:21:57.318142Z"},"links":{"cited_paper":"/paper/2108.11569","citing_paper":"/paper/2608.12100"},"observation_digest":"sha256:134b0cd82398e6b3667fb1aca735aefa34a1c6a257c073acf2eeaaa753835333","observation_id":"dc326788-e456-4597-af2a-936c89eec70e","resolution":{"observed_at":"2026-08-16T00:21:57.318142Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.12100","last_updated":"2026-08-12T14:23:14Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T04:20:42.948644Z","submitted_at":"2026-08-12T14:23:14Z","title":"Confidence Calibration of Deep Learning Systems"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":58,"verified_exact":1,"verified_fuzzy":41},"total_outbound_references":121},"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 18 August 2026, this Paper Citation Record lists 100 of 121 outbound references and 0 inbound Pith citation observations for arXiv:2608.12100."}