{"as_of":"2026-08-13T01:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3db14c14d764bec28aa48d5cadacbc56081af542996c0d87b86ee24eed5f8735","coverage":[{"denominator":130,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T18:53:10.567319Z","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":"2026-08-12T06:34:41.77262+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/2412.07520/citation-record","integrity":"/paper/2412.07520/integrity","json":"/paper/2412.07520/citation-record.json","paper":"/paper/2412.07520"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:53:09.314857Z","title":"Tldr: Deep learning-based automated privacy policy annotation with key policy highlights","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.314857Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:d4341268b51240ee962a611becc1f1c08049c262618eed6d200f242b94c0d8b4","observation_id":"39b61e03-47f8-4de9-86a5-0e8845c39299","resolution":{"observed_at":"2026-08-11T18:53:09.314857Z","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":"2026-08-11T18:53:09.323551Z","title":"A convergence theory for deep learning via over-parameterization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.323551Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:bc78b129b6020f57bc43059c64572e8322e5b1307de99f7607da62b63162650a","observation_id":"56d51929-c7ee-4a61-996c-22ea313481bf","resolution":{"observed_at":"2026-08-11T18:53:09.323551Z","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":"2026-08-11T18:53:09.333393Z","title":"Transductive versions of the lasso and the dantzig selector","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.333393Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:ee6bda5080ab0eb855233b8ac70419f3bddbdb242630aec493e879a7e01cada7","observation_id":"2163eca3-49af-4d34-bb52-d6b183076a0c","resolution":{"observed_at":"2026-08-11T18:53:09.333393Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.00420","last_updated":"2018-07-31T00:09:56Z","snapshot_observed_at":"2026-07-06T06:21:22.353187Z","submitted_at":"2018-02-01T18:20:05Z","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.00420","snapshot_observed_at":"2026-08-11T18:53:09.345108Z","title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.345108Z"},"links":{"cited_paper":"/paper/1802.00420","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:87de5f0a5478e5cc473dc5f565fb005d304996edc016a2522675922318fc6b3c","observation_id":"e2f7f5db-8200-43ad-9664-95a7220f2ec9","resolution":{"observed_at":"2026-08-11T18:53:09.345108Z","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":"2026-08-11T18:53:09.351844Z","title":"Bartlett, Dylan J","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.351844Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:c8eb6ddfa5605a8725384d7b690fb4abecf61ebd2f2752934a12431d67245da4","observation_id":"0168d43d-f40f-444b-b63b-9dbdc8f79068","resolution":{"observed_at":"2026-08-11T18:53:09.351844Z","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":"2026-08-11T18:53:09.358278Z","title":"Benign overfitting in linear regression","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.358278Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:d867f5c7098fc0495e70cfa6e0f973fb55eeb0d39af2c8fa3944ae40b0dfb309","observation_id":"0c77697e-de8a-4e71-a8c6-51e7c6a5262f","resolution":{"observed_at":"2026-08-11T18:53:09.358278Z","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":"2026-08-11T18:53:09.378108Z","title":"Hsu, and Partha Mitra","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.378108Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:066ded0f6f41c2df7e5e3e369e91bde0bce4a5ac669e1a8ffdc7d81edcd31385","observation_id":"7658ce33-182d-4a17-8bdd-0c4263a70f23","resolution":{"observed_at":"2026-08-11T18:53:09.378108Z","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":"2026-08-11T18:53:09.386003Z","title":"Reconciling modern machine-learning practice and the classical bias–variance trade-off","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.386003Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:c715efa065b035b82077933d80bc8555e61fe9d36ceab19801759227c78ead2d","observation_id":"b8386505-3e15-4357-b32b-041471e713ae","resolution":{"observed_at":"2026-08-11T18:53:09.386003Z","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":"2026-08-11T18:53:09.396948Z","title":"Generalized inverses: theory and appli- cations, volume 15","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.396948Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:2cfd1700555f9fd41b5c961bba625c05e538ab094c719c35deec5d1c82df4a05","observation_id":"554bbcea-71fe-4c68-ba87-90e84b35de8e","resolution":{"observed_at":"2026-08-11T18:53:09.396948Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.12286","last_updated":"2020-01-08T12:46:19Z","snapshot_observed_at":"2026-07-06T07:49:00.896271Z","submitted_at":"2019-04-28T09:35:50Z","title":"Deep pNML: Predictive Normalized Maximum Likelihood for Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.12286","snapshot_observed_at":"2026-08-11T18:53:09.407882Z","title":"Deep pnml: Predictive normalized max- imum likelihood for deep neural networks","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.407882Z"},"links":{"cited_paper":"/paper/1904.12286","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:707d0e3514b36334cc86639e2243352b550c82f74c9bef6e5bdc193c78aedd80","observation_id":"156d661c-785a-4e92-a5ed-b8e5669b550e","resolution":{"observed_at":"2026-08-11T18:53:09.407882Z","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":"2026-08-11T18:53:09.418129Z","title":"A new look at an old problem: A univer- sal learning approach to linear regression","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.418129Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:1083f153a7f31c198a2c989b4ea0575cde078dc9ccb3778c6658497a94f67f14","observation_id":"c9c16595-a17b-453a-865b-6be841a8aff5","resolution":{"observed_at":"2026-08-11T18:53:09.418129Z","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":"2026-08-11T18:53:09.424629Z","title":"Learning rotation invariant features for cryogenic electron microscopy image re- construction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.424629Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:f283ada4d45001105fad42706fa261db9d436c424c47c592ceaeef5b42b3c48f","observation_id":"742e2ecf-b593-4b0f-a8a2-98adcff69863","resolution":{"observed_at":"2026-08-11T18:53:09.424629Z","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":"2026-08-11T18:53:09.433463Z","title":"Evasion