{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5JLXOT6WXLEOUS7PB3J7ELVGZO","short_pith_number":"pith:5JLXOT6W","schema_version":"1.0","canonical_sha256":"ea57774fd6bac8ea4bef0ed3f22ea6cb800cc1af77d65201ceb6dd51ab8813a8","source":{"kind":"arxiv","id":"2110.03051","version":3},"attestation_state":"computed","paper":{"title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Hardmeier, Dennis Ulmer, Jes Frellsen","submitted_at":"2021-10-06T20:13:57Z","abstract_excerpt":"Popular approaches for quantifying predictive uncertainty in deep neural networks often involve distributions over weights or multiple models, for instance via Markov Chain sampling, ensembling, or Monte Carlo dropout. These techniques usually incur overhead by having to train multiple model instances or do not produce very diverse predictions. This comprehensive and extensive survey aims to familiarize the reader with an alternative class of models based on the concept of Evidential Deep Learning: For unfamiliar data, they aim to admit \"what they don't know\", and fall back onto a prior belief"},"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":"2110.03051","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T20:13:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9ef4b0d0241628d9b750940579377cc0d6c0e094540ea9de56f66b5dc497648d","abstract_canon_sha256":"0d6fa71090c804a209b39a24814305ccaef3f1a6fd9fe0f463fa881de2a35865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:31.221896Z","signature_b64":"9jS5WCwUl57lVs07yGus9J2IMiS/exSQGj7QpmyVDs6b8I7txhONHKvzbZ8+6Txhralk7BnGdtDX67gE8xtkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea57774fd6bac8ea4bef0ed3f22ea6cb800cc1af77d65201ceb6dd51ab8813a8","last_reissued_at":"2026-07-05T05:48:31.221554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:31.221554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian Hardmeier, Dennis Ulmer, Jes Frellsen","submitted_at":"2021-10-06T20:13:57Z","abstract_excerpt":"Popular approaches for quantifying predictive uncertainty in deep neural networks often involve distributions over weights or multiple models, for instance via Markov Chain sampling, ensembling, or Monte Carlo dropout. These techniques usually incur overhead by having to train multiple model instances or do not produce very diverse predictions. This comprehensive and extensive survey aims to familiarize the reader with an alternative class of models based on the concept of Evidential Deep Learning: For unfamiliar data, they aim to admit \"what they don't know\", and fall back onto a prior belief"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03051","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/2110.03051/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":"2110.03051","created_at":"2026-07-05T05:48:31.221609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03051v3","created_at":"2026-07-05T05:48:31.221609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03051","created_at":"2026-07-05T05:48:31.221609+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JLXOT6WXLEO","created_at":"2026-07-05T05:48:31.221609+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JLXOT6WXLEOUS7P","created_at":"2026-07-05T05:48:31.221609+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JLXOT6W","created_at":"2026-07-05T05:48:31.221609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10984","citing_title":"Principle-Guided Supervision for Interpretable Uncertainty in Medical Image Segmentation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10378","citing_title":"Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06032","citing_title":"Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5JLXOT6WXLEOUS7PB3J7ELVGZO","json":"https://pith.science/pith/5JLXOT6WXLEOUS7PB3J7ELVGZO.json","graph_json":"https://pith.science/api/pith-number/5JLXOT6WXLEOUS7PB3J7ELVGZO/graph.json","events_json":"https://pith.science/api/pith-number/5JLXOT6WXLEOUS7PB3J7ELVGZO/events.json","paper":"https://pith.science/paper/5JLXOT6W"},"agent_actions":{"view_html":"https://pith.science/pith/5JLXOT6WXLEOUS7PB3J7ELVGZO","download_json":"https://pith.science/pith/5JLXOT6WXLEOUS7PB3J7ELVGZO.json","view_paper":"https://pith.science/paper/5JLXOT6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03051&json=true","fetch_graph":"https://pith.science/api/pith-number/5JLXOT6WXLEOUS7PB3J7ELVGZO/graph.json","fetch_events":"https://pith.science/api/pith-number/5JLXOT6WXLEOUS7PB3J7ELVGZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JLXOT6WXLEOUS7PB3J7ELVGZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JLXOT6WXLEOUS7PB3J7ELVGZO/action/storage_attestation","attest_author":"https://pith.science/pith/5JLXOT6WXLEOUS7PB3J7ELVGZO/action/author_attestation","sign_citation":"https://pith.science/pith/5JLXOT6WXLEOUS7PB3J7ELVGZO/action/citation_signature","submit_replication":"https://pith.science/pith/5JLXOT6WXLEOUS7PB3J7ELVGZO/action/replication_record"}},"created_at":"2026-07-05T05:48:31.221609+00:00","updated_at":"2026-07-05T05:48:31.221609+00:00"}