{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SRL3SVGTS22GCU5XSNGGNCRZ7M","short_pith_number":"pith:SRL3SVGT","schema_version":"1.0","canonical_sha256":"9457b954d396b46153b7934c668a39fb34b6735af51556c8411bd5f09005f337","source":{"kind":"arxiv","id":"2003.02037","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty Estimation Using a Single Deep Deterministic Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Joost van Amersfoort, Lewis Smith, Yarin Gal, Yee Whye Teh","submitted_at":"2020-03-04T12:27:36Z","abstract_excerpt":"We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. Our approach, deterministic uncertainty quantification (DUQ), builds upon ideas of RBF networks. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models. By enforcing detectability of changes in the input using a gradient penalty, we are able to reliably detect out of distribution data. Our uncertainty quantification scales well to large datasets, and using a single model"},"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":"2003.02037","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-04T12:27:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"43fbccf5aa8df4c5fd4ba3ee3185b9d2f35067a238ce9452f523dcab0f19c9db","abstract_canon_sha256":"cfd83eb7991813b96599cd2b1daaf7a73e46a9c6562c465ea61885aeef4bcdfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:58.768454Z","signature_b64":"yKVM2ZadYWFDllv3MrsydWAkxGj/C8eGqGeDprEqUfx8o0UIiGB5Tqqbe3LkGKx1hvW70hqrMEMm/x4X33HICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9457b954d396b46153b7934c668a39fb34b6735af51556c8411bd5f09005f337","last_reissued_at":"2026-07-05T01:13:58.768095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:58.768095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Estimation Using a Single Deep Deterministic Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Joost van Amersfoort, Lewis Smith, Yarin Gal, Yee Whye Teh","submitted_at":"2020-03-04T12:27:36Z","abstract_excerpt":"We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. Our approach, deterministic uncertainty quantification (DUQ), builds upon ideas of RBF networks. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models. By enforcing detectability of changes in the input using a gradient penalty, we are able to reliably detect out of distribution data. Our uncertainty quantification scales well to large datasets, and using a single model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02037","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/2003.02037/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":"2003.02037","created_at":"2026-07-05T01:13:58.768153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.02037v2","created_at":"2026-07-05T01:13:58.768153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02037","created_at":"2026-07-05T01:13:58.768153+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRL3SVGTS22G","created_at":"2026-07-05T01:13:58.768153+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRL3SVGTS22GCU5X","created_at":"2026-07-05T01:13:58.768153+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRL3SVGT","created_at":"2026-07-05T01:13:58.768153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRL3SVGTS22GCU5XSNGGNCRZ7M","json":"https://pith.science/pith/SRL3SVGTS22GCU5XSNGGNCRZ7M.json","graph_json":"https://pith.science/api/pith-number/SRL3SVGTS22GCU5XSNGGNCRZ7M/graph.json","events_json":"https://pith.science/api/pith-number/SRL3SVGTS22GCU5XSNGGNCRZ7M/events.json","paper":"https://pith.science/paper/SRL3SVGT"},"agent_actions":{"view_html":"https://pith.science/pith/SRL3SVGTS22GCU5XSNGGNCRZ7M","download_json":"https://pith.science/pith/SRL3SVGTS22GCU5XSNGGNCRZ7M.json","view_paper":"https://pith.science/paper/SRL3SVGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.02037&json=true","fetch_graph":"https://pith.science/api/pith-number/SRL3SVGTS22GCU5XSNGGNCRZ7M/graph.json","fetch_events":"https://pith.science/api/pith-number/SRL3SVGTS22GCU5XSNGGNCRZ7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRL3SVGTS22GCU5XSNGGNCRZ7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRL3SVGTS22GCU5XSNGGNCRZ7M/action/storage_attestation","attest_author":"https://pith.science/pith/SRL3SVGTS22GCU5XSNGGNCRZ7M/action/author_attestation","sign_citation":"https://pith.science/pith/SRL3SVGTS22GCU5XSNGGNCRZ7M/action/citation_signature","submit_replication":"https://pith.science/pith/SRL3SVGTS22GCU5XSNGGNCRZ7M/action/replication_record"}},"created_at":"2026-07-05T01:13:58.768153+00:00","updated_at":"2026-07-05T01:13:58.768153+00:00"}