attacks against machine learning at test time","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.433463Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:bc45ae668981a17deb3ca2afa2aa651c3a538b1ae31fbc53c2ce225594c13e7b","observation_id":"242a3975-5ecb-4327-9ae5-f62127d3c801","resolution":{"observed_at":"2026-08-11T18:53:09.433463Z","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":"2026-08-11T18:53:09.441637Z","title":"The description length of deep learning models","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.441637Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:3267cd78aa168292c20cb5c6463f4b5dd9a3624f6a4702052650d0722274b85e","observation_id":"987c833b-7521-4152-902a-4466047f4b1c","resolution":{"observed_at":"2026-08-11T18:53:09.441637Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.06705","last_updated":"2019-02-20T17:38:32Z","snapshot_observed_at":"2026-08-12T14:46:48.605924Z","submitted_at":"2019-02-18T18:18:27Z","title":"On Evaluating Adversarial Robustness","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.06705","snapshot_observed_at":"2026-08-11T18:53:09.453328Z","title":"On evaluating adversarial robustness","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.453328Z"},"links":{"cited_paper":"/paper/1902.06705","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:df7df1d8e1b455e2d45956d6175eac0adcf6e7f421389a315f7df92b24a2ad9b","observation_id":"ab133727-9fd0-44dd-bc1b-ab1dd9df5147","resolution":{"observed_at":"2026-08-11T18:53:09.453328Z","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":"2026-08-11T18:53:09.485112Z","title":"Unlabeled data improves adversarial robustness","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.485112Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:d7f65645ff99c9ce4a1da6d589386445d61890c5643534fba05bf2b591837e0a","observation_id":"ac89abbc-cd83-47b5-a2a8-bbabed2edaab","resolution":{"observed_at":"2026-08-11T18:53:09.485112Z","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":"2026-08-11T18:53:09.498932Z","title":"Transductive inference for estimating values of functions","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.498932Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:5c013f192c1df05c50466379892690d77c51afe69812da246f5c276136bc59c0","observation_id":"cb8d82f4-2ec9-4bf0-b571-261f2d581b6a","resolution":{"observed_at":"2026-08-11T18:53:09.498932Z","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":"2026-08-11T18:53:09.516316Z","title":"Hopskipjumpattack: A query-efficient decision-based attack","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.516316Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:858d583ef4199ec6790f577e86cee2c2cba4ad5000f3819ba51a8b2ea03027b3","observation_id":"3b2449c1-2fe6-4125-9a3d-775db7f972ea","resolution":{"observed_at":"2026-08-11T18:53:09.516316Z","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":"2026-08-11T18:53:09.523605Z","title":"Emnist: Extending mnist to handwritten letters","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.523605Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:7b05065c3d47ec85a9fa839e4cf7a53a71c3ed729517ac9120898cadc2df701a","observation_id":"6cbc9f41-1d76-47f0-b7c8-b18680927f2b","resolution":{"observed_at":"2026-08-11T18:53:09.523605Z","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":"2026-08-11T18:53:09.548586Z","title":"On transductive regression","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.548586Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:cc0b14bbc96b12fd829715f578e7f79e618196a6fc7d3ba2e28a5d3bc486686b","observation_id":"47f8fc69-0c38-4cac-8a47-df6197f4681e","resolution":{"observed_at":"2026-08-11T18:53:09.548586Z","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":"2026-08-11T18:53:09.584646Z","title":"Laplace redux-effortless bayesian deep learn- ing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.584646Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:3b843173a02d56d3ff7fbcc7c07d4c9b82f0d553573cc915fe385de33b27fe17","observation_id":"86853eb9-0ebe-4c5f-8d67-cde98c418ead","resolution":{"observed_at":"2026-08-11T18:53:09.584646Z","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":"2026-08-11T18:53:09.604750Z","title":"Mathematics for machine learning, chapter 9.3","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.604750Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:b2652169af44794db1c09ff1916c04aa4a56fe1e0160dffc55bd90e817e218eb","observation_id":"5956927f-18f3-4f99-8d6d-8ae23153eaa5","resolution":{"observed_at":"2026-08-11T18:53:09.604750Z","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":"2026-08-11T18:53:09.634752Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.634752Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:a39dd9f33630b01911956b8cbdd5387f7b531ca4cc6ce8832bfa5fb0eebbdd76","observation_id":"432c7931-c30f-490a-9688-83386a4250d8","resolution":{"observed_at":"2026-08-11T18:53:09.634752Z","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":"2026-08-11T18:53:09.664751Z","title":"The mnist database of handwritten digit images for machine learning research [best of the web].IEEE signal processing magazine, 29(6):141–142, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.664751Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:45bffc42c61ed8f733cac46ff9be6e8741e29ea36c18dc1fef66f9e93847c9f3","observation_id":"abea52cf-f1e6-4e01-8917-15143335549e","resolution":{"observed_at":"2026-08-11T18:53:09.664751Z","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":"2026-08-11T18:53:09.680069Z","title":"Reducing network agnostophobia","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.680069Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:3080aebb71593894777f38fba85a525809eff07b6ca63e95be265c1820cd8d8d","observation_id":"1c431e89-b338-4df2-9f69-9b892a7b8cdb","resolution":{"observed_at":"2026-08-11T18:53:09.680069Z","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":"2026-08-11T18:53:09.716059Z","title":"UCI machine learning repository, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.716059Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:efe34ea1d8eff1b39e5decbbd60071594fe7d15a9e89c20dbe1ab02d79e43fd5","observation_id":"09a50b94-04f5-4a88-b2b6-ac6012dfe17a","resolution":{"observed_at":"2026-08-11T18:53:09.716059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10189","last_updated":"2023-10-12T23:18:22Z","snapshot_observed_at":"2026-08-13T00:43:09.826302Z","submitted_at":"2020-06-17T22:45:14Z","title":"Revisiting