{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BYD3ZZAJ24FMDIPNBMSKWVUDM2","short_pith_number":"pith:BYD3ZZAJ","schema_version":"1.0","canonical_sha256":"0e07bce409d70ac1a1ed0b24ab568366ae2f2a26f6afc9d9e884e013026fe966","source":{"kind":"arxiv","id":"1809.02499","version":3},"attestation_state":"computed","paper":{"title":"MixUp as Locally Linear Out-Of-Manifold Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyu Guo, Richong Zhang, Yongyi Mao","submitted_at":"2018-09-07T14:26:17Z","abstract_excerpt":"MixUp is a recently proposed data-augmentation scheme, which linearly interpolates a random pair of training examples and correspondingly the one-hot representations of their labels. Training deep neural networks with such additional data is shown capable of significantly improving the predictive accuracy of the current art. The power of MixUp, however, is primarily established empirically and its working and effectiveness have not been explained in any depth. In this paper, we develop an understanding for MixUp as a form of \"out-of-manifold regularization\", which imposes certain \"local linear"},"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":"1809.02499","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-07T14:26:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"38cce064a2144a50b6ea2c3980e19d72cbb41e237acebddc6e4bef9c2c154e11","abstract_canon_sha256":"9ac3ce010a6261a11d2941f48939477febec91e953f2f207477b74194013cb2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:08.066729Z","signature_b64":"R7aPS4p/LciDNOxome/YeoAB7ZsZ0rZx/zQHDCze97A6RtNppCuM8YMcZwvUKG6nE15v7K/vzjfS8OtYKGgeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e07bce409d70ac1a1ed0b24ab568366ae2f2a26f6afc9d9e884e013026fe966","last_reissued_at":"2026-05-18T00:00:08.066128Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:08.066128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixUp as Locally Linear Out-Of-Manifold Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyu Guo, Richong Zhang, Yongyi Mao","submitted_at":"2018-09-07T14:26:17Z","abstract_excerpt":"MixUp is a recently proposed data-augmentation scheme, which linearly interpolates a random pair of training examples and correspondingly the one-hot representations of their labels. Training deep neural networks with such additional data is shown capable of significantly improving the predictive accuracy of the current art. The power of MixUp, however, is primarily established empirically and its working and effectiveness have not been explained in any depth. In this paper, we develop an understanding for MixUp as a form of \"out-of-manifold regularization\", which imposes certain \"local linear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02499","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":"1809.02499","created_at":"2026-05-18T00:00:08.066196+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02499v3","created_at":"2026-05-18T00:00:08.066196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02499","created_at":"2026-05-18T00:00:08.066196+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYD3ZZAJ24FM","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYD3ZZAJ24FMDIPN","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYD3ZZAJ","created_at":"2026-05-18T12:32:16.446611+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/BYD3ZZAJ24FMDIPNBMSKWVUDM2","json":"https://pith.science/pith/BYD3ZZAJ24FMDIPNBMSKWVUDM2.json","graph_json":"https://pith.science/api/pith-number/BYD3ZZAJ24FMDIPNBMSKWVUDM2/graph.json","events_json":"https://pith.science/api/pith-number/BYD3ZZAJ24FMDIPNBMSKWVUDM2/events.json","paper":"https://pith.science/paper/BYD3ZZAJ"},"agent_actions":{"view_html":"https://pith.science/pith/BYD3ZZAJ24FMDIPNBMSKWVUDM2","download_json":"https://pith.science/pith/BYD3ZZAJ24FMDIPNBMSKWVUDM2.json","view_paper":"https://pith.science/paper/BYD3ZZAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02499&json=true","fetch_graph":"https://pith.science/api/pith-number/BYD3ZZAJ24FMDIPNBMSKWVUDM2/graph.json","fetch_events":"https://pith.science/api/pith-number/BYD3ZZAJ24FMDIPNBMSKWVUDM2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYD3ZZAJ24FMDIPNBMSKWVUDM2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYD3ZZAJ24FMDIPNBMSKWVUDM2/action/storage_attestation","attest_author":"https://pith.science/pith/BYD3ZZAJ24FMDIPNBMSKWVUDM2/action/author_attestation","sign_citation":"https://pith.science/pith/BYD3ZZAJ24FMDIPNBMSKWVUDM2/action/citation_signature","submit_replication":"https://pith.science/pith/BYD3ZZAJ24FMDIPNBMSKWVUDM2/action/replication_record"}},"created_at":"2026-05-18T00:00:08.066196+00:00","updated_at":"2026-05-18T00:00:08.066196+00:00"}