{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LAJVPTZBGISY4W3AA7BH4WF6NT","short_pith_number":"pith:LAJVPTZB","schema_version":"1.0","canonical_sha256":"581357cf2132258e5b6007c27e58be6cc72e73fcb49707c67e12642173a5a2d5","source":{"kind":"arxiv","id":"2006.10108","version":2},"attestation_state":"computed","paper":{"title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaji Lakshminarayanan, Dustin Tran, Jeremiah Zhe Liu, Shreyas Padhy, Tania Bedrax-Weiss, Zi Lin","submitted_at":"2020-06-17T19:18:22Z","abstract_excerpt":"Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model. However their practicality in real-time, industrial-scale applications are limited due to their heavy memory and inference cost. This motivates us to study principled approaches to high-quality uncertainty estimation that require only a single deep neural network (DNN). By formalizing the uncertainty quantification as a minimax learning problem, we first identify input distance awareness, i.e., the model's ability to quantify the distance of a testing exa"},"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":"2006.10108","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-17T19:18:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"26bfe928aa988e1356ba130d4ec05f81265ca0ec1cb0d56d60c797cac2f7d292","abstract_canon_sha256":"2588f03f1cee95548435ea8b4035d9a0cbea5b3d60c8b69af6abb23b342f54f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:46:01.896634Z","signature_b64":"pC7OxEwBD98ZVra/BEn3TLWCWV6xltPKcaKFmiRuS8jTlghQwlN09M0mFIb3wrtok/Q5wAm9sfIcCSE68SEaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"581357cf2132258e5b6007c27e58be6cc72e73fcb49707c67e12642173a5a2d5","last_reissued_at":"2026-07-05T01:46:01.896194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:46:01.896194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaji Lakshminarayanan, Dustin Tran, Jeremiah Zhe Liu, Shreyas Padhy, Tania Bedrax-Weiss, Zi Lin","submitted_at":"2020-06-17T19:18:22Z","abstract_excerpt":"Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model. However their practicality in real-time, industrial-scale applications are limited due to their heavy memory and inference cost. This motivates us to study principled approaches to high-quality uncertainty estimation that require only a single deep neural network (DNN). By formalizing the uncertainty quantification as a minimax learning problem, we first identify input distance awareness, i.e., the model's ability to quantify the distance of a testing exa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10108","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.10108/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2006.10108","created_at":"2026-07-05T01:46:01.896250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10108v2","created_at":"2026-07-05T01:46:01.896250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10108","created_at":"2026-07-05T01:46:01.896250+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAJVPTZBGISY","created_at":"2026-07-05T01:46:01.896250+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAJVPTZBGISY4W3A","created_at":"2026-07-05T01:46:01.896250+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAJVPTZB","created_at":"2026-07-05T01:46:01.896250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17187","citing_title":"PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media","ref_index":187,"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":21,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAJVPTZBGISY4W3AA7BH4WF6NT","json":"https://pith.science/pith/LAJVPTZBGISY4W3AA7BH4WF6NT.json","graph_json":"https://pith.science/api/pith-number/LAJVPTZBGISY4W3AA7BH4WF6NT/graph.json","events_json":"https://pith.science/api/pith-number/LAJVPTZBGISY4W3AA7BH4WF6NT/events.json","paper":"https://pith.science/paper/LAJVPTZB"},"agent_actions":{"view_html":"https://pith.science/pith/LAJVPTZBGISY4W3AA7BH4WF6NT","download_json":"https://pith.science/pith/LAJVPTZBGISY4W3AA7BH4WF6NT.json","view_paper":"https://pith.science/paper/LAJVPTZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10108&json=true","fetch_graph":"https://pith.science/api/pith-number/LAJVPTZBGISY4W3AA7BH4WF6NT/graph.json","fetch_events":"https://pith.science/api/pith-number/LAJVPTZBGISY4W3AA7BH4WF6NT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAJVPTZBGISY4W3AA7BH4WF6NT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAJVPTZBGISY4W3AA7BH4WF6NT/action/storage_attestation","attest_author":"https://pith.science/pith/LAJVPTZBGISY4W3AA7BH4WF6NT/action/author_attestation","sign_citation":"https://pith.science/pith/LAJVPTZBGISY4W3AA7BH4WF6NT/action/citation_signature","submit_replication":"https://pith.science/pith/LAJVPTZBGISY4W3AA7BH4WF6NT/action/replication_record"}},"created_at":"2026-07-05T01:46:01.896250+00:00","updated_at":"2026-07-05T01:46:01.896250+00:00"}