minimum description length complexity in overparameterized models","version":4},"cited_work":{"arxiv_id":"2006.10189","doi":null,"metadata_source":"pith","pith_arxiv_id":"2006.10189","snapshot_observed_at":"2026-08-11T18:53:11.872476Z","title":"Revisiting minimum description length complexity in overparameterized models","venue":"cs.LG","work_id":"2028e2df-2b12-409e-b9fa-ebd1b6ae18ab","year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.732076Z"},"links":{"cited_paper":"/paper/2006.10189","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:139dc1348f40efdeca10d759c3a6fabf7d8506e970267006e345c1ebf07902de","observation_id":"ff57d101-ac47-401e-ab79-61bbdf5f2e48","resolution":{"observed_at":"2026-08-11T18:53:11.904752Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:09.749155Z","title":"Wainwright","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.749155Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:7e39f807995c0c0342ce5fc2639321e777e7dbad956b74eb0f70da888bf9c3b4","observation_id":"bb4202dd-e40c-4564-b343-938c6914ed5e","resolution":{"observed_at":"2026-08-11T18:53:09.749155Z","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":"2026-08-11T18:53:09.759275Z","title":"Theory of optimal experiments","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.759275Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:d644afa0f64aad2026b2148681abaedfdfbe67e143e9e80794a3e9712250f8f6","observation_id":"f4138b0c-f57a-4025-b62c-4c9762d7d94d","resolution":{"observed_at":"2026-08-11T18:53:09.759275Z","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":"2026-08-11T18:53:09.768183Z","title":"The use of multiple measurements in taxonomic problems.Annals of eugenics, 7(2):179–188, 1936","venue":null,"work_id":null,"year":1936},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.768183Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:b1f74626f85e9f7cbd824c723e9e704aed35d2c52836c43201a9e579d26c3f68","observation_id":"4397ec8e-2cb6-4ded-b10e-5435b1121be7","resolution":{"observed_at":"2026-08-11T18:53:09.768183Z","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":"2026-08-11T18:53:09.787532Z","title":"On the problem of on-line learning with log-loss.IEEE International Symposium on Information Theory - Proceedings, pages 2995–2999,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.787532Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:6d6886cf7cf3efe603db04486fcc78dcef109f8d7a8d183d775f50fec7a354d8","observation_id":"01996fab-1f3c-4db6-89fc-d24b0012d096","resolution":{"observed_at":"2026-08-11T18:53:09.787532Z","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":"2026-08-11T18:53:09.815942Z","title":"Universal batch learning with log-loss","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.815942Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:d56d8755d618b188ad49fb90b2b40750036f7e74b50efc60d5008ed4e3fb4b9d","observation_id":"da68c0e3-31f7-41b6-a11e-fc1257dcff0a","resolution":{"observed_at":"2026-08-11T18:53:09.815942Z","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":"2026-08-11T18:53:09.826706Z","title":"Universal learning of individual data","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.826706Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:bfd3a23192bb2788b339ef7864bce31726d6d070d589a6a57f609039301f6807","observation_id":"dc8f18b4-85f1-42e2-9999-d848c0167c43","resolution":{"observed_at":"2026-08-11T18:53:09.826706Z","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":"2026-08-11T18:53:09.840447Z","title":"Dropout as a bayesian approximation: Repre- senting model uncertainty in deep learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.840447Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:b3d2e109cee6cf2859b605a908c5387e5a2f4561570eff0857e6430e58e1b616","observation_id":"5e5cca97-2736-4273-9ed9-e1f44508d6c9","resolution":{"observed_at":"2026-08-11T18:53:09.840447Z","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":"2026-08-11T18:53:09.852522Z","title":"Deep bayesian active learning with image data","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.852522Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:0bf7e495ef11be9515d5c7e357838f9d2c6efc7828b0cb94f24b36444036dea1","observation_id":"1dba6246-04a4-4b9d-a8ea-14674d7b1fae","resolution":{"observed_at":"2026-08-11T18:53:09.852522Z","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":"2026-08-11T18:53:09.859985Z","title":"Degrees of freedom in deep neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.859985Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:a3c6e19080f5107015e02231ce5026dc2e7040f984da1cc347a5b4cb64866ba2","observation_id":"a480eb4b-976c-40e2-92c8-e3f33efea6df","resolution":{"observed_at":"2026-08-11T18:53:09.859985Z","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":"2026-08-11T18:53:09.869022Z","title":"Deep learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.869022Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:f06fd40611545b8dd56330b992d3ba685f761791cb6df3a1c64966a179296ae2","observation_id":"51bd8b8d-ece3-4883-aba6-a2a0156f0271","resolution":{"observed_at":"2026-08-11T18:53:09.869022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-12T17:13:46.394331Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-11T18:53:09.879547Z","title":"Explaining and harness- ing adversarial examples","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.879547Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:f9ba3660ff8a54e9b69422d066bfae07dc99d60d5832593b00b7af06b5473538","observation_id":"64f6698b-e507-4326-91ed-24f4041429ab","resolution":{"observed_at":"2026-08-11T18:53:09.879547Z","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":"2026-08-11T18:53:09.888131Z","title":"Machine learning for social science: An agnostic approach","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.888131Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:ede973c99f383cda3f701bb13017c7b1735f374207ec518149d697857b668fde","observation_id":"0f66fae0-c4c9-4c8b-85cb-d156c0512dd8","resolution":{"observed_at":"2026-08-11T18:53:09.888131Z","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":"2026-08-11T18:53:09.899228Z","title":"The minimum description length