{"as_of":"2026-08-07T23:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3ab62c0ad93040f2e00b2fa8a8ae81c398486ef9bd2ff02e8f9e8066d3289f6b","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T09:40:43.024616Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2607.18278/citation-record","integrity":"/paper/2607.18278/integrity","json":"/paper/2607.18278/citation-record.json","paper":"/paper/2607.18278"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:40:38.824931Z","title":"Pitfalls of in- domain uncertainty estimation and ensembling in deep learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:38.824931Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:744ece1fc717c65d5e010ded706096acd6437751379a45e1281843e46fd2086b","observation_id":"83436d99-e530-4906-92cb-b11f37e6f51d","resolution":{"observed_at":"2026-08-02T09:40:38.824931Z","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":"2026-08-02T09:40:38.920506Z","title":"Addressing failure prediction by learning model confidence","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:38.920506Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:9ab558b03b4830f7f1f9b4380b69486c7b6b040090580b11611c786a178dce19","observation_id":"5d737c02-e8d4-4867-924e-3ed87353ce8e","resolution":{"observed_at":"2026-08-02T09:40:38.920506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.15583","last_updated":"2025-03-19T16:47:15Z","snapshot_observed_at":"2026-08-07T17:28:35.365247Z","submitted_at":"2025-03-19T16:47:15Z","title":"Efficient Post-Hoc Uncertainty Calibration via Variance-Based Smoothing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.15583","snapshot_observed_at":"2026-08-02T09:40:39.005075Z","title":"Efficient post-hoc uncertainty calibration via variance-based smoothing.arXiv preprint arXiv:2503.15583, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:39.005075Z"},"links":{"cited_paper":"/paper/2503.15583","citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:d22b2c4680972761a86fd077971d1d2a8c19ae062843176723471dcddbe174c6","observation_id":"80f435a7-66e2-4447-898f-f756a0c8ef6e","resolution":{"observed_at":"2026-08-02T09:40:39.005075Z","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":"2026-08-02T09:40:39.144959Z","title":"Phases of uncertainty: Confidence–calibration dynamics in language model training","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:39.144959Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:a1780e04e7c305b30ab3a34402366afc3669cb3ca5a63e608cdb219cc48607d4","observation_id":"6a31970b-2d63-42f6-aa53-04189dc73827","resolution":{"observed_at":"2026-08-02T09:40:39.144959Z","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":"2026-08-02T09:40:39.284749Z","title":"On the foundations of noise-free selective classification.Journal of Machine Learning Research, 11(5):1605–1641, 2010","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:39.284749Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:2b64f68977877383618860c76b64c91ab2e0fb8801e671fa254c7bb9bb841d41","observation_id":"2d741bdf-bee9-4127-9b67-2eb9ccb132e2","resolution":{"observed_at":"2026-08-02T09:40:39.284749Z","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":"2026-08-02T09:40:39.424754Z","title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:39.424754Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:b495725bcec908995605c10ef8d2c70a24f64d6349d644dde3953e52a38a02e6","observation_id":"e55eb204-705c-478e-b5cc-18bf7ea4caf6","resolution":{"observed_at":"2026-08-02T09:40:39.424754Z","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":"2026-08-02T09:40:39.572908Z","title":"Datasheets for datasets.Communications of the ACM, 64(12):86–92, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:39.572908Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:aeef5acb1fa382a524c93274d6ce7cafa937c157315290ab9e6c52fc497bc763","observation_id":"43faf19b-ae1e-488f-9657-b9a25082d7aa","resolution":{"observed_at":"2026-08-02T09:40:39.572908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.08500","last_updated":"2017-06-01T14:10:34Z","snapshot_observed_at":"2026-07-06T05:43:59.308291Z","submitted_at":"2017-05-23T19:43:56Z","title":"Selective Classification for Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.08500","snapshot_observed_at":"2026-08-02T09:40:39.737356Z","title":"Selective classification for deep neural networks.arXiv preprint arXiv:1705.08500, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:39.737356Z"},"links":{"cited_paper":"/paper/1705.08500","citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:95229bf06697167a3a73ceab37ef40816d802785b5df1dbe4c4e57eeed3d20dd","observation_id":"ebbd52c1-e2a5-4b6c-a90a-5d7aad99255c","resolution":{"observed_at":"2026-08-02T09:40:39.737356Z","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":"2026-08-02T09:40:39.910993Z","title":"Selectivenet: A deep neural network with an integrated reject option","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:39.910993Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:575e8ae20f4b8b8a5b1ab8549f34f9ca8eebcbb11c24b57338c6cc6af384c18d","observation_id":"0b217baa-67fb-4aa5-9f25-aaddd8ccdc28","resolution":{"observed_at":"2026-08-02T09:40:39.910993Z","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":"2026-08-02T09:40:40.094211Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:40.094211Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:3ed6677b5554f6fa8cb2934a38d69abfa52c812ea48c44126477d3d1d7e5aa1b","observation_id":"467929dd-9a06-4812-8039-aab205c65756","resolution":{"observed_at":"2026-08-02T09:40:40.094211Z","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":"2026-08-02T09:40:40.288201Z","title":"Why