{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MUHOB5IP4PNBMLHDF26RX7RFB2","short_pith_number":"pith:MUHOB5IP","schema_version":"1.0","canonical_sha256":"650ee0f50fe3da162ce32ebd1bfe250eaf2e1042144690c08e3f6e58d8bab351","source":{"kind":"arxiv","id":"2306.12497","version":2},"attestation_state":"computed","paper":{"title":"Density Uncertainty Layers for Reliable Uncertainty Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David M. Blei, Yookoon Park","submitted_at":"2023-06-21T18:12:58Z","abstract_excerpt":"Assessing the predictive uncertainty of deep neural networks is crucial for safety-related applications of deep learning. Although Bayesian deep learning offers a principled framework for estimating model uncertainty, the common approaches that approximate the parameter posterior often fail to deliver reliable estimates of predictive uncertainty. In this paper, we propose a novel criterion for reliable predictive uncertainty: a model's predictive variance should be grounded in the empirical density of the input. That is, the model should produce higher uncertainty for inputs that are improbabl"},"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":"2306.12497","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T18:12:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a2b22a235181a1d5cde3edd32c48ce58e230e5500850d326030c40d7079d29a3","abstract_canon_sha256":"89558db4cccd7a990d242fdfd52d7b93b9a2d5dd41ef960bebef3a2011ea2fb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:59.808671Z","signature_b64":"umkeUSPZ4xkEg7HdQFy4vv+9P7jcAOB/08RC0bqsRx5fLx86rVfh2SBljPN3VQoExBQwyEbafM0BLfWx5zr/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"650ee0f50fe3da162ce32ebd1bfe250eaf2e1042144690c08e3f6e58d8bab351","last_reissued_at":"2026-07-05T07:51:59.808176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:59.808176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Density Uncertainty Layers for Reliable Uncertainty Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David M. Blei, Yookoon Park","submitted_at":"2023-06-21T18:12:58Z","abstract_excerpt":"Assessing the predictive uncertainty of deep neural networks is crucial for safety-related applications of deep learning. Although Bayesian deep learning offers a principled framework for estimating model uncertainty, the common approaches that approximate the parameter posterior often fail to deliver reliable estimates of predictive uncertainty. In this paper, we propose a novel criterion for reliable predictive uncertainty: a model's predictive variance should be grounded in the empirical density of the input. That is, the model should produce higher uncertainty for inputs that are improbabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12497","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/2306.12497/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":"2306.12497","created_at":"2026-07-05T07:51:59.808232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12497v2","created_at":"2026-07-05T07:51:59.808232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12497","created_at":"2026-07-05T07:51:59.808232+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUHOB5IP4PNB","created_at":"2026-07-05T07:51:59.808232+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUHOB5IP4PNBMLHD","created_at":"2026-07-05T07:51:59.808232+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUHOB5IP","created_at":"2026-07-05T07:51:59.808232+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/MUHOB5IP4PNBMLHDF26RX7RFB2","json":"https://pith.science/pith/MUHOB5IP4PNBMLHDF26RX7RFB2.json","graph_json":"https://pith.science/api/pith-number/MUHOB5IP4PNBMLHDF26RX7RFB2/graph.json","events_json":"https://pith.science/api/pith-number/MUHOB5IP4PNBMLHDF26RX7RFB2/events.json","paper":"https://pith.science/paper/MUHOB5IP"},"agent_actions":{"view_html":"https://pith.science/pith/MUHOB5IP4PNBMLHDF26RX7RFB2","download_json":"https://pith.science/pith/MUHOB5IP4PNBMLHDF26RX7RFB2.json","view_paper":"https://pith.science/paper/MUHOB5IP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12497&json=true","fetch_graph":"https://pith.science/api/pith-number/MUHOB5IP4PNBMLHDF26RX7RFB2/graph.json","fetch_events":"https://pith.science/api/pith-number/MUHOB5IP4PNBMLHDF26RX7RFB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUHOB5IP4PNBMLHDF26RX7RFB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUHOB5IP4PNBMLHDF26RX7RFB2/action/storage_attestation","attest_author":"https://pith.science/pith/MUHOB5IP4PNBMLHDF26RX7RFB2/action/author_attestation","sign_citation":"https://pith.science/pith/MUHOB5IP4PNBMLHDF26RX7RFB2/action/citation_signature","submit_replication":"https://pith.science/pith/MUHOB5IP4PNBMLHDF26RX7RFB2/action/replication_record"}},"created_at":"2026-07-05T07:51:59.808232+00:00","updated_at":"2026-07-05T07:51:59.808232+00:00"}