principle","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.899228Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:ed8ba0cdc9e6174e1a26c7aff97cc69c80cc810c055d8ba89b63530e87d89792","observation_id":"8d750e82-98c8-4080-9ca7-08d747213ff9","resolution":{"observed_at":"2026-08-11T18:53:09.899228Z","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":"2026-08-11T18:53:09.914186Z","title":"Lee, Daniel Soudry, and Nati Srebro","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.914186Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:9098436c58b7d560f53559c473eb21a4966ce9fb186be06951d1caee444f1760","observation_id":"0a5038df-51d5-4de9-a612-8111cff29575","resolution":{"observed_at":"2026-08-11T18:53:09.914186Z","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":"2026-08-11T18:53:09.927781Z","title":"Coun- tering adversarial images using input transformations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.927781Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:a44f031f0f047b1466695ef4598d455d5694a263f9505717687b2d95cab2e83c","observation_id":"53a75aea-608a-4a44-82fa-3b374aa52dc2","resolution":{"observed_at":"2026-08-11T18:53:09.927781Z","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":"2026-08-11T18:53:09.937562Z","title":"Friedman","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.937562Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:05dc74ec404ebf4c8384a63b0dfd6be02be2aef104c78fe08b124d3596cb7326","observation_id":"d0b714ee-b3fc-45fa-ba8d-746bbe415f90","resolution":{"observed_at":"2026-08-11T18:53:09.937562Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.08560","last_updated":"2020-12-07T17:59:02Z","snapshot_observed_at":"2026-08-11T16:54:05.338986Z","submitted_at":"2019-03-19T16:53:11Z","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.08560","snapshot_observed_at":"2026-08-11T18:53:09.945673Z","title":"Sur- prises in high-dimensional ridgeless least squares interpolation","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.945673Z"},"links":{"cited_paper":"/paper/1903.08560","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:4e444fe8ea82fcca3fc33af110e4d83ce5320950a19f0e4be4d814853ef2fc26","observation_id":"ac4dc5cd-0d4d-4ac1-9a89-0ca169f4ec6f","resolution":{"observed_at":"2026-08-11T18:53:09.945673Z","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":"2026-08-11T18:53:09.956777Z","title":"9.4: Recursive least squares","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.956777Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:1f120f187de7e1a37e00a1bd9a66cac5437e44dbcd605f9f250e8c58b8534677","observation_id":"c6e8c9c4-3cc7-4213-8e9d-1713be1973ff","resolution":{"observed_at":"2026-08-11T18:53:09.956777Z","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":"2026-08-11T18:53:09.971261Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.971261Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:34433a23a5942fb6e4430788c498447a2c12259286e7d0fcaa0507ab228fe8d6","observation_id":"76b5b47d-1026-4df3-a176-608515a3bb3a","resolution":{"observed_at":"2026-08-11T18:53:09.971261Z","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":"2026-08-11T18:53:09.984266Z","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":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.984266Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:5bccd33529ec65aa104671835d5f2da926115f4296c05e6c21cfbc86a7a58576","observation_id":"0e892211-2bf0-4b0b-85c6-9ddc3873d0b0","resolution":{"observed_at":"2026-08-11T18:53:09.984266Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.02136","last_updated":"2018-10-03T07:32:57Z","snapshot_observed_at":"2026-08-02T06:41:33.803920Z","submitted_at":"2016-10-07T04:06:01Z","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02136","snapshot_observed_at":"2026-08-11T18:53:09.993571Z","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":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:09.993571Z"},"links":{"cited_paper":"/paper/1610.02136","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:fbe034bb51eb7bf29e7d817bc756fcc5189530c4563872345a9943196506fbb3","observation_id":"187fb769-4a7b-4fbb-a013-370e59e7a68f","resolution":{"observed_at":"2026-08-11T18:53:09.993571Z","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":"2026-08-11T18:53:10.007408Z","title":"Using self- supervised learning can improve model robustness and uncertainty","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.007408Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:b394cc0f69f38d7f21422afc5574a07d2bc5165344bd4ccb09544a40b3b7f70f","observation_id":"139eba2f-8743-4042-a8e2-8104d9cc9bde","resolution":{"observed_at":"2026-08-11T18:53:10.007408Z","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":"2026-08-11T18:53:10.021547Z","title":"Probabilistic backpropagation for scalable learning of bayesian neural networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.021547Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:7659efecca9f0cb9cd12e9a1bb7ccd166691d73a9f0a28977d309ee56bec00f1","observation_id":"2406deba-5a40-4409-a9e5-5ba238c6131c","resolution":{"observed_at":"2026-08-11T18:53:10.021547Z","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":"2026-08-11T18:53:10.038019Z","title":"Efficient computation of normalized maximum like- lihood coding for gaussian mixtures with its applications to optimal clustering","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.038019Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:0813732bee18d7ff0dc6986d57fbc998799c9de21e1d78917a544e8e17fc199c","observation_id":"42fbbccd-2119-424c-979b-876f422905dc","resolution":{"observed_at":"2026-08-11T18:53:10.038019Z","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":"2026-08-11T18:53:10.047879Z","title":"Hoerl and R Kennard","venue":null,"work_id":null,"year":1970},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.047879Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:2cdb4ed28408cafbc57d59eb90b5369919d8a5b564d4a91d523cdd44a7828a23","observation_id":"768a8355-f3c9-48fd-9795-4cf3a913ff6b","resolution":{"observed_at":"2026-08-11T18:53:10.047879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1112.5745","last_updated":"2011-12-24T17:53:19Z","snapshot_observed_at":"2026-08-12T12:05:47.570397Z","submitted_at":"2011-12-24T17:53:19Z","title":"Bayesian Active Learning for Classification and Preference Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1112.5745","snapshot_observed_at":"2026-08-11T18:53:10.069384Z","title":"Bayesian