{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IGGMRA5YN5VKPYICASRYEJYYJH","short_pith_number":"pith:IGGMRA5Y","schema_version":"1.0","canonical_sha256":"418cc883b86f6aa7e10204a382271849cd6e9c76674b9e2d61e6dd354712f3cb","source":{"kind":"arxiv","id":"1802.07896","version":4},"attestation_state":"computed","paper":{"title":"L2-Nonexpansive Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Haifeng Qian, Mark N. Wegman","submitted_at":"2018-02-22T04:01:18Z","abstract_excerpt":"This paper proposes a class of well-conditioned neural networks in which a unit amount of change in the inputs causes at most a unit amount of change in the outputs or any of the internal layers. We develop the known methodology of controlling Lipschitz constants to realize its full potential in maximizing robustness, with a new regularization scheme for linear layers, new ways to adapt nonlinearities and a new loss function. With MNIST and CIFAR-10 classifiers, we demonstrate a number of advantages. Without needing any adversarial training, the proposed classifiers exceed the state of the art"},"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":"1802.07896","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-22T04:01:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6d25bf6cc236d7efaa81626575e3529ce452135575883832d7f2542ed852a818","abstract_canon_sha256":"606bb7a7fd9ffadc03ca547dbf480213aa55fea583f2e83776cd380f72e360fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:41.578262Z","signature_b64":"qUjuAdRo9YOkXgJYWKB6VC6SvKIOoCCv/ycgNCa5mS5Nj/phI8OyU7JOQRVHhxsghARuyuuAEF9HkJ8Ty1vyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"418cc883b86f6aa7e10204a382271849cd6e9c76674b9e2d61e6dd354712f3cb","last_reissued_at":"2026-05-17T23:54:41.577842Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:41.577842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L2-Nonexpansive Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Haifeng Qian, Mark N. Wegman","submitted_at":"2018-02-22T04:01:18Z","abstract_excerpt":"This paper proposes a class of well-conditioned neural networks in which a unit amount of change in the inputs causes at most a unit amount of change in the outputs or any of the internal layers. We develop the known methodology of controlling Lipschitz constants to realize its full potential in maximizing robustness, with a new regularization scheme for linear layers, new ways to adapt nonlinearities and a new loss function. With MNIST and CIFAR-10 classifiers, we demonstrate a number of advantages. Without needing any adversarial training, the proposed classifiers exceed the state of the art"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07896","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":"1802.07896","created_at":"2026-05-17T23:54:41.577901+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.07896v4","created_at":"2026-05-17T23:54:41.577901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07896","created_at":"2026-05-17T23:54:41.577901+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGGMRA5YN5VK","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGGMRA5YN5VKPYIC","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGGMRA5Y","created_at":"2026-05-18T12:32:28.185984+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/IGGMRA5YN5VKPYICASRYEJYYJH","json":"https://pith.science/pith/IGGMRA5YN5VKPYICASRYEJYYJH.json","graph_json":"https://pith.science/api/pith-number/IGGMRA5YN5VKPYICASRYEJYYJH/graph.json","events_json":"https://pith.science/api/pith-number/IGGMRA5YN5VKPYICASRYEJYYJH/events.json","paper":"https://pith.science/paper/IGGMRA5Y"},"agent_actions":{"view_html":"https://pith.science/pith/IGGMRA5YN5VKPYICASRYEJYYJH","download_json":"https://pith.science/pith/IGGMRA5YN5VKPYICASRYEJYYJH.json","view_paper":"https://pith.science/paper/IGGMRA5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.07896&json=true","fetch_graph":"https://pith.science/api/pith-number/IGGMRA5YN5VKPYICASRYEJYYJH/graph.json","fetch_events":"https://pith.science/api/pith-number/IGGMRA5YN5VKPYICASRYEJYYJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGGMRA5YN5VKPYICASRYEJYYJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGGMRA5YN5VKPYICASRYEJYYJH/action/storage_attestation","attest_author":"https://pith.science/pith/IGGMRA5YN5VKPYICASRYEJYYJH/action/author_attestation","sign_citation":"https://pith.science/pith/IGGMRA5YN5VKPYICASRYEJYYJH/action/citation_signature","submit_replication":"https://pith.science/pith/IGGMRA5YN5VKPYICASRYEJYYJH/action/replication_record"}},"created_at":"2026-05-17T23:54:41.577901+00:00","updated_at":"2026-05-17T23:54:41.577901+00:00"}