{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZCIU2UL5QVJWY23ZOCDV2RBKEC","short_pith_number":"pith:ZCIU2UL5","schema_version":"1.0","canonical_sha256":"c8914d517d85536c6b7970875d442a20819406258c6910c591a22fd8eb9d6433","source":{"kind":"arxiv","id":"1609.08764","version":2},"attestation_state":"computed","paper":{"title":"Understanding data augmentation for classification: when to warp?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Gatt, Mark D. McDonnell, Sebastien C. Wong, Victor Stamatescu","submitted_at":"2016-09-28T04:37:32Z","abstract_excerpt":"In this paper we investigate the benefit of augmenting data with synthetically created samples when training a machine learning classifier. Two approaches for creating additional training samples are data warping, which generates additional samples through transformations applied in the data-space, and synthetic over-sampling, which creates additional samples in feature-space. We experimentally evaluate the benefits of data augmentation for a convolutional backpropagation-trained neural network, a convolutional support vector machine and a convolutional extreme learning machine classifier, usi"},"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":"1609.08764","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-28T04:37:32Z","cross_cats_sorted":[],"title_canon_sha256":"8db66537f1c5d353874c6d8bb861525625b4c6b9cfe6396b5fc5194797ce9792","abstract_canon_sha256":"f81605610447388a93a71759affcf871487b3057e8f209ba2679c07d8bd99fa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:37.563536Z","signature_b64":"gz3TgnER+zg8ncK9p0dTgwSvwPmZni47XgY+dPWqDkK12z9hM22JX0QZDF51RwCdxOMGPbHUFUrEJkFqqHdjCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8914d517d85536c6b7970875d442a20819406258c6910c591a22fd8eb9d6433","last_reissued_at":"2026-05-18T00:56:37.562784Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:37.562784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding data augmentation for classification: when to warp?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Gatt, Mark D. McDonnell, Sebastien C. Wong, Victor Stamatescu","submitted_at":"2016-09-28T04:37:32Z","abstract_excerpt":"In this paper we investigate the benefit of augmenting data with synthetically created samples when training a machine learning classifier. Two approaches for creating additional training samples are data warping, which generates additional samples through transformations applied in the data-space, and synthetic over-sampling, which creates additional samples in feature-space. We experimentally evaluate the benefits of data augmentation for a convolutional backpropagation-trained neural network, a convolutional support vector machine and a convolutional extreme learning machine classifier, usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.08764","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":"1609.08764","created_at":"2026-05-18T00:56:37.562904+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.08764v2","created_at":"2026-05-18T00:56:37.562904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.08764","created_at":"2026-05-18T00:56:37.562904+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCIU2UL5QVJW","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCIU2UL5QVJWY23Z","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCIU2UL5","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10861","citing_title":"Assessing Post Deletion in Sina Weibo: Multi-modal Classification of Hot Topics","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZCIU2UL5QVJWY23ZOCDV2RBKEC","json":"https://pith.science/pith/ZCIU2UL5QVJWY23ZOCDV2RBKEC.json","graph_json":"https://pith.science/api/pith-number/ZCIU2UL5QVJWY23ZOCDV2RBKEC/graph.json","events_json":"https://pith.science/api/pith-number/ZCIU2UL5QVJWY23ZOCDV2RBKEC/events.json","paper":"https://pith.science/paper/ZCIU2UL5"},"agent_actions":{"view_html":"https://pith.science/pith/ZCIU2UL5QVJWY23ZOCDV2RBKEC","download_json":"https://pith.science/pith/ZCIU2UL5QVJWY23ZOCDV2RBKEC.json","view_paper":"https://pith.science/paper/ZCIU2UL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.08764&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCIU2UL5QVJWY23ZOCDV2RBKEC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCIU2UL5QVJWY23ZOCDV2RBKEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCIU2UL5QVJWY23ZOCDV2RBKEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCIU2UL5QVJWY23ZOCDV2RBKEC/action/storage_attestation","attest_author":"https://pith.science/pith/ZCIU2UL5QVJWY23ZOCDV2RBKEC/action/author_attestation","sign_citation":"https://pith.science/pith/ZCIU2UL5QVJWY23ZOCDV2RBKEC/action/citation_signature","submit_replication":"https://pith.science/pith/ZCIU2UL5QVJWY23ZOCDV2RBKEC/action/replication_record"}},"created_at":"2026-05-18T00:56:37.562904+00:00","updated_at":"2026-05-18T00:56:37.562904+00:00"}