{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WARCMRX3VWUWVPJWRILLLVHHCO","short_pith_number":"pith:WARCMRX3","schema_version":"1.0","canonical_sha256":"b0222646fbada96abd368a16b5d4e713a722acef976d93adef6b3af685616a69","source":{"kind":"arxiv","id":"1905.03177","version":1},"attestation_state":"computed","paper":{"title":"Does Data Augmentation Lead to Positive Margin?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dimitris Papailiopoulos, Po-Ling Loh, Shashank Rajput, Zachary Charles, Zhili Feng","submitted_at":"2019-05-08T16:03:06Z","abstract_excerpt":"Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying random noise, rotations, crops, or even adversarial perturbations to the input data. Although DA is widely used, its capacity to provably improve robustness is not fully understood. In this work, we analyze the robustness that DA begets by quantifying the margin that DA enforces on empirical risk minimizers. We first focus on linear separators, and then a class of nonlinear models whose labeling is constant within smal"},"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":"1905.03177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-08T16:03:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"73ec410274634291050bbba41a8599cfd4c14dbec0d55cd449c625f8c3183d7f","abstract_canon_sha256":"f5d0bd912d66057514057ea8ab36cfc2fea9c5504c6ff94db3b8a832453e9af7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:42.671337Z","signature_b64":"fUP+nEseEyzcuBkk1GLmY/9r9Lp0+t1pVYrdg+ql1za1LU2rNOL6GPchwOQ6GJ+uAWn9plzrLuGMrt1yEKbPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0222646fbada96abd368a16b5d4e713a722acef976d93adef6b3af685616a69","last_reissued_at":"2026-05-17T23:46:42.670717Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:42.670717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Data Augmentation Lead to Positive Margin?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dimitris Papailiopoulos, Po-Ling Loh, Shashank Rajput, Zachary Charles, Zhili Feng","submitted_at":"2019-05-08T16:03:06Z","abstract_excerpt":"Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying random noise, rotations, crops, or even adversarial perturbations to the input data. Although DA is widely used, its capacity to provably improve robustness is not fully understood. In this work, we analyze the robustness that DA begets by quantifying the margin that DA enforces on empirical risk minimizers. We first focus on linear separators, and then a class of nonlinear models whose labeling is constant within smal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03177","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":"1905.03177","created_at":"2026-05-17T23:46:42.670828+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.03177v1","created_at":"2026-05-17T23:46:42.670828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03177","created_at":"2026-05-17T23:46:42.670828+00:00"},{"alias_kind":"pith_short_12","alias_value":"WARCMRX3VWUW","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WARCMRX3VWUWVPJW","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WARCMRX3","created_at":"2026-05-18T12:33:30.264802+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/WARCMRX3VWUWVPJWRILLLVHHCO","json":"https://pith.science/pith/WARCMRX3VWUWVPJWRILLLVHHCO.json","graph_json":"https://pith.science/api/pith-number/WARCMRX3VWUWVPJWRILLLVHHCO/graph.json","events_json":"https://pith.science/api/pith-number/WARCMRX3VWUWVPJWRILLLVHHCO/events.json","paper":"https://pith.science/paper/WARCMRX3"},"agent_actions":{"view_html":"https://pith.science/pith/WARCMRX3VWUWVPJWRILLLVHHCO","download_json":"https://pith.science/pith/WARCMRX3VWUWVPJWRILLLVHHCO.json","view_paper":"https://pith.science/paper/WARCMRX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.03177&json=true","fetch_graph":"https://pith.science/api/pith-number/WARCMRX3VWUWVPJWRILLLVHHCO/graph.json","fetch_events":"https://pith.science/api/pith-number/WARCMRX3VWUWVPJWRILLLVHHCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WARCMRX3VWUWVPJWRILLLVHHCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WARCMRX3VWUWVPJWRILLLVHHCO/action/storage_attestation","attest_author":"https://pith.science/pith/WARCMRX3VWUWVPJWRILLLVHHCO/action/author_attestation","sign_citation":"https://pith.science/pith/WARCMRX3VWUWVPJWRILLLVHHCO/action/citation_signature","submit_replication":"https://pith.science/pith/WARCMRX3VWUWVPJWRILLLVHHCO/action/replication_record"}},"created_at":"2026-05-17T23:46:42.670828+00:00","updated_at":"2026-05-17T23:46:42.670828+00:00"}