{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3BSH2X52AC5SKDAOWS2JKMVYTO","short_pith_number":"pith:3BSH2X52","schema_version":"1.0","canonical_sha256":"d8647d5fba00bb250c0eb4b49532b89bab9c16b0a31977dc0fa890cca0ff72c2","source":{"kind":"arxiv","id":"1904.12220","version":1},"attestation_state":"computed","paper":{"title":"Analysis of Confident-Classifiers for Out-of-distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashish Gaurav, Buu Phan, Krzysztof Czarnecki, Rick Salay, Sachin Vernekar, Taylor Denouden, Vahdat Abdelzad","submitted_at":"2019-04-27T22:33:34Z","abstract_excerpt":"Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors. In the context of OOD detection for image classification, one of the recent approaches proposes training a classifier called \"confident-classifier\" by minimizing the standard cross-entropy loss on in-distribution samples and minimizing the KL divergence between the predictive distribution of OOD samples in the low-density regions of in-distribution and"},"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":"1904.12220","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-27T22:33:34Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"e142cc1dfa224095c9b06e4f05e057cafe79e62d332a63f1d606bffa60aef5b0","abstract_canon_sha256":"1a169b7cc906559dc45a83058eb456a28cc4911eac8eede49767b2e910bf54a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:38.633929Z","signature_b64":"57fRl8EmsJx+WUN6ZCqYewvK1WOGA1H4xn5WPdbTSKl9PwP/34eZkBkzXCogpbpWbHmeULxD1ehQ4Z8pjD0SAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8647d5fba00bb250c0eb4b49532b89bab9c16b0a31977dc0fa890cca0ff72c2","last_reissued_at":"2026-05-17T23:47:38.633499Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:38.633499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis of Confident-Classifiers for Out-of-distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashish Gaurav, Buu Phan, Krzysztof Czarnecki, Rick Salay, Sachin Vernekar, Taylor Denouden, Vahdat Abdelzad","submitted_at":"2019-04-27T22:33:34Z","abstract_excerpt":"Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors. In the context of OOD detection for image classification, one of the recent approaches proposes training a classifier called \"confident-classifier\" by minimizing the standard cross-entropy loss on in-distribution samples and minimizing the KL divergence between the predictive distribution of OOD samples in the low-density regions of in-distribution and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12220","kind":"arxiv","version":1},"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":"1904.12220","created_at":"2026-05-17T23:47:38.633558+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.12220v1","created_at":"2026-05-17T23:47:38.633558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12220","created_at":"2026-05-17T23:47:38.633558+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BSH2X52AC5S","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BSH2X52AC5SKDAO","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BSH2X52","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3BSH2X52AC5SKDAOWS2JKMVYTO","json":"https://pith.science/pith/3BSH2X52AC5SKDAOWS2JKMVYTO.json","graph_json":"https://pith.science/api/pith-number/3BSH2X52AC5SKDAOWS2JKMVYTO/graph.json","events_json":"https://pith.science/api/pith-number/3BSH2X52AC5SKDAOWS2JKMVYTO/events.json","paper":"https://pith.science/paper/3BSH2X52"},"agent_actions":{"view_html":"https://pith.science/pith/3BSH2X52AC5SKDAOWS2JKMVYTO","download_json":"https://pith.science/pith/3BSH2X52AC5SKDAOWS2JKMVYTO.json","view_paper":"https://pith.science/paper/3BSH2X52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.12220&json=true","fetch_graph":"https://pith.science/api/pith-number/3BSH2X52AC5SKDAOWS2JKMVYTO/graph.json","fetch_events":"https://pith.science/api/pith-number/3BSH2X52AC5SKDAOWS2JKMVYTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BSH2X52AC5SKDAOWS2JKMVYTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BSH2X52AC5SKDAOWS2JKMVYTO/action/storage_attestation","attest_author":"https://pith.science/pith/3BSH2X52AC5SKDAOWS2JKMVYTO/action/author_attestation","sign_citation":"https://pith.science/pith/3BSH2X52AC5SKDAOWS2JKMVYTO/action/citation_signature","submit_replication":"https://pith.science/pith/3BSH2X52AC5SKDAOWS2JKMVYTO/action/replication_record"}},"created_at":"2026-05-17T23:47:38.633558+00:00","updated_at":"2026-05-17T23:47:38.633558+00:00"}