{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2CXNNIUGWXO7GZMCCWAZ4H7D52","short_pith_number":"pith:2CXNNIUG","schema_version":"1.0","canonical_sha256":"d0aed6a286b5ddf3658215819e1fe3ee880cb97368ffd1e9f257093f4d7d7123","source":{"kind":"arxiv","id":"2006.11590","version":2},"attestation_state":"computed","paper":{"title":"Regression Prior Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrey Malinin, Ivan Provilkov, Mark Gales, Sergey Chervontsev","submitted_at":"2020-06-20T14:50:14Z","abstract_excerpt":"Prior Networks are a recently developed class of models which yield interpretable measures of uncertainty and have been shown to outperform state-of-the-art ensemble approaches on a range of tasks. They can also be used to distill an ensemble of models via Ensemble Distribution Distillation (EnD$^2$), such that its accuracy, calibration and uncertainty estimates are retained within a single model. However, Prior Networks have so far been developed only for classification tasks. This work extends Prior Networks and EnD$^2$ to regression tasks by considering the Normal-Wishart distribution. The "},"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":"2006.11590","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-20T14:50:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"36abedcfd773677e8080f526cc5301036f73d444da87ea87ea756ad80e76a4ef","abstract_canon_sha256":"db07e1e7a7c1688f3c08b125ef8ce6b1aefa7fd611a7edffa1b473c1b48c2718"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:10.364440Z","signature_b64":"SNdWA9BVJMfyOa1aWk/VcKqUjP5GwzlugcwEm1hDivOZYqn1inC2eDp5x0Q5SsVxm2Oq8B1MuiG6+H9g022eDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0aed6a286b5ddf3658215819e1fe3ee880cb97368ffd1e9f257093f4d7d7123","last_reissued_at":"2026-07-05T01:58:10.363881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:10.363881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regression Prior Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrey Malinin, Ivan Provilkov, Mark Gales, Sergey Chervontsev","submitted_at":"2020-06-20T14:50:14Z","abstract_excerpt":"Prior Networks are a recently developed class of models which yield interpretable measures of uncertainty and have been shown to outperform state-of-the-art ensemble approaches on a range of tasks. They can also be used to distill an ensemble of models via Ensemble Distribution Distillation (EnD$^2$), such that its accuracy, calibration and uncertainty estimates are retained within a single model. However, Prior Networks have so far been developed only for classification tasks. This work extends Prior Networks and EnD$^2$ to regression tasks by considering the Normal-Wishart distribution. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11590","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/2006.11590/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":"2006.11590","created_at":"2026-07-05T01:58:10.363944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11590v2","created_at":"2026-07-05T01:58:10.363944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11590","created_at":"2026-07-05T01:58:10.363944+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CXNNIUGWXO7","created_at":"2026-07-05T01:58:10.363944+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CXNNIUGWXO7GZMC","created_at":"2026-07-05T01:58:10.363944+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CXNNIUG","created_at":"2026-07-05T01:58:10.363944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19569","citing_title":"On the QUEST for Uncertainty Quantification via Highest Density Regions","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22746","citing_title":"Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2302.09664","citing_title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CXNNIUGWXO7GZMCCWAZ4H7D52","json":"https://pith.science/pith/2CXNNIUGWXO7GZMCCWAZ4H7D52.json","graph_json":"https://pith.science/api/pith-number/2CXNNIUGWXO7GZMCCWAZ4H7D52/graph.json","events_json":"https://pith.science/api/pith-number/2CXNNIUGWXO7GZMCCWAZ4H7D52/events.json","paper":"https://pith.science/paper/2CXNNIUG"},"agent_actions":{"view_html":"https://pith.science/pith/2CXNNIUGWXO7GZMCCWAZ4H7D52","download_json":"https://pith.science/pith/2CXNNIUGWXO7GZMCCWAZ4H7D52.json","view_paper":"https://pith.science/paper/2CXNNIUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11590&json=true","fetch_graph":"https://pith.science/api/pith-number/2CXNNIUGWXO7GZMCCWAZ4H7D52/graph.json","fetch_events":"https://pith.science/api/pith-number/2CXNNIUGWXO7GZMCCWAZ4H7D52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CXNNIUGWXO7GZMCCWAZ4H7D52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CXNNIUGWXO7GZMCCWAZ4H7D52/action/storage_attestation","attest_author":"https://pith.science/pith/2CXNNIUGWXO7GZMCCWAZ4H7D52/action/author_attestation","sign_citation":"https://pith.science/pith/2CXNNIUGWXO7GZMCCWAZ4H7D52/action/citation_signature","submit_replication":"https://pith.science/pith/2CXNNIUGWXO7GZMCCWAZ4H7D52/action/replication_record"}},"created_at":"2026-07-05T01:58:10.363944+00:00","updated_at":"2026-07-05T01:58:10.363944+00:00"}