{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AOBPM7BQLVEFLIJ6RVD3HDQYF3","short_pith_number":"pith:AOBPM7BQ","schema_version":"1.0","canonical_sha256":"0382f67c305d4855a13e8d47b38e182ec2a7687e4123c3c4da70b3a5b1d7a8f0","source":{"kind":"arxiv","id":"1805.03438","version":1},"attestation_state":"computed","paper":{"title":"Robust Classification with Convolutional Prototype Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Lin Liu, Fei Yin, Hong-Ming Yang, Xu-Yao Zhang","submitted_at":"2018-05-09T09:55:45Z","abstract_excerpt":"Convolutional neural networks (CNNs) have been widely used for image classification. Despite its high accuracies, CNN has been shown to be easily fooled by some adversarial examples, indicating that CNN is not robust enough for pattern classification. In this paper, we argue that the lack of robustness for CNN is caused by the softmax layer, which is a totally discriminative model and based on the assumption of closed world (i.e., with a fixed number of categories). To improve the robustness, we propose a novel learning framework called convolutional prototype learning (CPL). The advantage of "},"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":"1805.03438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-09T09:55:45Z","cross_cats_sorted":[],"title_canon_sha256":"a73e12a25b16d402dec0c27732ae5035b2358b37bb489c6a8bc7008105b2d58d","abstract_canon_sha256":"477e6d62e633e49f4eb6359fef3293ee6af35a6ae429794bd7974cbe648b0122"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:20.230619Z","signature_b64":"WnX1GPVn2/6tAJgqEAKDgmn/TGOEUsMGCeqBRb5LRAzYM34tqXeqQJ7BbhNU9FHClt4xkLknzk4eGavfw8L+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0382f67c305d4855a13e8d47b38e182ec2a7687e4123c3c4da70b3a5b1d7a8f0","last_reissued_at":"2026-05-18T00:16:20.229997Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:20.229997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Classification with Convolutional Prototype Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Lin Liu, Fei Yin, Hong-Ming Yang, Xu-Yao Zhang","submitted_at":"2018-05-09T09:55:45Z","abstract_excerpt":"Convolutional neural networks (CNNs) have been widely used for image classification. Despite its high accuracies, CNN has been shown to be easily fooled by some adversarial examples, indicating that CNN is not robust enough for pattern classification. In this paper, we argue that the lack of robustness for CNN is caused by the softmax layer, which is a totally discriminative model and based on the assumption of closed world (i.e., with a fixed number of categories). To improve the robustness, we propose a novel learning framework called convolutional prototype learning (CPL). The advantage of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03438","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":"1805.03438","created_at":"2026-05-18T00:16:20.230081+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.03438v1","created_at":"2026-05-18T00:16:20.230081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03438","created_at":"2026-05-18T00:16:20.230081+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOBPM7BQLVEF","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOBPM7BQLVEFLIJ6","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOBPM7BQ","created_at":"2026-05-18T12:32:13.499390+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/AOBPM7BQLVEFLIJ6RVD3HDQYF3","json":"https://pith.science/pith/AOBPM7BQLVEFLIJ6RVD3HDQYF3.json","graph_json":"https://pith.science/api/pith-number/AOBPM7BQLVEFLIJ6RVD3HDQYF3/graph.json","events_json":"https://pith.science/api/pith-number/AOBPM7BQLVEFLIJ6RVD3HDQYF3/events.json","paper":"https://pith.science/paper/AOBPM7BQ"},"agent_actions":{"view_html":"https://pith.science/pith/AOBPM7BQLVEFLIJ6RVD3HDQYF3","download_json":"https://pith.science/pith/AOBPM7BQLVEFLIJ6RVD3HDQYF3.json","view_paper":"https://pith.science/paper/AOBPM7BQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.03438&json=true","fetch_graph":"https://pith.science/api/pith-number/AOBPM7BQLVEFLIJ6RVD3HDQYF3/graph.json","fetch_events":"https://pith.science/api/pith-number/AOBPM7BQLVEFLIJ6RVD3HDQYF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOBPM7BQLVEFLIJ6RVD3HDQYF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOBPM7BQLVEFLIJ6RVD3HDQYF3/action/storage_attestation","attest_author":"https://pith.science/pith/AOBPM7BQLVEFLIJ6RVD3HDQYF3/action/author_attestation","sign_citation":"https://pith.science/pith/AOBPM7BQLVEFLIJ6RVD3HDQYF3/action/citation_signature","submit_replication":"https://pith.science/pith/AOBPM7BQLVEFLIJ6RVD3HDQYF3/action/replication_record"}},"created_at":"2026-05-18T00:16:20.230081+00:00","updated_at":"2026-05-18T00:16:20.230081+00:00"}