{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DOFBEBK6CU443C55KJ5ZDXNV5J","short_pith_number":"pith:DOFBEBK6","schema_version":"1.0","canonical_sha256":"1b8a12055e1539cd8bbd527b91ddb5ea75f1507e89d5da02f3588af8abd36754","source":{"kind":"arxiv","id":"1908.04951","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kiyoharu Aizawa, Qing Yu","submitted_at":"2019-08-14T04:44:37Z","abstract_excerpt":"Since deep learning models have been implemented in many commercial applications, it is important to detect out-of-distribution (OOD) inputs correctly to maintain the performance of the models, ensure the quality of the collected data, and prevent the applications from being used for other-than-intended purposes. In this work, we propose a two-head deep convolutional neural network (CNN) and maximize the discrepancy between the two classifiers to detect OOD inputs. We train a two-head CNN consisting of one common feature extractor and two classifiers which have different decision boundaries bu"},"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":"1908.04951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-14T04:44:37Z","cross_cats_sorted":[],"title_canon_sha256":"68d7ad972ea5ab3624eed683b17806c67cc6a27859f84881e973ee41f04534b7","abstract_canon_sha256":"ea882ccd416ce6f9bee5f06d517bf6c32fc11e2da9883f0df2f7aac4cd791202"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:00.513889Z","signature_b64":"s7hzqFMrzLhkpjYjIT7Dn4qE9IIehbEl5YBwhH30ACWpVonsEsAms1/4w+I+0zr3OIxeOoERf72yqoaNFfF7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b8a12055e1539cd8bbd527b91ddb5ea75f1507e89d5da02f3588af8abd36754","last_reissued_at":"2026-07-05T00:03:00.513479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:00.513479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kiyoharu Aizawa, Qing Yu","submitted_at":"2019-08-14T04:44:37Z","abstract_excerpt":"Since deep learning models have been implemented in many commercial applications, it is important to detect out-of-distribution (OOD) inputs correctly to maintain the performance of the models, ensure the quality of the collected data, and prevent the applications from being used for other-than-intended purposes. In this work, we propose a two-head deep convolutional neural network (CNN) and maximize the discrepancy between the two classifiers to detect OOD inputs. We train a two-head CNN consisting of one common feature extractor and two classifiers which have different decision boundaries bu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04951","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.04951/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":"1908.04951","created_at":"2026-07-05T00:03:00.513542+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04951v1","created_at":"2026-07-05T00:03:00.513542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04951","created_at":"2026-07-05T00:03:00.513542+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOFBEBK6CU44","created_at":"2026-07-05T00:03:00.513542+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOFBEBK6CU443C55","created_at":"2026-07-05T00:03:00.513542+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOFBEBK6","created_at":"2026-07-05T00:03:00.513542+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/DOFBEBK6CU443C55KJ5ZDXNV5J","json":"https://pith.science/pith/DOFBEBK6CU443C55KJ5ZDXNV5J.json","graph_json":"https://pith.science/api/pith-number/DOFBEBK6CU443C55KJ5ZDXNV5J/graph.json","events_json":"https://pith.science/api/pith-number/DOFBEBK6CU443C55KJ5ZDXNV5J/events.json","paper":"https://pith.science/paper/DOFBEBK6"},"agent_actions":{"view_html":"https://pith.science/pith/DOFBEBK6CU443C55KJ5ZDXNV5J","download_json":"https://pith.science/pith/DOFBEBK6CU443C55KJ5ZDXNV5J.json","view_paper":"https://pith.science/paper/DOFBEBK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04951&json=true","fetch_graph":"https://pith.science/api/pith-number/DOFBEBK6CU443C55KJ5ZDXNV5J/graph.json","fetch_events":"https://pith.science/api/pith-number/DOFBEBK6CU443C55KJ5ZDXNV5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOFBEBK6CU443C55KJ5ZDXNV5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOFBEBK6CU443C55KJ5ZDXNV5J/action/storage_attestation","attest_author":"https://pith.science/pith/DOFBEBK6CU443C55KJ5ZDXNV5J/action/author_attestation","sign_citation":"https://pith.science/pith/DOFBEBK6CU443C55KJ5ZDXNV5J/action/citation_signature","submit_replication":"https://pith.science/pith/DOFBEBK6CU443C55KJ5ZDXNV5J/action/replication_record"}},"created_at":"2026-07-05T00:03:00.513542+00:00","updated_at":"2026-07-05T00:03:00.513542+00:00"}