active learning for classification and preference learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.069384Z"},"links":{"cited_paper":"/paper/1112.5745","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:cd84b596867f6e093f3f301c68b6b65ae637b0b5cc6cfa678e50541510df0f0a","observation_id":"cd34d54a-d044-4598-8ecf-3cfe94222695","resolution":{"observed_at":"2026-08-11T18:53:10.069384Z","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":"2026-08-11T18:53:10.093629Z","title":"Densely connected convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.093629Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:f3a19e2c80f55313553a7a1e81763a7bef8e1d0b6ffde2327f857e1671536d68","observation_id":"e9ec9086-3267-4838-8098-e0a30d96a286","resolution":{"observed_at":"2026-08-11T18:53:10.093629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.15258","last_updated":"2021-11-30T10:17:58Z","snapshot_observed_at":"2026-08-12T19:15:39.285450Z","submitted_at":"2021-11-30T10:17:58Z","title":"DeepAL: Deep Active Learning in Python","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.15258","snapshot_observed_at":"2026-08-11T18:53:10.110693Z","title":"Deepal: Deep active learning in python","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.110693Z"},"links":{"cited_paper":"/paper/2111.15258","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:bbb3eea595b347d4d9267e82068a3a1a6af6124585ee698af0a271c4dd61a82e","observation_id":"54b61527-45e9-4e27-9529-7fb83456252e","resolution":{"observed_at":"2026-08-11T18:53:10.110693Z","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":"2026-08-11T18:53:10.120661Z","title":"An introduc- tion to statistical learning, volume 112","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.120661Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:468b6910d679755581438042ca55ed5558b01727c5481c157f5904ca474055c4","observation_id":"e8f44783-9e38-4a5e-8123-6d03bc82308e","resolution":{"observed_at":"2026-08-11T18:53:10.120661Z","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":"2026-08-11T18:53:10.127176Z","title":"Fantastic generalization measures and where to find them","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.127176Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:a2e735addb6858720ef2bd16f96ad26c2ac54c56fe35e051692603fc263132e2","observation_id":"e6f4d126-07cb-41cd-97be-e31722313c27","resolution":{"observed_at":"2026-08-11T18:53:10.127176Z","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":"2026-08-11T18:53:10.134247Z","title":"On the complexity of linear prediction: Risk bounds, margin bounds, and regularization","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.134247Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:9603d49b229ca4c24c723f4c2f6fb74884295b8236eb24535d5867024e1c0d93","observation_id":"d72bbd94-c720-4da2-a5e3-52191da9c437","resolution":{"observed_at":"2026-08-11T18:53:10.134247Z","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":"2026-08-11T18:53:10.147304Z","title":"Balancing specialization, generalization, and compression for detection and track- ing","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.147304Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:8c01a24dc103db6286a425386957ffbdad104f7a464edafb9489c3478f5b0b71","observation_id":"837a9b83-b4d4-4ce7-839c-278a4cd43e94","resolution":{"observed_at":"2026-08-11T18:53:10.147304Z","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":"2026-08-11T18:53:16.983482Z","title":"The cifar-10 dataset","venue":null,"work_id":"4fc2755d-f65b-4735-b628-6f78a5326f90","year":2014},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.162170Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:f8fcd5ed3b2a418c7f04a109fe8fe84df0b3caa888bcfe5f92a13649783dfb03","observation_id":"36ebc282-2a41-462d-b6a7-5283686c2930","resolution":{"observed_at":"2026-08-11T18:53:16.995971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:16.919921Z","title":"Solving least squares problems , vol- ume 15","venue":null,"work_id":"86f8446c-5701-45de-8a3d-3718bffd0762","year":1995},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.181699Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:221b1f2aa8a34448902fd7e10d3c282f1fd0dc7069687505a44b1a2fee8b366e","observation_id":"e7e0585e-6737-447d-b0be-a4fe7489ffcb","resolution":{"observed_at":"2026-08-11T18:53:16.934743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:16.866999Z","title":"MNIST handwritten digit database","venue":null,"work_id":"e6e79bfe-9db3-4792-84c8-919a2b17878a","year":2010},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.199398Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:b9059ecd054643638176c5193505a04946a719bab036d25797b673de5e961a23","observation_id":"28854fb5-9731-4404-97ee-dd79f0b70ced","resolution":{"observed_at":"2026-08-11T18:53:16.883721Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:16.791771Z","title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","venue":null,"work_id":"4410e817-881c-4bbf-a439-ad0bae98fbaf","year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.215606Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:316f2d904a531f1dc50beec4f0033e66b6552c046129a5a3f976cf34793b6979","observation_id":"e0883a7e-06aa-49aa-bcc6-b538ae81752c","resolution":{"observed_at":"2026-08-11T18:53:16.814762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:16.690096Z","title":"Near-optimal linear regression under distribution shift","venue":null,"work_id":"c4631283-5a36-427e-9c7c-6089d1b50267","year":2021},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.224823Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:5477398980664530855a2059cc5337f5aea1502a064e184c1ac2720befb48952","observation_id":"99d05c64-280c-463f-931d-c3c1256853b0","resolution":{"observed_at":"2026-08-11T18:53:16.702162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:16.571726Z","title":"Measuring the intrinsic dimension of objective landscapes","venue":null,"work_id":"d2ca4546-0989-480d-b82d-cac3957833ea","year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.247765Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:6205fecc5683b3656c0529a9edcc28d1bbacabbeea908552faed2afa9112968f","observation_id":"d1f82d82-5f45-45ff-842c-961b57023279","resolution":{"observed_at":"2026-08-11T18:53:16.614832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:16.484749Z","title":null,"venue":null,"work_id":"c373a77f-63d5-487d-b59d-6238e659adfa","year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.259295Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:40823ed7ac13845c62c98cda599738fd90c0c10a19da3c86d5fb5dabcde39737","observation_id":"6bdb3df7-2e68-40cc-a93c-d896a695a353","resolution":{"observed_at":"2026-08-11T18:53:16.514289Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:16.404854Z","title":"Just