{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HSNXMW6TXTNXZGUC7WHF2QMSRW","short_pith_number":"pith:HSNXMW6T","schema_version":"1.0","canonical_sha256":"3c9b765bd3bcdb7c9a82fd8e5d41928d87bc62526b70cccf50c68987adb6b575","source":{"kind":"arxiv","id":"1902.10887","version":3},"attestation_state":"computed","paper":{"title":"Towards Robust ResNet: A Small Step but A Giant Leap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Han, Jingfeng Zhang, Kian Hsiang Low, Laura Wynter, Mohan Kankanhalli","submitted_at":"2019-02-28T04:24:46Z","abstract_excerpt":"This paper presents a simple yet principled approach to boosting the robustness of the residual network (ResNet) that is motivated by the dynamical system perspective. Namely, a deep neural network can be interpreted using a partial differential equation, which naturally inspires us to characterize ResNet by an explicit Euler method. Our analytical studies reveal that the step factor h in the Euler method is able to control the robustness of ResNet in both its training and generalization. Specifically, we prove that a small step factor h can benefit the training robustness for back-propagation"},"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":"1902.10887","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-28T04:24:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"db70dc5b722c88cba04c4a61f552a16e2ab782b7333403d6aab026fd10150bd8","abstract_canon_sha256":"e8ef7505f5d22153bc4203f8c20a3a869ddfb333b5caf45a9957204d6a2ec004"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:44.815802Z","signature_b64":"tHEk3mEczuK9n1Et9Y6OUwle1JUcMdBv1UX2p9H3Mhza2B8KDQYjUvSDdobQEnQVVszN8hSqJ+mhPeVzIH+bDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c9b765bd3bcdb7c9a82fd8e5d41928d87bc62526b70cccf50c68987adb6b575","last_reissued_at":"2026-05-17T23:41:44.815306Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:44.815306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Robust ResNet: A Small Step but A Giant Leap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Han, Jingfeng Zhang, Kian Hsiang Low, Laura Wynter, Mohan Kankanhalli","submitted_at":"2019-02-28T04:24:46Z","abstract_excerpt":"This paper presents a simple yet principled approach to boosting the robustness of the residual network (ResNet) that is motivated by the dynamical system perspective. Namely, a deep neural network can be interpreted using a partial differential equation, which naturally inspires us to characterize ResNet by an explicit Euler method. Our analytical studies reveal that the step factor h in the Euler method is able to control the robustness of ResNet in both its training and generalization. Specifically, we prove that a small step factor h can benefit the training robustness for back-propagation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10887","kind":"arxiv","version":3},"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":"1902.10887","created_at":"2026-05-17T23:41:44.815382+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10887v3","created_at":"2026-05-17T23:41:44.815382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10887","created_at":"2026-05-17T23:41:44.815382+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSNXMW6TXTNX","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSNXMW6TXTNXZGUC","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSNXMW6T","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06933","citing_title":"Neural equilibria for long-term prediction of nonlinear conservation laws","ref_index":87,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSNXMW6TXTNXZGUC7WHF2QMSRW","json":"https://pith.science/pith/HSNXMW6TXTNXZGUC7WHF2QMSRW.json","graph_json":"https://pith.science/api/pith-number/HSNXMW6TXTNXZGUC7WHF2QMSRW/graph.json","events_json":"https://pith.science/api/pith-number/HSNXMW6TXTNXZGUC7WHF2QMSRW/events.json","paper":"https://pith.science/paper/HSNXMW6T"},"agent_actions":{"view_html":"https://pith.science/pith/HSNXMW6TXTNXZGUC7WHF2QMSRW","download_json":"https://pith.science/pith/HSNXMW6TXTNXZGUC7WHF2QMSRW.json","view_paper":"https://pith.science/paper/HSNXMW6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10887&json=true","fetch_graph":"https://pith.science/api/pith-number/HSNXMW6TXTNXZGUC7WHF2QMSRW/graph.json","fetch_events":"https://pith.science/api/pith-number/HSNXMW6TXTNXZGUC7WHF2QMSRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSNXMW6TXTNXZGUC7WHF2QMSRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSNXMW6TXTNXZGUC7WHF2QMSRW/action/storage_attestation","attest_author":"https://pith.science/pith/HSNXMW6TXTNXZGUC7WHF2QMSRW/action/author_attestation","sign_citation":"https://pith.science/pith/HSNXMW6TXTNXZGUC7WHF2QMSRW/action/citation_signature","submit_replication":"https://pith.science/pith/HSNXMW6TXTNXZGUC7WHF2QMSRW/action/replication_record"}},"created_at":"2026-05-17T23:41:44.815382+00:00","updated_at":"2026-05-17T23:41:44.815382+00:00"}