{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:W22NMRGJNQRIH6IFTW4TRGE4SK","short_pith_number":"pith:W22NMRGJ","schema_version":"1.0","canonical_sha256":"b6b4d644c96c2283f9059db938989c92a2be94493c83d298181b4e57f5ef7c57","source":{"kind":"arxiv","id":"1808.08282","version":2},"attestation_state":"computed","paper":{"title":"Controlling Over-generalization and its Effect on Adversarial Examples Generation and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Arezoo Rajabi, Azadeh Sadat Mozafari, Christian Gagne, Mahdieh Abbasi, Rakesh B. Bobba","submitted_at":"2018-08-21T02:05:57Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to confidently classify out-distribution samples from unknown classes into pre-defined known classes. Further, they are also vulnerable to adversarial examples. We are relating these two issues through the tendency of CNNs to over-generalize for areas of the input space not covered well by the training set. We show that a CNN augmented with an extra output class can act as a simple yet effective end-to-end model for con"},"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":"1808.08282","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-21T02:05:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b6dce5e91fe64c232e374973d6060cb389875e11cd65ed2b13d770316a526a24","abstract_canon_sha256":"e85467aaac2f63d70fa0c6c5fa444318012e076e82029c0d3a230b7e6410bcb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:07.384075Z","signature_b64":"vmHh9AQD7m3N43VM5aAzZXlQm9U36Eystcj0vTq1TuNV14QGvZOC0Kzs5YfwI+t//Td78qwX7GSxLcDMN9jAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6b4d644c96c2283f9059db938989c92a2be94493c83d298181b4e57f5ef7c57","last_reissued_at":"2026-05-18T00:04:07.383308Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:07.383308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlling Over-generalization and its Effect on Adversarial Examples Generation and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Arezoo Rajabi, Azadeh Sadat Mozafari, Christian Gagne, Mahdieh Abbasi, Rakesh B. Bobba","submitted_at":"2018-08-21T02:05:57Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to confidently classify out-distribution samples from unknown classes into pre-defined known classes. Further, they are also vulnerable to adversarial examples. We are relating these two issues through the tendency of CNNs to over-generalize for areas of the input space not covered well by the training set. We show that a CNN augmented with an extra output class can act as a simple yet effective end-to-end model for con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08282","kind":"arxiv","version":2},"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":"1808.08282","created_at":"2026-05-18T00:04:07.383437+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.08282v2","created_at":"2026-05-18T00:04:07.383437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08282","created_at":"2026-05-18T00:04:07.383437+00:00"},{"alias_kind":"pith_short_12","alias_value":"W22NMRGJNQRI","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"W22NMRGJNQRIH6IF","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"W22NMRGJ","created_at":"2026-05-18T12:32:59.047623+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/W22NMRGJNQRIH6IFTW4TRGE4SK","json":"https://pith.science/pith/W22NMRGJNQRIH6IFTW4TRGE4SK.json","graph_json":"https://pith.science/api/pith-number/W22NMRGJNQRIH6IFTW4TRGE4SK/graph.json","events_json":"https://pith.science/api/pith-number/W22NMRGJNQRIH6IFTW4TRGE4SK/events.json","paper":"https://pith.science/paper/W22NMRGJ"},"agent_actions":{"view_html":"https://pith.science/pith/W22NMRGJNQRIH6IFTW4TRGE4SK","download_json":"https://pith.science/pith/W22NMRGJNQRIH6IFTW4TRGE4SK.json","view_paper":"https://pith.science/paper/W22NMRGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.08282&json=true","fetch_graph":"https://pith.science/api/pith-number/W22NMRGJNQRIH6IFTW4TRGE4SK/graph.json","fetch_events":"https://pith.science/api/pith-number/W22NMRGJNQRIH6IFTW4TRGE4SK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W22NMRGJNQRIH6IFTW4TRGE4SK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W22NMRGJNQRIH6IFTW4TRGE4SK/action/storage_attestation","attest_author":"https://pith.science/pith/W22NMRGJNQRIH6IFTW4TRGE4SK/action/author_attestation","sign_citation":"https://pith.science/pith/W22NMRGJNQRIH6IFTW4TRGE4SK/action/citation_signature","submit_replication":"https://pith.science/pith/W22NMRGJNQRIH6IFTW4TRGE4SK/action/replication_record"}},"created_at":"2026-05-18T00:04:07.383437+00:00","updated_at":"2026-05-18T00:04:07.383437+00:00"}