{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GUBLO43XQNZWCRMS2EYYOZLIFS","short_pith_number":"pith:GUBLO43X","schema_version":"1.0","canonical_sha256":"3502b773778373614592d1318765682cb26765d4bb8bdf26dc0d224c5bedda03","source":{"kind":"arxiv","id":"2607.28248","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty quantification for trustworthy deep learning: Methods and measures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"H. Martin Gillis, Thomas Trappenberg","submitted_at":"2026-07-30T14:10:31Z","abstract_excerpt":"The deployment of deep neural networks in safety-critical domains demands reliable estimates of predictive confidence, yet conventional architectures lack principled uncertainty quantification. This survey provides a structured, critical review of methods for Uncertainty Quantification (UQ) in deep learning, scoped to ensemble-based and approximate Bayesian approaches and the measures used to summarize their outputs. Relative to existing UQ surveys, our contribution is depth on efficient ensemble approximations and single-pass methods, and a unified treatment that separates the method producin"},"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":"2607.28248","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-30T14:10:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"96aefadc87f235e8e134240791ffb1ff5ddbff9fb16cbbfe789811c3cbbf9be5","abstract_canon_sha256":"6c12e04fe98cd0c57595b5cd7492f939ffc40bdcefb1543ce9a46a9eb9799c75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3502b773778373614592d1318765682cb26765d4bb8bdf26dc0d224c5bedda03","last_reissued_at":"2026-07-31T01:36:54.938358Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:36:54.938358Z"},"graph_snapshot":{"paper":{"title":"Uncertainty quantification for trustworthy deep learning: Methods and measures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"H. Martin Gillis, Thomas Trappenberg","submitted_at":"2026-07-30T14:10:31Z","abstract_excerpt":"The deployment of deep neural networks in safety-critical domains demands reliable estimates of predictive confidence, yet conventional architectures lack principled uncertainty quantification. This survey provides a structured, critical review of methods for Uncertainty Quantification (UQ) in deep learning, scoped to ensemble-based and approximate Bayesian approaches and the measures used to summarize their outputs. Relative to existing UQ surveys, our contribution is depth on efficient ensemble approximations and single-pass methods, and a unified treatment that separates the method producin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28248","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/2607.28248/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":"2607.28248","created_at":"2026-07-31T01:36:54.942066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28248v1","created_at":"2026-07-31T01:36:54.942066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28248","created_at":"2026-07-31T01:36:54.942066+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUBLO43XQNZW","created_at":"2026-07-31T01:36:54.942066+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUBLO43XQNZWCRMS","created_at":"2026-07-31T01:36:54.942066+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUBLO43X","created_at":"2026-07-31T01:36:54.942066+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/GUBLO43XQNZWCRMS2EYYOZLIFS","json":"https://pith.science/pith/GUBLO43XQNZWCRMS2EYYOZLIFS.json","graph_json":"https://pith.science/api/pith-number/GUBLO43XQNZWCRMS2EYYOZLIFS/graph.json","events_json":"https://pith.science/api/pith-number/GUBLO43XQNZWCRMS2EYYOZLIFS/events.json","paper":"https://pith.science/paper/GUBLO43X"},"agent_actions":{"view_html":"https://pith.science/pith/GUBLO43XQNZWCRMS2EYYOZLIFS","download_json":"https://pith.science/pith/GUBLO43XQNZWCRMS2EYYOZLIFS.json","view_paper":"https://pith.science/paper/GUBLO43X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28248&json=true","fetch_graph":"https://pith.science/api/pith-number/GUBLO43XQNZWCRMS2EYYOZLIFS/graph.json","fetch_events":"https://pith.science/api/pith-number/GUBLO43XQNZWCRMS2EYYOZLIFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUBLO43XQNZWCRMS2EYYOZLIFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUBLO43XQNZWCRMS2EYYOZLIFS/action/storage_attestation","attest_author":"https://pith.science/pith/GUBLO43XQNZWCRMS2EYYOZLIFS/action/author_attestation","sign_citation":"https://pith.science/pith/GUBLO43XQNZWCRMS2EYYOZLIFS/action/citation_signature","submit_replication":"https://pith.science/pith/GUBLO43XQNZWCRMS2EYYOZLIFS/action/replication_record"}},"created_at":"2026-07-31T01:36:54.942066+00:00","updated_at":"2026-07-31T01:36:54.942066+00:00"}