interpolate: Kernel ridgeless re- gression can generalize","venue":null,"work_id":"e56142d6-7788-4000-afb7-60a0a4cd9a28","year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.269994Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:b7411b3df6f094e59e900365614068fed770825c9a29a7c3cdc05626761c24bd","observation_id":"4fbf62a1-a14c-46d3-b5e2-8f3d59bfc686","resolution":{"observed_at":"2026-08-11T18:53:16.435698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:16.296368Z","title":"Ridge regression: Structure, cross-validation, and sketching","venue":null,"work_id":"ce2dfd4f-ec70-49a7-a3c3-1c1067346196","year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.285392Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:0209166f04b10f5804c486547208008dc8d9b60f3aadf4a4876527a7592cad64","observation_id":"a9a30069-bb44-40da-b77e-8af5a0adb82b","resolution":{"observed_at":"2026-08-11T18:53:16.333934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:16.199609Z","title":"Energy-based out-of- distribution detection","venue":null,"work_id":"9e724aa4-61f0-4e8d-972b-2574499a926a","year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.295427Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:9795e0adca23c05417d404ab3f75532eae47d302c459492c584396eab0f19997","observation_id":"930fc5df-87b7-46f2-b465-99d38d5e39d4","resolution":{"observed_at":"2026-08-11T18:53:16.244750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:16.124320Z","title":"Deep learning face at- tributes in the wild","venue":null,"work_id":"cb0b4a2d-de88-4f8d-8dd7-7226183b01ad","year":2015},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.302608Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:ce8af46c6ecc6f311ed9c8a6dc22dabf1f02b4dac7a5e0c94677d5dd448b5e64","observation_id":"648cfe01-a00a-4b15-953f-a2cc0d001f6b","resolution":{"observed_at":"2026-08-11T18:53:16.153142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.06987","last_updated":"2021-01-28T15:16:12Z","snapshot_observed_at":"2026-08-07T16:40:27.049046Z","submitted_at":"2019-12-15T06:05:14Z","title":"The Generalization Error of the Minimum-norm Solutions for Over-parameterized Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.06987","snapshot_observed_at":"2026-08-11T18:53:10.312485Z","title":"On the generalization properties of minimum- norm solutions for over-parameterized neural network models","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.312485Z"},"links":{"cited_paper":"/paper/1912.06987","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:27425f21474da7f73aa12a94a9eafd3b094a53c18920c73cafc4d57851e8c6e8","observation_id":"8334df0e-6608-4cce-9ef8-b9d608e3b7d8","resolution":{"observed_at":"2026-08-11T18:53:10.312485Z","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":"2026-08-11T18:53:16.059289Z","title":"Information-based objective functions for active data selection","venue":null,"work_id":"5bb3c66f-6951-40f4-af41-cdb871a6d9b6","year":1992},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.321594Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:6d50f030d974ad8f5ba8ba555ae41c4d07e01050ac002a2373caab42e2a36b04","observation_id":"60eaa49c-cc02-42e1-b708-18c60eb2a359","resolution":{"observed_at":"2026-08-11T18:53:16.088010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-11T18:53:10.329846Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.329846Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:d5b199c5a2a92937bd9972b456bd60d8900c1e853649858a8ade27d641ed2869","observation_id":"f0d90f6b-10c8-4bad-a197-776cc5c947d4","resolution":{"observed_at":"2026-08-11T18:53:10.329846Z","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":"2026-08-11T18:53:15.978956Z","title":"Universal prediction","venue":null,"work_id":"30446aa5-e82c-478b-b895-026a4228239a","year":1998},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.337862Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:5f42f54674242fa8b44324f2e648246db6f2f8e9e07dae85f5a93438006689c4","observation_id":"18c605f6-657a-4540-8dbc-e430b6869812","resolution":{"observed_at":"2026-08-11T18:53:16.005314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.01861","last_updated":"2017-09-01T05:43:01Z","snapshot_observed_at":"2026-08-04T22:38:07.213976Z","submitted_at":"2017-08-06T08:22:40Z","title":"Normalized Maximum Likelihood with Luckiness for Multivariate Normal Distributions","version":3},"cited_work":{"arxiv_id":"1708.01861","doi":null,"metadata_source":"pith","pith_arxiv_id":"1708.01861","snapshot_observed_at":"2026-08-11T18:53:11.335968Z","title":"Normalized Maximum Likelihood with Luckiness for Multivariate Normal Distributions","venue":"math.ST","work_id":"84bb2f46-2e72-4e7c-a3d5-d77ff551821d","year":2017},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.345655Z"},"links":{"cited_paper":"/paper/1708.01861","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:610e781deef106a6f2d3cae44e614480ed65adfe0cf3ad61d3439f6be2add2cc","observation_id":"989dbfa4-6484-42b9-8d3b-8033a0b98adb","resolution":{"observed_at":"2026-08-11T18:53:11.344258Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:15.869785Z","title":"Harmless interpolation of noisy data in regression","venue":null,"work_id":"9ec93d67-005c-46c4-8217-9a8913e44116","year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.355566Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:84ec2ae9734f98fbde98d0bf0d72efc3c31973070fa5544471bbf405095c89c3","observation_id":"c63ee255-2856-47ba-9bc5-e8a124209cde","resolution":{"observed_at":"2026-08-11T18:53:15.911221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01897","last_updated":"2021-04-29T04:45:47Z","snapshot_observed_at":"2026-08-12T03:11:12.770617Z","submitted_at":"2020-03-04T05:19:09Z","title":"Optimal Regularization Can Mitigate Double Descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.01897","snapshot_observed_at":"2026-08-11T18:53:10.365287Z","title":"Optimal regu- larization can mitigate double