{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z3SMTBGFUXAUSUYKMY5SCDTMFY","short_pith_number":"pith:Z3SMTBGF","schema_version":"1.0","canonical_sha256":"cee4c984c5a5c149530a663b210e6c2e2296823de762b09b9a94af8ef6702010","source":{"kind":"arxiv","id":"2602.22747","version":2},"attestation_state":"computed","paper":{"title":"Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Moens, Fabio Cuzzolin, Hans Hallez, Kaizheng Wang, Siu Lun Chau, Yunjia Wang","submitted_at":"2026-02-26T08:36:09Z","abstract_excerpt":"Epistemic uncertainty in neural networks is commonly modeled using two second-order paradigms: distribution-based representations, which rely on posterior parameter distributions, and set-based representations based on credal sets (convex sets of probability distributions). These frameworks are often regarded as fundamentally non-comparable due to differing semantics, assumptions, and evaluation practices, leaving their relative merits unclear. Empirical comparisons are further confounded by variations in the underlying predictive models. To clarify this issue, we present a controlled comparat"},"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":"2602.22747","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-26T08:36:09Z","cross_cats_sorted":[],"title_canon_sha256":"090f084e48bcef405595fae34de12dc122d54b472f7ed63cc102597f82922487","abstract_canon_sha256":"353397576111deca4b521e5472707dadc637d1f8fa8e5191111e05d2495f35c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:12:47.195716Z","signature_b64":"FVMZoRha8aJX2hk0j2cVpve1nF7t8D6vMau+nNB5NtrvsngI5Hfk0exyljdWpHNvY/4TY3KeYjuNVFaxVZKVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cee4c984c5a5c149530a663b210e6c2e2296823de762b09b9a94af8ef6702010","last_reissued_at":"2026-06-23T02:12:47.195217Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:12:47.195217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Moens, Fabio Cuzzolin, Hans Hallez, Kaizheng Wang, Siu Lun Chau, Yunjia Wang","submitted_at":"2026-02-26T08:36:09Z","abstract_excerpt":"Epistemic uncertainty in neural networks is commonly modeled using two second-order paradigms: distribution-based representations, which rely on posterior parameter distributions, and set-based representations based on credal sets (convex sets of probability distributions). These frameworks are often regarded as fundamentally non-comparable due to differing semantics, assumptions, and evaluation practices, leaving their relative merits unclear. Empirical comparisons are further confounded by variations in the underlying predictive models. To clarify this issue, we present a controlled comparat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22747","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/2602.22747/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":"2602.22747","created_at":"2026-06-23T02:12:47.195278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.22747v2","created_at":"2026-06-23T02:12:47.195278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22747","created_at":"2026-06-23T02:12:47.195278+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3SMTBGFUXAU","created_at":"2026-06-23T02:12:47.195278+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3SMTBGFUXAUSUYK","created_at":"2026-06-23T02:12:47.195278+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3SMTBGF","created_at":"2026-06-23T02:12:47.195278+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/Z3SMTBGFUXAUSUYKMY5SCDTMFY","json":"https://pith.science/pith/Z3SMTBGFUXAUSUYKMY5SCDTMFY.json","graph_json":"https://pith.science/api/pith-number/Z3SMTBGFUXAUSUYKMY5SCDTMFY/graph.json","events_json":"https://pith.science/api/pith-number/Z3SMTBGFUXAUSUYKMY5SCDTMFY/events.json","paper":"https://pith.science/paper/Z3SMTBGF"},"agent_actions":{"view_html":"https://pith.science/pith/Z3SMTBGFUXAUSUYKMY5SCDTMFY","download_json":"https://pith.science/pith/Z3SMTBGFUXAUSUYKMY5SCDTMFY.json","view_paper":"https://pith.science/paper/Z3SMTBGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.22747&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3SMTBGFUXAUSUYKMY5SCDTMFY/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3SMTBGFUXAUSUYKMY5SCDTMFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3SMTBGFUXAUSUYKMY5SCDTMFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3SMTBGFUXAUSUYKMY5SCDTMFY/action/storage_attestation","attest_author":"https://pith.science/pith/Z3SMTBGFUXAUSUYKMY5SCDTMFY/action/author_attestation","sign_citation":"https://pith.science/pith/Z3SMTBGFUXAUSUYKMY5SCDTMFY/action/citation_signature","submit_replication":"https://pith.science/pith/Z3SMTBGFUXAUSUYKMY5SCDTMFY/action/replication_record"}},"created_at":"2026-06-23T02:12:47.195278+00:00","updated_at":"2026-06-23T02:12:47.195278+00:00"}