{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7M2RUUYNWY5VXYDA4QNZBRZRZC","short_pith_number":"pith:7M2RUUYN","schema_version":"1.0","canonical_sha256":"fb351a530db63b5be060e41b90c731c8a9faf996f646f9c6e6cf580cbcd378ee","source":{"kind":"arxiv","id":"1909.13550","version":3},"attestation_state":"computed","paper":{"title":"Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Karl-Philipp Kortmann, Max-Heinrich Laves, Sontje Ihler, Tobias Ortmaier","submitted_at":"2019-09-30T09:29:44Z","abstract_excerpt":"Model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. The uncertainty does not represent the model error well. In this paper, temperature scaling is extended to dropout variational inference to calibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration of uncertainty. The effectiveness of this approach is evaluated on CIFAR-10/100 for recent CNN architectures. Experimental results show, that temperature scaling considerably reduces miscalibration by means of UCE and ena"},"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":"1909.13550","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-30T09:29:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d22127658f382f249ec4f2969c90f192ae474d60fd2b1e1a100675c606aae491","abstract_canon_sha256":"f06069ec585f0d471bc43b0918266dae4ba6eb10f962b554e8948577bbf9ca2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:01.944773Z","signature_b64":"Rfvmgu+mxPgDAMiopRSTpeecRWidZPE94d9aX3vSSDVnpNsOJXtGL55FV2j2zYIsQeP4yrwQ8QZQJy7vPJ3JCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb351a530db63b5be060e41b90c731c8a9faf996f646f9c6e6cf580cbcd378ee","last_reissued_at":"2026-07-05T00:20:01.944238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:01.944238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Karl-Philipp Kortmann, Max-Heinrich Laves, Sontje Ihler, Tobias Ortmaier","submitted_at":"2019-09-30T09:29:44Z","abstract_excerpt":"Model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. The uncertainty does not represent the model error well. In this paper, temperature scaling is extended to dropout variational inference to calibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration of uncertainty. The effectiveness of this approach is evaluated on CIFAR-10/100 for recent CNN architectures. Experimental results show, that temperature scaling considerably reduces miscalibration by means of UCE and ena"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13550","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.13550/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":"1909.13550","created_at":"2026-07-05T00:20:01.944301+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.13550v3","created_at":"2026-07-05T00:20:01.944301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13550","created_at":"2026-07-05T00:20:01.944301+00:00"},{"alias_kind":"pith_short_12","alias_value":"7M2RUUYNWY5V","created_at":"2026-07-05T00:20:01.944301+00:00"},{"alias_kind":"pith_short_16","alias_value":"7M2RUUYNWY5VXYDA","created_at":"2026-07-05T00:20:01.944301+00:00"},{"alias_kind":"pith_short_8","alias_value":"7M2RUUYN","created_at":"2026-07-05T00:20:01.944301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16570","citing_title":"A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7M2RUUYNWY5VXYDA4QNZBRZRZC","json":"https://pith.science/pith/7M2RUUYNWY5VXYDA4QNZBRZRZC.json","graph_json":"https://pith.science/api/pith-number/7M2RUUYNWY5VXYDA4QNZBRZRZC/graph.json","events_json":"https://pith.science/api/pith-number/7M2RUUYNWY5VXYDA4QNZBRZRZC/events.json","paper":"https://pith.science/paper/7M2RUUYN"},"agent_actions":{"view_html":"https://pith.science/pith/7M2RUUYNWY5VXYDA4QNZBRZRZC","download_json":"https://pith.science/pith/7M2RUUYNWY5VXYDA4QNZBRZRZC.json","view_paper":"https://pith.science/paper/7M2RUUYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.13550&json=true","fetch_graph":"https://pith.science/api/pith-number/7M2RUUYNWY5VXYDA4QNZBRZRZC/graph.json","fetch_events":"https://pith.science/api/pith-number/7M2RUUYNWY5VXYDA4QNZBRZRZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7M2RUUYNWY5VXYDA4QNZBRZRZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7M2RUUYNWY5VXYDA4QNZBRZRZC/action/storage_attestation","attest_author":"https://pith.science/pith/7M2RUUYNWY5VXYDA4QNZBRZRZC/action/author_attestation","sign_citation":"https://pith.science/pith/7M2RUUYNWY5VXYDA4QNZBRZRZC/action/citation_signature","submit_replication":"https://pith.science/pith/7M2RUUYNWY5VXYDA4QNZBRZRZC/action/replication_record"}},"created_at":"2026-07-05T00:20:01.944301+00:00","updated_at":"2026-07-05T00:20:01.944301+00:00"}