{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NJ7QLRQ433ZYNL6CME4KJXLGJ3","short_pith_number":"pith:NJ7QLRQ4","schema_version":"1.0","canonical_sha256":"6a7f05c61cdef386afc26138a4dd664ef958aa6ba65e2b5e7032aee691ae2e2e","source":{"kind":"arxiv","id":"2104.06135","version":4},"attestation_state":"computed","paper":{"title":"Multivariate Deep Evidential Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Lavin, Nis Meinert","submitted_at":"2021-04-13T12:20:18Z","abstract_excerpt":"There is significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware neural networks (NNs), based on learning evidential distributions for aleatoric and epistemic uncertainties, shows promise over traditional deterministic methods and typical Bayesian NNs, yet several important gaps in the theory and implementation of these networks remain. We discuss three issues with a proposed solution to extract aleatoric and epistemic uncertainties from regression-based neural networks"},"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":"2104.06135","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-13T12:20:18Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"49b82b34a22140e259b7612681e03c2156b2bd3537d68a9b32212df1ea84c7ff","abstract_canon_sha256":"20da52f00bdeb1b1be620f9763582443476f6e4b377250a13b04daf28ca459c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:38.628273Z","signature_b64":"I1qPR8+oWQ35ff/o/AMM3UW1VdHDx9oOyLXA4uD9Ec/fX0Y/vi04+gzjYFzQ+eLKL82wCCbIE7t0gIFrV/YxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a7f05c61cdef386afc26138a4dd664ef958aa6ba65e2b5e7032aee691ae2e2e","last_reissued_at":"2026-07-05T03:59:38.627856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:38.627856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multivariate Deep Evidential Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Lavin, Nis Meinert","submitted_at":"2021-04-13T12:20:18Z","abstract_excerpt":"There is significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware neural networks (NNs), based on learning evidential distributions for aleatoric and epistemic uncertainties, shows promise over traditional deterministic methods and typical Bayesian NNs, yet several important gaps in the theory and implementation of these networks remain. We discuss three issues with a proposed solution to extract aleatoric and epistemic uncertainties from regression-based neural networks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06135","kind":"arxiv","version":4},"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/2104.06135/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":"2104.06135","created_at":"2026-07-05T03:59:38.627912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06135v4","created_at":"2026-07-05T03:59:38.627912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06135","created_at":"2026-07-05T03:59:38.627912+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJ7QLRQ433ZY","created_at":"2026-07-05T03:59:38.627912+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJ7QLRQ433ZYNL6C","created_at":"2026-07-05T03:59:38.627912+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJ7QLRQ4","created_at":"2026-07-05T03:59:38.627912+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":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19539","citing_title":"Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00155","citing_title":"Amplitude Uncertainties Everywhere All at Once","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NJ7QLRQ433ZYNL6CME4KJXLGJ3","json":"https://pith.science/pith/NJ7QLRQ433ZYNL6CME4KJXLGJ3.json","graph_json":"https://pith.science/api/pith-number/NJ7QLRQ433ZYNL6CME4KJXLGJ3/graph.json","events_json":"https://pith.science/api/pith-number/NJ7QLRQ433ZYNL6CME4KJXLGJ3/events.json","paper":"https://pith.science/paper/NJ7QLRQ4"},"agent_actions":{"view_html":"https://pith.science/pith/NJ7QLRQ433ZYNL6CME4KJXLGJ3","download_json":"https://pith.science/pith/NJ7QLRQ433ZYNL6CME4KJXLGJ3.json","view_paper":"https://pith.science/paper/NJ7QLRQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06135&json=true","fetch_graph":"https://pith.science/api/pith-number/NJ7QLRQ433ZYNL6CME4KJXLGJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/NJ7QLRQ433ZYNL6CME4KJXLGJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJ7QLRQ433ZYNL6CME4KJXLGJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJ7QLRQ433ZYNL6CME4KJXLGJ3/action/storage_attestation","attest_author":"https://pith.science/pith/NJ7QLRQ433ZYNL6CME4KJXLGJ3/action/author_attestation","sign_citation":"https://pith.science/pith/NJ7QLRQ433ZYNL6CME4KJXLGJ3/action/citation_signature","submit_replication":"https://pith.science/pith/NJ7QLRQ433ZYNL6CME4KJXLGJ3/action/replication_record"}},"created_at":"2026-07-05T03:59:38.627912+00:00","updated_at":"2026-07-05T03:59:38.627912+00:00"}