{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Q4OMMVUGGMR6KIK3SRVZUJSJKW","short_pith_number":"pith:Q4OMMVUG","schema_version":"1.0","canonical_sha256":"871cc656863323e5215b946b9a264955a8b9033723b0aa3e31255489e496211d","source":{"kind":"arxiv","id":"1910.14179","version":1},"attestation_state":"computed","paper":{"title":"Heteroscedastic Calibration of Uncertainty Estimators in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bindya Venkatesh, Jayaraman J. Thiagarajan","submitted_at":"2019-10-30T23:22:39Z","abstract_excerpt":"The role of uncertainty quantification (UQ) in deep learning has become crucial with growing use of predictive models in high-risk applications. Though a large class of methods exists for measuring deep uncertainties, in practice, the resulting estimates are found to be poorly calibrated, thus making it challenging to translate them into actionable insights. A common workaround is to utilize a separate recalibration step, which adjusts the estimates to compensate for the miscalibration. Instead, we propose to repurpose the heteroscedastic regression objective as a surrogate for calibration and"},"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":"1910.14179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-10-30T23:22:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9ec3cdd116560036942a50ed8f5ea370b7e6acb6f2a80262c78e670da72eb99a","abstract_canon_sha256":"6f01d74f5412180ffcc8d5fd4443b47f876506b938b8e9e46d01a441eea36133"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:08.303076Z","signature_b64":"6pG9OFt2g3fm8AxoHegJzOA6n1tdeA2xe7ZKFtWlITzLnMtqcag/6RoreTgZ7VkTcNejqjE+1xAG3SWwf5OeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"871cc656863323e5215b946b9a264955a8b9033723b0aa3e31255489e496211d","last_reissued_at":"2026-07-05T00:16:08.302699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:08.302699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heteroscedastic Calibration of Uncertainty Estimators in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bindya Venkatesh, Jayaraman J. Thiagarajan","submitted_at":"2019-10-30T23:22:39Z","abstract_excerpt":"The role of uncertainty quantification (UQ) in deep learning has become crucial with growing use of predictive models in high-risk applications. Though a large class of methods exists for measuring deep uncertainties, in practice, the resulting estimates are found to be poorly calibrated, thus making it challenging to translate them into actionable insights. A common workaround is to utilize a separate recalibration step, which adjusts the estimates to compensate for the miscalibration. Instead, we propose to repurpose the heteroscedastic regression objective as a surrogate for calibration and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.14179","kind":"arxiv","version":1},"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/1910.14179/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":"1910.14179","created_at":"2026-07-05T00:16:08.302753+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.14179v1","created_at":"2026-07-05T00:16:08.302753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.14179","created_at":"2026-07-05T00:16:08.302753+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4OMMVUGGMR6","created_at":"2026-07-05T00:16:08.302753+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4OMMVUGGMR6KIK3","created_at":"2026-07-05T00:16:08.302753+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4OMMVUG","created_at":"2026-07-05T00:16:08.302753+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/Q4OMMVUGGMR6KIK3SRVZUJSJKW","json":"https://pith.science/pith/Q4OMMVUGGMR6KIK3SRVZUJSJKW.json","graph_json":"https://pith.science/api/pith-number/Q4OMMVUGGMR6KIK3SRVZUJSJKW/graph.json","events_json":"https://pith.science/api/pith-number/Q4OMMVUGGMR6KIK3SRVZUJSJKW/events.json","paper":"https://pith.science/paper/Q4OMMVUG"},"agent_actions":{"view_html":"https://pith.science/pith/Q4OMMVUGGMR6KIK3SRVZUJSJKW","download_json":"https://pith.science/pith/Q4OMMVUGGMR6KIK3SRVZUJSJKW.json","view_paper":"https://pith.science/paper/Q4OMMVUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.14179&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4OMMVUGGMR6KIK3SRVZUJSJKW/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4OMMVUGGMR6KIK3SRVZUJSJKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4OMMVUGGMR6KIK3SRVZUJSJKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4OMMVUGGMR6KIK3SRVZUJSJKW/action/storage_attestation","attest_author":"https://pith.science/pith/Q4OMMVUGGMR6KIK3SRVZUJSJKW/action/author_attestation","sign_citation":"https://pith.science/pith/Q4OMMVUGGMR6KIK3SRVZUJSJKW/action/citation_signature","submit_replication":"https://pith.science/pith/Q4OMMVUGGMR6KIK3SRVZUJSJKW/action/replication_record"}},"created_at":"2026-07-05T00:16:08.302753+00:00","updated_at":"2026-07-05T00:16:08.302753+00:00"}