{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WB7SCDSHQMUQ4CBPY3ZKUJW5NJ","short_pith_number":"pith:WB7SCDSH","schema_version":"1.0","canonical_sha256":"b07f210e4783290e082fc6f2aa26dd6a7597841a22efcb1118088878abba8118","source":{"kind":"arxiv","id":"1811.07308","version":4},"attestation_state":"computed","paper":{"title":"A Variational Dirichlet Framework for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongxia Jin, Wenhu Chen, William Wang, Yilin Shen","submitted_at":"2018-11-18T10:24:58Z","abstract_excerpt":"With the recently rapid development in deep learning, deep neural networks have been widely adopted in many real-life applications. However, deep neural networks are also known to have very little control over its uncertainty for unseen examples, which potentially causes very harmful and annoying consequences in practical scenarios. In this paper, we are particularly interested in designing a higher-order uncertainty metric for deep neural networks and investigate its effectiveness under the out-of-distribution detection task proposed by~\\cite{hendrycks2016baseline}. Our method first assumes 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":"1811.07308","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-18T10:24:58Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"932c30ef0b897a932511552586706c60a18000890da25026a693c2c67a3974bf","abstract_canon_sha256":"946998c00e587adced9ec75ad9a320f51997995042ed9f9ad83ffd0fecc9bec0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:06.404882Z","signature_b64":"7ldY67IykrfCuyhsrE62M0U8EH/CB0iEjIzmSCRwCwtxMxR21v0gMJd8/ImVIVZ/L0dW67hKO8Je9WkIjzKYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b07f210e4783290e082fc6f2aa26dd6a7597841a22efcb1118088878abba8118","last_reissued_at":"2026-05-17T23:48:06.404489Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:06.404489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Variational Dirichlet Framework for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongxia Jin, Wenhu Chen, William Wang, Yilin Shen","submitted_at":"2018-11-18T10:24:58Z","abstract_excerpt":"With the recently rapid development in deep learning, deep neural networks have been widely adopted in many real-life applications. However, deep neural networks are also known to have very little control over its uncertainty for unseen examples, which potentially causes very harmful and annoying consequences in practical scenarios. In this paper, we are particularly interested in designing a higher-order uncertainty metric for deep neural networks and investigate its effectiveness under the out-of-distribution detection task proposed by~\\cite{hendrycks2016baseline}. Our method first assumes t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07308","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":""},"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":"1811.07308","created_at":"2026-05-17T23:48:06.404551+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.07308v4","created_at":"2026-05-17T23:48:06.404551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07308","created_at":"2026-05-17T23:48:06.404551+00:00"},{"alias_kind":"pith_short_12","alias_value":"WB7SCDSHQMUQ","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WB7SCDSHQMUQ4CBP","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WB7SCDSH","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08627","citing_title":"Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ","json":"https://pith.science/pith/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ.json","graph_json":"https://pith.science/api/pith-number/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ/graph.json","events_json":"https://pith.science/api/pith-number/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ/events.json","paper":"https://pith.science/paper/WB7SCDSH"},"agent_actions":{"view_html":"https://pith.science/pith/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ","download_json":"https://pith.science/pith/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ.json","view_paper":"https://pith.science/paper/WB7SCDSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.07308&json=true","fetch_graph":"https://pith.science/api/pith-number/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ/action/storage_attestation","attest_author":"https://pith.science/pith/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ/action/author_attestation","sign_citation":"https://pith.science/pith/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ/action/citation_signature","submit_replication":"https://pith.science/pith/WB7SCDSHQMUQ4CBPY3ZKUJW5NJ/action/replication_record"}},"created_at":"2026-05-17T23:48:06.404551+00:00","updated_at":"2026-05-17T23:48:06.404551+00:00"}