descent","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.365287Z"},"links":{"cited_paper":"/paper/2003.01897","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:56ae4dd8cae9265d587b37eb886563fb10c3940e55881907577efb96ed7217a4","observation_id":"2f6ef4e8-bd5f-4d7c-ae12-595303d66d7a","resolution":{"observed_at":"2026-08-11T18:53:10.365287Z","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":"2026-08-11T18:53:15.724840Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"d8c923ba-2871-4510-b9a9-bc0b54427414","year":2011},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.376231Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:24e19baa6270ca11be367f758bc45ffa316efa0589e45d613f57fe37439bdbe8","observation_id":"3fbea74d-cfb1-431c-ae2b-9e3a08811021","resolution":{"observed_at":"2026-08-11T18:53:15.771923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:15.610472Z","title":"A pac-bayesian approach to spectrally-normalized margin bounds for neural networks","venue":null,"work_id":"d884ab9b-fcda-4fb6-b00b-ce2c6d25b818","year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.398656Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:0a78db1ef9bca953babf69511ec73888ef90f7d2a15e66daad94bf7cafb5ac55","observation_id":"1b4b99c7-809c-42de-a93c-cc5ffbb1936e","resolution":{"observed_at":"2026-08-11T18:53:15.638083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.09610","last_updated":"2021-06-04T21:57:42Z","snapshot_observed_at":"2026-08-05T14:27:10.362888Z","submitted_at":"2020-10-19T15:46:48Z","title":"Increasing Depth Leads to U-Shaped Test Risk in Over-parameterized Convolutional Networks","version":2},"cited_work":{"arxiv_id":"2010.09610","doi":null,"metadata_source":"pith","pith_arxiv_id":"2010.09610","snapshot_observed_at":"2026-08-11T18:53:11.237441Z","title":"Increasing Depth Leads to U-Shaped Test Risk in Over-parameterized Convolutional Networks","venue":"cs.LG","work_id":"d55a3499-16bc-4554-ad45-cdc6e9b401e9","year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.407653Z"},"links":{"cited_paper":"/paper/2010.09610","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:64b62c0c05c61565f1cc5988ba3905a1ce7dd724e67c7705b81de03f63145e90","observation_id":"7b5df05b-5fe7-41b7-89b8-2bef2763038c","resolution":{"observed_at":"2026-08-11T18:53:11.250377Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:10.415984Z","title":"Olson, William La Cava, Patryk Orzechowski, Ryan J","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.415984Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:0c12db54ca5671cc64de8ac0ecde973235229b8049281e5594f5e71a58b7b4d0","observation_id":"bcd1c617-fccd-4893-925a-ba8f920db91b","resolution":{"observed_at":"2026-08-11T18:53:10.415984Z","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":"2026-08-11T18:53:15.474836Z","title":"Outlier exposure with confidence control for out-of-distribution detection","venue":null,"work_id":"93d8f644-372a-4213-adc4-b3e07b022f42","year":2021},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.422843Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:d073b2f7193e18339893df8b8fc316b4e7bb0b105ae1d12a6345c35b2ce6972a","observation_id":"b2e80e63-19e4-40f0-8a02-8a584eb35b66","resolution":{"observed_at":"2026-08-11T18:53:15.519345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:15.314207Z","title":"Practical black-box attacks against machine learning","venue":null,"work_id":"810f6314-6bfd-4f13-a592-fb4641a5eb16","year":2017},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.429257Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:0d2fc08a2551998d2d3e9d061bdd4135f493ef1a734e988b12239985e705ed47","observation_id":"a5e7621c-0bb4-48bd-a1d1-5f1a82d67d35","resolution":{"observed_at":"2026-08-11T18:53:15.341100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:15.203695Z","title":"Evaluation methods in face recognition","venue":null,"work_id":"43fa164b-8bda-46a0-8d35-32e046d9ab27","year":2011},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.437609Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:2d2515d52a81ac056c71fe8a9a04cc3215ff8c08edd7e01b4a0f646b1db81f79","observation_id":"bb7db2a6-b2c9-48fb-967d-9d05cecbfae4","resolution":{"observed_at":"2026-08-11T18:53:15.245535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:15.084743Z","title":"Ad- versarial robustness through local linearization","venue":null,"work_id":"376bb127-adbf-406f-ad8c-6b64d0badec9","year":2019},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.448370Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:14992c0c11f2198b20edd077d5f6ce447c38bac57852e0c7595db3e0e25e7643","observation_id":"26429507-18f8-4d62-8975-d793e5e3c0c1","resolution":{"observed_at":"2026-08-11T18:53:15.110221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:15.024749Z","title":"Information-based complexity, feedback and dynamics in convex programming","venue":null,"work_id":"0ccbd827-0c40-408d-9dbf-d89769744fea","year":2011},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.457125Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:cb73ade91cedc0ecb15ca07e65d81960866fc416f236c90638e66405e7d7c90f","observation_id":"2e8632da-596e-4872-abce-e2935a3a1ebc","resolution":{"observed_at":"2026-08-11T18:53:15.046776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:10.465470Z","title":"A survey of deep active learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.465470Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:87b354a30b562debc3d925f198a3f3710c08c4e14dff1b3d4e2c4ecfc0d9dd3a","observation_id":"577978c8-aa93-4422-bfef-6210ca65b524","resolution":{"observed_at":"2026-08-11T18:53:10.465470Z","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":"2026-08-11T18:53:14.867770Z","title":"Mdl regression and denoising","venue":null,"work_id":"995d5299-b7ce-44dc-8f74-81b0e6f6a2a5","year":2004},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.473873Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:168747204767ad5e0589f3ce9fc7b5f03c9c803a96888a958e5d0e9ae68ab9fd","observation_id":"ad11f546-782b-41c9-bdc5-6e31f583cef2","resolution":{"observed_at":"2026-08-11T18:53:14.888139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:14.744818Z","title":"Defense-GAN: Protect- ing classifiers against adversarial attacks using generative models","venue":null,"work_id":"f93715a2-e77c-4301-9f8b-d93f6fc164cb","year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.481090Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:86ff1d9491306931a7431f9011867eda7e2ca66791cb16a0ebe3f6be842982dd","observation_id":"71631046-eb9c-41d0-9540-620a2ebce052","resolution":{"observed_at":"2026-08-11T18:53:14.760936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:14.674871Z","title":"Detecting