do tree-based models still outperform deep learning on typical tabular data? InAdvances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:40.288201Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:891520ccdd3c3be8d04292023e15abd47184ec24ba0d51f1b3157e59ba9e3453","observation_id":"400a427b-5402-4a2f-986a-a1c352614331","resolution":{"observed_at":"2026-08-02T09:40:40.288201Z","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":"2026-08-02T09:40:40.416693Z","title":"Weinberger","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:40.416693Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:9e28dd30e107578ff053d228aed2464aa2abd2235a2808e8646a4ab0d527f010","observation_id":"1823934c-1c7d-4f3f-9d1a-267e300f3360","resolution":{"observed_at":"2026-08-02T09:40:40.416693Z","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":"2026-08-02T09:40:40.544744Z","title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:40.544744Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:ee9f9b0b7ac4c3cbe0f8eeeaa7c1b92fdb44792e4348e0746135fbeb9837a598","observation_id":"b0d96079-2623-4f01-8c03-705427211002","resolution":{"observed_at":"2026-08-02T09:40:40.544744Z","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":"2026-08-02T09:40:40.679028Z","title":"Better by default: Strong pre-tuned MLPs and boosted trees on tabular data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:40.679028Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:87a92d89a76f6611253da9dea404f8e415aa8c1e124c517ec65c71ae87faac87","observation_id":"84cb4d3d-5aa2-4e28-9e0b-fe73e66f4e89","resolution":{"observed_at":"2026-08-02T09:40:40.679028Z","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":"2026-08-02T09:40:40.824954Z","title":"Guan, and Maya Gupta","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:40.824954Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:2326f9771159ed66d0009dc6f204885a8f3c06db55b8c373ecd8243500e2b0fc","observation_id":"7a079776-c904-41c9-a485-70207e334625","resolution":{"observed_at":"2026-08-02T09:40:40.824954Z","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":"2026-08-02T09:40:40.942908Z","title":"Accurate uncertainties for deep learning using calibrated regression","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:40.942908Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:d061cffce9eefddc593d51b8b12552b119a6402303536ea293d27174344cdfb7","observation_id":"5abd9f5f-f645-448c-8a0f-cca919e9e836","resolution":{"observed_at":"2026-08-02T09:40:40.942908Z","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":"2026-08-02T09:40:41.094840Z","title":"Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with dirichlet calibration","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:41.094840Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:db45bbe24532a80ad33a768ef319dd68566603f4892bfb248a6ad96f7d155348","observation_id":"42a99b1a-82dd-4430-b54c-f3d36f5e4a39","resolution":{"observed_at":"2026-08-02T09:40:41.094840Z","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":"2026-08-02T09:40:41.224764Z","title":"Beta calibration: a well-founded and easily implemented improvement on logistic calibration for binary classifiers","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:41.224764Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:6636d897074d53971b09bf5fb592305314186be231f2d12d570f4ae0c18d8378","observation_id":"132b7021-fb7d-44c7-8190-8af74dfd65b8","resolution":{"observed_at":"2026-08-02T09:40:41.224764Z","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":"2026-08-02T09:40:41.444758Z","title":"Simple and scalable predictive uncertainty estimation using deep ensembles","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:41.444758Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:71b2142ebe7069939963e34f069fbc8f95041e7a33a87b7c655da703a06c7456","observation_id":"d59892ad-8b6e-4a42-a1e4-765b38411002","resolution":{"observed_at":"2026-08-02T09:40:41.444758Z","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":"2026-08-02T09:40:41.556018Z","title":"Owens, and Yixuan Li","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:41.556018Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:7bc457c5218d758f337cfb3852feef6fd3bd38c152fad0a8e29066b36f7c0164","observation_id":"c9b839a4-efe0-4d7e-81e9-efb9f353fce0","resolution":{"observed_at":"2026-08-02T09:40:41.556018Z","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":"2026-08-02T09:40:41.759938Z","title":"When do neural nets outperform boosted trees on tabular data? InAdvances in Neural Information Processing Systems 36 (NeurIPS 2023), 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:41.759938Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:f40d61e25227def3ff6f47172a10df7a0ee156ec1946addde4aff1d7d4a0010f","observation_id":"b7e05f9f-7fd7-4a42-b2d2-d1e8cdc51326","resolution":{"observed_at":"2026-08-02T09:40:41.759938Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22803","last_updated":"2025-05-28T19:23:47Z","snapshot_observed_at":"2026-08-07T18:58:08.604314Z","submitted_at":"2025-05-28T19:23:47Z","title":"CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.22803","snapshot_observed_at":"2026-08-02T09:40:41.846764Z","title":"CLUE: