{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FCGTF5FWD2VLLW75U2Q22PW5KC","short_pith_number":"pith:FCGTF5FW","schema_version":"1.0","canonical_sha256":"288d32f4b61eaab5dbfda6a1ad3edd50882f830944e41fe5b4205f2ee6685948","source":{"kind":"arxiv","id":"2402.09056","version":3},"attestation_state":"computed","paper":{"title":"Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Eyke H\\\"ullermeier, Mira J\\\"urgens, Nis Meinert, Viktor Bengs, Willem Waegeman","submitted_at":"2024-02-14T10:07:05Z","abstract_excerpt":"Trustworthy ML systems should not only return accurate predictions, but also a reliable representation of their uncertainty. Bayesian methods are commonly used to quantify both aleatoric and epistemic uncertainty, but alternative approaches, such as evidential deep learning methods, have become popular in recent years. The latter group of methods in essence extends empirical risk minimization (ERM) for predicting second-order probability distributions over outcomes, from which measures of epistemic (and aleatoric) uncertainty can be extracted. This paper presents novel theoretical insights of "},"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":"2402.09056","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-14T10:07:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f52af467c20ed38064de3eafbd3947d609e28f40eca7eac00ec4ed60e3e6a739","abstract_canon_sha256":"7d088b3e27170afa507d8fe5cfe227c6ea9c3926f0c5972f0ab648fe65496004"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:56.498540Z","signature_b64":"j6mT8GXLbHenlFCeSLp8Gb6W4ahrtHQvswBfmlo4rDc08GkNsqjMAu06m+zga9R6kwwLA2fsHFjBvpC8+hFaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"288d32f4b61eaab5dbfda6a1ad3edd50882f830944e41fe5b4205f2ee6685948","last_reissued_at":"2026-07-05T09:04:56.498052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:56.498052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Eyke H\\\"ullermeier, Mira J\\\"urgens, Nis Meinert, Viktor Bengs, Willem Waegeman","submitted_at":"2024-02-14T10:07:05Z","abstract_excerpt":"Trustworthy ML systems should not only return accurate predictions, but also a reliable representation of their uncertainty. Bayesian methods are commonly used to quantify both aleatoric and epistemic uncertainty, but alternative approaches, such as evidential deep learning methods, have become popular in recent years. The latter group of methods in essence extends empirical risk minimization (ERM) for predicting second-order probability distributions over outcomes, from which measures of epistemic (and aleatoric) uncertainty can be extracted. This paper presents novel theoretical insights of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09056","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/2402.09056/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":"2402.09056","created_at":"2026-07-05T09:04:56.498116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09056v3","created_at":"2026-07-05T09:04:56.498116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09056","created_at":"2026-07-05T09:04:56.498116+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCGTF5FWD2VL","created_at":"2026-07-05T09:04:56.498116+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCGTF5FWD2VLLW75","created_at":"2026-07-05T09:04:56.498116+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCGTF5FW","created_at":"2026-07-05T09:04:56.498116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22110","citing_title":"Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06032","citing_title":"Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCGTF5FWD2VLLW75U2Q22PW5KC","json":"https://pith.science/pith/FCGTF5FWD2VLLW75U2Q22PW5KC.json","graph_json":"https://pith.science/api/pith-number/FCGTF5FWD2VLLW75U2Q22PW5KC/graph.json","events_json":"https://pith.science/api/pith-number/FCGTF5FWD2VLLW75U2Q22PW5KC/events.json","paper":"https://pith.science/paper/FCGTF5FW"},"agent_actions":{"view_html":"https://pith.science/pith/FCGTF5FWD2VLLW75U2Q22PW5KC","download_json":"https://pith.science/pith/FCGTF5FWD2VLLW75U2Q22PW5KC.json","view_paper":"https://pith.science/paper/FCGTF5FW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09056&json=true","fetch_graph":"https://pith.science/api/pith-number/FCGTF5FWD2VLLW75U2Q22PW5KC/graph.json","fetch_events":"https://pith.science/api/pith-number/FCGTF5FWD2VLLW75U2Q22PW5KC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCGTF5FWD2VLLW75U2Q22PW5KC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCGTF5FWD2VLLW75U2Q22PW5KC/action/storage_attestation","attest_author":"https://pith.science/pith/FCGTF5FWD2VLLW75U2Q22PW5KC/action/author_attestation","sign_citation":"https://pith.science/pith/FCGTF5FWD2VLLW75U2Q22PW5KC/action/citation_signature","submit_replication":"https://pith.science/pith/FCGTF5FWD2VLLW75U2Q22PW5KC/action/replication_record"}},"created_at":"2026-07-05T09:04:56.498116+00:00","updated_at":"2026-07-05T09:04:56.498116+00:00"}