out-of-distribution exam- ples with Gram matrices","venue":null,"work_id":"ecb1cedd-54e3-4084-964d-8b3c9ec91ba6","year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.488622Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:4b1e5433cdbb6fb6f137e9dc4c07f20fc07d30e5fc5463c8e7ba756568cdeac3","observation_id":"f4a7c16e-32d1-4f6d-88f4-3b06cb28af6b","resolution":{"observed_at":"2026-08-11T18:53:14.682715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:14.540989Z","title":"Toward open set recognition","venue":null,"work_id":"75ffa166-531d-4818-99ca-270a7d674ff1","year":2012},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.495093Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:d9abd778ebc097f20ef2c0874df5168a855f314d34f8385719eb65bcda9fcf18","observation_id":"a7de1edf-c25c-43bf-a31d-c7063ce7e3a4","resolution":{"observed_at":"2026-08-11T18:53:14.584752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.00489","last_updated":"2018-06-01T10:17:23Z","snapshot_observed_at":"2026-07-06T05:53:39.440274Z","submitted_at":"2017-08-01T19:50:53Z","title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.00489","snapshot_observed_at":"2026-08-11T18:53:10.506001Z","title":"Active learning for convolutional neural networks: A core-set approach","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.506001Z"},"links":{"cited_paper":"/paper/1708.00489","citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:c222165d1a1e228022688331b247c762949b44529c4384e4ba81232b1a0ca7da","observation_id":"74379126-262c-45e5-9b8b-2c28d51b924d","resolution":{"observed_at":"2026-08-11T18:53:10.506001Z","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":"2026-08-11T18:53:14.414861Z","title":"On the asymptotic distribution of ridge re- gression estimators using training and test samples","venue":null,"work_id":"1a1430c8-a55d-4176-9c65-2b3da29db08f","year":2020},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.515252Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:11e0e2809bfecdce0e2f34c72519f6eb38eb2f8f1dddeb558eb068283bdb25db","observation_id":"2dfc783d-bc45-4d74-8e0e-72385aef6f4d","resolution":{"observed_at":"2026-08-11T18:53:14.453357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:14.250064Z","title":"Convolutional neural net- works applied to house numbers digit classification","venue":null,"work_id":"0af61718-605b-4c18-8001-96220f9734f5","year":2012},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.522178Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:b7f01075ca8624701241ed4183cb336b1da2dc0feda6c68615e3ea6fee1ee78b","observation_id":"93a04cc2-3dc7-4aac-b858-6bb5734fb404","resolution":{"observed_at":"2026-08-11T18:53:14.294892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:14.104888Z","title":"Minimum norm solutions do not always generalize well for over-parameterized problems.stat, 1050:16, 2018","venue":null,"work_id":"8ee65cbe-164f-4c50-b0cf-e1f672e965ed","year":2018},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.531343Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:57057d5b558c1c424b42bc3ef479174c695ad5651c7276e742baf9e385c37d04","observation_id":"15b44e18-6225-4899-a7df-2e0bfba9da8d","resolution":{"observed_at":"2026-08-11T18:53:14.144850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:13.936392Z","title":"Learn- ability, stability and uniform convergence","venue":null,"work_id":"c56e8a58-4a14-4828-8f67-e110226775d8","year":2010},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.540481Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:3d65e81fff2fd2676e78f8f2e1b99ef509a3f636b978011ece285f218969b50e","observation_id":"c3b95e30-e300-4907-9a40-5f3d04b4f5f9","resolution":{"observed_at":"2026-08-11T18:53:13.984755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:13.793796Z","title":"The sample complexity of learning linear predictors with the squared loss","venue":null,"work_id":"1a8a8e37-46af-4882-ac9e-233761f04227","year":2015},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.546396Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:55b95df4f32ead5af91c1973114fde04a01ff3a340877975af69648f9f0ace44","observation_id":"635da1eb-b0a0-4ac4-b0b4-b03df967c276","resolution":{"observed_at":"2026-08-11T18:53:13.825024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:13.644749Z","title":"Universal active learning via conditional mutual information minimization","venue":null,"work_id":"91fdd5e3-2fef-4b56-9240-b4393d8f4d7d","year":2021},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.555182Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:22817cab4ad79b2368607a58302a2143d6d02e7bb7b4dfc12080ee17408a4299","observation_id":"60ec9ca7-6adc-4e2d-974e-124d221bd150","resolution":{"observed_at":"2026-08-11T18:53:13.694760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:13.559170Z","title":"Minimax active learning via minimal model capacity","venue":null,"work_id":"24d2ce7f-8f91-47ff-ab6e-25f3db870512","year":2019},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.560981Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:d96e14a7d77816f3b795a3e431a4da561a16193a366f5f59c13cd1e533459cdb","observation_id":"0f5260ed-70be-473c-a182-3ee00d670ec4","resolution":{"observed_at":"2026-08-11T18:53:13.568883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T18:53:13.473718Z","title":"Universal sequential coding of single messages.Prob- lemy Peredachi Informatsii, 23(3):3–17, 1987","venue":null,"work_id":"22af5ba0-c5b0-4667-9fca-7cdf2507d258","year":1987},"citing_paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-11T18:53:10.567319Z"},"links":{"citing_paper":"/paper/2412.07520"},"observation_digest":"sha256:6ca1774b712501615b47368853ce0e74c3d558b086f82dd83ef6961811818da8","observation_id":"3bee3eb7-771f-4681-8b0b-e405d09b0c34","resolution":{"observed_at":"2026-08-11T18:53:13.501123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.07520","last_updated":"2024-12-10T13:58:19Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T07:00:26.127526Z","submitted_at":"2024-12-10T13:58:19Z","title":"Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":65,"verified_exact":3,"verified_fuzzy":32},"total_outbound_references":130},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 100 of 130 outbound references and 0 inbound Pith citation observations for arXiv:2412.07520."}