Neural networks calibration via learning uncertainty-error alignment.arXiv preprint arXiv:2505.22803, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:41.846764Z"},"links":{"cited_paper":"/paper/2505.22803","citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:a099c5026a0cb9f18c328371339c46c373a74a8e6fee66f3aa65c8a5d1ea9028","observation_id":"a496416e-71ca-4569-9d1a-6d7339cc7e1c","resolution":{"observed_at":"2026-08-02T09:40:41.846764Z","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":"2026-08-02T09:40:41.972665Z","title":"Revisiting the calibration of modern neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:41.972665Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:5d9a3ab04ed1cb8ee820e5ff3ec23f68727213dfb41de876252d3515e533a1d9","observation_id":"86c3be45-8267-43a9-9bb6-135f464d758d","resolution":{"observed_at":"2026-08-02T09:40:41.972665Z","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":"2026-08-02T09:40:42.064656Z","title":"Model cards for model reporting","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:42.064656Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:4172d239eb5682ce16d61a47893e983b51b9fc5528f35c781c3fae7c14db6167","observation_id":"3ad6c22d-a69e-4574-8d2f-2e0f2ed0c19f","resolution":{"observed_at":"2026-08-02T09:40:42.064656Z","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":"2026-08-02T09:40:42.132522Z","title":"Cooper, and Milos Hauskrecht","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:42.132522Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:64bbcd11e6c031d07d64f2c2f91da95fbf6543c438d1983b5dfc729678acfeb4","observation_id":"5bf7d92e-36af-420e-918d-7796549194c6","resolution":{"observed_at":"2026-08-02T09:40:42.132522Z","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":"2026-08-02T09:40:42.224750Z","title":"Predicting good probabilities with supervised learning","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:42.224750Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:f8a5ff5aac406f56fc6237e6304470f982fb433ab322d43b31980929b066e938","observation_id":"70975b74-efb1-44f9-a91e-fca60bcdd3b8","resolution":{"observed_at":"2026-08-02T09:40:42.224750Z","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":"2026-08-02T09:40:42.398207Z","title":"Sculley, Sebastian Nowozin, Joshua Dillon, Balaji Lakshminarayanan, and Jasper Snoek","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:42.398207Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:2123b6140df94be18e499ff6ed663a12871bd3ed36fa538d11c61e70ea2d9714","observation_id":"595110c8-8d03-45d1-b005-bb9cafaad9b6","resolution":{"observed_at":"2026-08-02T09:40:42.398207Z","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":"2026-08-02T09:40:42.524743Z","title":null,"venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:42.524743Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:36f94f5b251b10f9e688e67da879118fc1e4959b0cd69809e03a4152b7e37990","observation_id":"81ed7e8d-da41-4893-b4b4-b83fdb338914","resolution":{"observed_at":"2026-08-02T09:40:42.524743Z","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":"2026-08-02T09:40:42.632007Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:42.632007Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:602621bd00067aab0ab869b88ca5598f719ced9e07489d304a0b8e8314894a46","observation_id":"df1144f8-696c-4d8a-aff1-8f7e4fe963da","resolution":{"observed_at":"2026-08-02T09:40:42.632007Z","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":"2026-08-02T09:40:42.743482Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:42.743482Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:66e3eb6bdc37844674728ac6b1fbffb53c7fcc6ded0a96d14617706ba09ebd12","observation_id":"cb103e8d-d629-446d-9882-4f8e055bdb10","resolution":{"observed_at":"2026-08-02T09:40:42.743482Z","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":"2026-08-02T09:40:42.834751Z","title":"Springer, 2005","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:42.834751Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:e8d002f7ffda19aa06c5b9fb248ed5facccbce438196480109ad6c47570ab3c0","observation_id":"8ebb835a-c8ce-45fa-8feb-519100b043f3","resolution":{"observed_at":"2026-08-02T09:40:42.834751Z","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":"2026-08-02T09:40:42.924761Z","title":"Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:42.924761Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:71f2738cede8905b1baa1e03754c333818fd2447b0ef0947d271bb51563a7d5c","observation_id":"dfcb4e9d-c0db-4623-9327-b2128864a8fd","resolution":{"observed_at":"2026-08-02T09:40:42.924761Z","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":"2026-08-02T09:40:43.024616Z","title":"Transforming classifier scores into accurate multiclass probability estimates","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T09:40:43.024616Z"},"links":{"citing_paper":"/paper/2607.18278"},"observation_digest":"sha256:1b4cc7d12a60fac418087dca13bc81c4ce84fa3220a28dc43d61f006ff5281be","observation_id":"c7acf1d8-cf91-4e07-960e-f9e495b0725d","resolution":{"observed_at":"2026-08-02T09:40:43.024616Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.18278","last_updated":"2026-06-29T01:23:52Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T09:40:37.864183Z","submitted_at":"2026-06-29T01:23:52Z","title":"FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":33},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2607.18278."}