{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:R4FUWBBDUPVPQZUYLPWX5LBITK","short_pith_number":"pith:R4FUWBBD","schema_version":"1.0","canonical_sha256":"8f0b4b0423a3eaf866985bed7eac289aba788212d31db813fd1a4b0f8346a18f","source":{"kind":"arxiv","id":"1806.01768","version":3},"attestation_state":"computed","paper":{"title":"Evidential Deep Learning to Quantify Classification Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lance Kaplan, Melih Kandemir, Murat Sensoy","submitted_at":"2018-06-05T16:07:27Z","abstract_excerpt":"Deterministic neural nets have been shown to learn effective predictors on a wide range of machine learning problems. However, as the standard approach is to train the network to minimize a prediction loss, the resultant model remains ignorant to its prediction confidence. Orthogonally to Bayesian neural nets that indirectly infer prediction uncertainty through weight uncertainties, we propose explicit modeling of the same using the theory of subjective logic. By placing a Dirichlet distribution on the class probabilities, we treat predictions of a neural net as subjective opinions and learn t"},"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":"1806.01768","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-05T16:07:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2798cd4340f35683649c14d5128905379645722de45370dfc5008f68450caae","abstract_canon_sha256":"8e56c27d47ee59223911b8921b2be1dd6b8396d04e523f006d2a7a5a61a8e9b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:48.821881Z","signature_b64":"BIWSOHWpRvyBY5+v/Ln2i9hoXlwlVAs66Lh7kM2LPT07GTDnIzSboExQZVoYqZc8biRpHUGyHzBGzWq/qxFWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f0b4b0423a3eaf866985bed7eac289aba788212d31db813fd1a4b0f8346a18f","last_reissued_at":"2026-05-18T00:01:48.821230Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:48.821230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evidential Deep Learning to Quantify Classification Uncertainty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lance Kaplan, Melih Kandemir, Murat Sensoy","submitted_at":"2018-06-05T16:07:27Z","abstract_excerpt":"Deterministic neural nets have been shown to learn effective predictors on a wide range of machine learning problems. However, as the standard approach is to train the network to minimize a prediction loss, the resultant model remains ignorant to its prediction confidence. Orthogonally to Bayesian neural nets that indirectly infer prediction uncertainty through weight uncertainties, we propose explicit modeling of the same using the theory of subjective logic. By placing a Dirichlet distribution on the class probabilities, we treat predictions of a neural net as subjective opinions and learn t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01768","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":""},"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":"1806.01768","created_at":"2026-05-18T00:01:48.821346+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.01768v3","created_at":"2026-05-18T00:01:48.821346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01768","created_at":"2026-05-18T00:01:48.821346+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4FUWBBDUPVP","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4FUWBBDUPVPQZUY","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4FUWBBD","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2511.10292","citing_title":"Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03615","citing_title":"PriorNet: Prior-Guided Engagement Estimation from Face Video","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06382","citing_title":"Rethinking Vacuity for OOD Detection in Evidential Deep Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08868","citing_title":"MedFormer-UR: Uncertainty-Routed Transformer for Medical Image Classification","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06032","citing_title":"Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4FUWBBDUPVPQZUYLPWX5LBITK","json":"https://pith.science/pith/R4FUWBBDUPVPQZUYLPWX5LBITK.json","graph_json":"https://pith.science/api/pith-number/R4FUWBBDUPVPQZUYLPWX5LBITK/graph.json","events_json":"https://pith.science/api/pith-number/R4FUWBBDUPVPQZUYLPWX5LBITK/events.json","paper":"https://pith.science/paper/R4FUWBBD"},"agent_actions":{"view_html":"https://pith.science/pith/R4FUWBBDUPVPQZUYLPWX5LBITK","download_json":"https://pith.science/pith/R4FUWBBDUPVPQZUYLPWX5LBITK.json","view_paper":"https://pith.science/paper/R4FUWBBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.01768&json=true","fetch_graph":"https://pith.science/api/pith-number/R4FUWBBDUPVPQZUYLPWX5LBITK/graph.json","fetch_events":"https://pith.science/api/pith-number/R4FUWBBDUPVPQZUYLPWX5LBITK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4FUWBBDUPVPQZUYLPWX5LBITK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4FUWBBDUPVPQZUYLPWX5LBITK/action/storage_attestation","attest_author":"https://pith.science/pith/R4FUWBBDUPVPQZUYLPWX5LBITK/action/author_attestation","sign_citation":"https://pith.science/pith/R4FUWBBDUPVPQZUYLPWX5LBITK/action/citation_signature","submit_replication":"https://pith.science/pith/R4FUWBBDUPVPQZUYLPWX5LBITK/action/replication_record"}},"created_at":"2026-05-18T00:01:48.821346+00:00","updated_at":"2026-05-18T00:01:48.821346+00:00"}