{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JZW7YMUATXVNCOMTRJJQY65XEM","short_pith_number":"pith:JZW7YMUA","schema_version":"1.0","canonical_sha256":"4e6dfc32809dead139938a530c7bb72323ef43ac95702837a0006c3c9e044f9e","source":{"kind":"arxiv","id":"1612.01474","version":3},"attestation_state":"computed","paper":{"title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Pritzel, Balaji Lakshminarayanan, Charles Blundell","submitted_at":"2016-12-05T18:54:43Z","abstract_excerpt":"Deep neural networks (NNs) are powerful black box predictors that have recently achieved impressive performance on a wide spectrum of tasks. Quantifying predictive uncertainty in NNs is a challenging and yet unsolved problem. Bayesian NNs, which learn a distribution over weights, are currently the state-of-the-art for estimating predictive uncertainty; however these require significant modifications to the training procedure and are computationally expensive compared to standard (non-Bayesian) NNs. We propose an alternative to Bayesian NNs that is simple to implement, readily parallelizable, r"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1612.01474","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-05T18:54:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4156a3e245f4dcffa33339e3d82899a385dc5dc830e7c87ab6d7d105a2f1ab89","abstract_canon_sha256":"0777a514db4d09cb5458a3cfd52f9437006348fab805e6e567e4809603336fc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:22.317224Z","signature_b64":"2mm+tse1Tlctu+PWlBdM1e2HuFhbB54LahHCDaTiLzYdJU8d7Bs5U0SXcT11ESmizC6KjY80M2yZ/DpJeByoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e6dfc32809dead139938a530c7bb72323ef43ac95702837a0006c3c9e044f9e","last_reissued_at":"2026-05-18T00:31:22.316809Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:22.316809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Pritzel, Balaji Lakshminarayanan, Charles Blundell","submitted_at":"2016-12-05T18:54:43Z","abstract_excerpt":"Deep neural networks (NNs) are powerful black box predictors that have recently achieved impressive performance on a wide spectrum of tasks. Quantifying predictive uncertainty in NNs is a challenging and yet unsolved problem. Bayesian NNs, which learn a distribution over weights, are currently the state-of-the-art for estimating predictive uncertainty; however these require significant modifications to the training procedure and are computationally expensive compared to standard (non-Bayesian) NNs. We propose an alternative to Bayesian NNs that is simple to implement, readily parallelizable, r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01474","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1612.01474","created_at":"2026-05-18T00:31:22.316872+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.01474v3","created_at":"2026-05-18T00:31:22.316872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01474","created_at":"2026-05-18T00:31:22.316872+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZW7YMUATXVN","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZW7YMUATXVNCOMT","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZW7YMUA","created_at":"2026-05-18T12:30:25.849896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"1906.08312","citing_title":"Calibrated Model-Based Deep Reinforcement Learning","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23189","citing_title":"Empirical Bayes Conformal Prediction for Vision and Language Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2601.00990","citing_title":"Uncertainty-Calibrated Explainable Artificial Intelligence for Fetal Ultrasound Plane Classification: A Systematic Review","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2603.03190","citing_title":"Expectation and Acoustic Neural Network Representations Enhance Music Identification from Brain Activity","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17433","citing_title":"VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2510.03046","citing_title":"Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2601.16391","citing_title":"Extraction of the color dipole amplitude with physics-informed neural networks","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27098","citing_title":"Ensemble-Based Uncertainty Estimation for Code Correctness Estimation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12762","citing_title":"Multi-Quantile Regression for Extreme Precipitation Downscaling","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13595","citing_title":"Inducing Artificial Uncertainty in Language Models","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29184","citing_title":"Cell-induced densification and tether formation in fibrous extracellular matrices with biomimetic physics-informed neural networks","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22688","citing_title":"COMPASS: A Unified Decision-Intelligence System for Navigating Performance Trade-off in HPC","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04997","citing_title":"DualTCN: A Physics-Constrained Temporal Convolutional Network for 2 Time-Domain Marine CSEM Inversion","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08977","citing_title":"Testing the Assumptions of Active Learning for Translation Tasks with Few Samples","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08974","citing_title":"Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06032","citing_title":"Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11507","citing_title":"Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14133","citing_title":"AI-assisted modeling and Bayesian inference of unpolarized quark transverse momentum distributions from Drell-Yan data","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15271","citing_title":"SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZW7YMUATXVNCOMTRJJQY65XEM","json":"https://pith.science/pith/JZW7YMUATXVNCOMTRJJQY65XEM.json","graph_json":"https://pith.science/api/pith-number/JZW7YMUATXVNCOMTRJJQY65XEM/graph.json","events_json":"https://pith.science/api/pith-number/JZW7YMUATXVNCOMTRJJQY65XEM/events.json","paper":"https://pith.science/paper/JZW7YMUA"},"agent_actions":{"view_html":"https://pith.science/pith/JZW7YMUATXVNCOMTRJJQY65XEM","download_json":"https://pith.science/pith/JZW7YMUATXVNCOMTRJJQY65XEM.json","view_paper":"https://pith.science/paper/JZW7YMUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.01474&json=true","fetch_graph":"https://pith.science/api/pith-number/JZW7YMUATXVNCOMTRJJQY65XEM/graph.json","fetch_events":"https://pith.science/api/pith-number/JZW7YMUATXVNCOMTRJJQY65XEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZW7YMUATXVNCOMTRJJQY65XEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZW7YMUATXVNCOMTRJJQY65XEM/action/storage_attestation","attest_author":"https://pith.science/pith/JZW7YMUATXVNCOMTRJJQY65XEM/action/author_attestation","sign_citation":"https://pith.science/pith/JZW7YMUATXVNCOMTRJJQY65XEM/action/citation_signature","submit_replication":"https://pith.science/pith/JZW7YMUATXVNCOMTRJJQY65XEM/action/replication_record"}},"created_at":"2026-05-18T00:31:22.316872+00:00","updated_at":"2026-05-18T00:31:22.316872+00:00"}