{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QQNV45FFDVRTOSQDSXSQLY5ZLO","short_pith_number":"pith:QQNV45FF","schema_version":"1.0","canonical_sha256":"841b5e74a51d63374a0395e505e3b95b94b0cd7488dd298bdad9f132c62e31f8","source":{"kind":"arxiv","id":"2505.02277","version":2},"attestation_state":"computed","paper":{"title":"Epistemic Wrapping for Uncertainty Quantification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fabio Cuzzolin, Kaizheng Wang, Maryam Sultana, Muhammad Mubashar, Neil Yorke-Smith, Shireen Kudukkil Manchingal","submitted_at":"2025-05-04T22:15:56Z","abstract_excerpt":"Uncertainty estimation is pivotal in machine learning, especially for classification tasks, as it improves the robustness and reliability of models. We introduce a novel `Epistemic Wrapping' methodology aimed at improving uncertainty estimation in classification. Our approach uses Bayesian Neural Networks (BNNs) as a baseline and transforms their outputs into belief function posteriors, effectively capturing epistemic uncertainty and offering an efficient and general methodology for uncertainty quantification. Comprehensive experiments employing a Bayesian Neural Network (BNN) baseline and an "},"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":"2505.02277","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-04T22:15:56Z","cross_cats_sorted":[],"title_canon_sha256":"d1b2a18481c6b7defe951f3bde9fc79b77c5047bc1484323fd8371b0c61c1c4d","abstract_canon_sha256":"434ff48819d372d80c1418553d0be4977ae5f3f34110446281bf4eef43359580"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:39.676000Z","signature_b64":"TZBKdyZW1YjgzLDlflF0TmM6MwOTKf7gN8d5hadsqaqW5SutanlK4hqFO2QhfZrtlzejvRvkoKd0Sj6Mbn9zCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"841b5e74a51d63374a0395e505e3b95b94b0cd7488dd298bdad9f132c62e31f8","last_reissued_at":"2026-07-05T11:55:39.675494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:39.675494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Epistemic Wrapping for Uncertainty Quantification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fabio Cuzzolin, Kaizheng Wang, Maryam Sultana, Muhammad Mubashar, Neil Yorke-Smith, Shireen Kudukkil Manchingal","submitted_at":"2025-05-04T22:15:56Z","abstract_excerpt":"Uncertainty estimation is pivotal in machine learning, especially for classification tasks, as it improves the robustness and reliability of models. We introduce a novel `Epistemic Wrapping' methodology aimed at improving uncertainty estimation in classification. Our approach uses Bayesian Neural Networks (BNNs) as a baseline and transforms their outputs into belief function posteriors, effectively capturing epistemic uncertainty and offering an efficient and general methodology for uncertainty quantification. Comprehensive experiments employing a Bayesian Neural Network (BNN) baseline and an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02277","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/2505.02277/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":"2505.02277","created_at":"2026-07-05T11:55:39.675552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02277v2","created_at":"2026-07-05T11:55:39.675552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02277","created_at":"2026-07-05T11:55:39.675552+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQNV45FFDVRT","created_at":"2026-07-05T11:55:39.675552+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQNV45FFDVRTOSQD","created_at":"2026-07-05T11:55:39.675552+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQNV45FF","created_at":"2026-07-05T11:55:39.675552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11987","citing_title":"Random-Set Graph Neural Networks","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQNV45FFDVRTOSQDSXSQLY5ZLO","json":"https://pith.science/pith/QQNV45FFDVRTOSQDSXSQLY5ZLO.json","graph_json":"https://pith.science/api/pith-number/QQNV45FFDVRTOSQDSXSQLY5ZLO/graph.json","events_json":"https://pith.science/api/pith-number/QQNV45FFDVRTOSQDSXSQLY5ZLO/events.json","paper":"https://pith.science/paper/QQNV45FF"},"agent_actions":{"view_html":"https://pith.science/pith/QQNV45FFDVRTOSQDSXSQLY5ZLO","download_json":"https://pith.science/pith/QQNV45FFDVRTOSQDSXSQLY5ZLO.json","view_paper":"https://pith.science/paper/QQNV45FF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02277&json=true","fetch_graph":"https://pith.science/api/pith-number/QQNV45FFDVRTOSQDSXSQLY5ZLO/graph.json","fetch_events":"https://pith.science/api/pith-number/QQNV45FFDVRTOSQDSXSQLY5ZLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQNV45FFDVRTOSQDSXSQLY5ZLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQNV45FFDVRTOSQDSXSQLY5ZLO/action/storage_attestation","attest_author":"https://pith.science/pith/QQNV45FFDVRTOSQDSXSQLY5ZLO/action/author_attestation","sign_citation":"https://pith.science/pith/QQNV45FFDVRTOSQDSXSQLY5ZLO/action/citation_signature","submit_replication":"https://pith.science/pith/QQNV45FFDVRTOSQDSXSQLY5ZLO/action/replication_record"}},"created_at":"2026-07-05T11:55:39.675552+00:00","updated_at":"2026-07-05T11:55:39.675552+00:00"}