{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OHXPWZTKMEXY5VHVQYNPHUDERZ","short_pith_number":"pith:OHXPWZTK","schema_version":"1.0","canonical_sha256":"71eefb666a612f8ed4f5861af3d0648e7b4f67e7924fe2e69ba0a3489c680435","source":{"kind":"arxiv","id":"2006.06049","version":3},"attestation_state":"computed","paper":{"title":"On Mixup Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jean-Philippe Vert, Luigi Carratino, Moustapha Ciss\\'e, Rodolphe Jenatton","submitted_at":"2020-06-10T20:11:46Z","abstract_excerpt":"Mixup is a data augmentation technique that creates new examples as convex combinations of training points and labels. This simple technique has empirically shown to improve the accuracy of many state-of-the-art models in different settings and applications, but the reasons behind this empirical success remain poorly understood. In this paper we take a substantial step in explaining the theoretical foundations of Mixup, by clarifying its regularization effects. We show that Mixup can be interpreted as standard empirical risk minimization estimator subject to a combination of data transformatio"},"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":"2006.06049","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T20:11:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4e6b6ecb3c1e4beeab14a952bc2a34e8a4366ea646404bffa195127ced928233","abstract_canon_sha256":"0adc679bf183e963cf190ae8db5ea24d470e044703939ce2ed10bd81a5987aec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:23.235554Z","signature_b64":"EuSqXZD2eam/T9h5tDKAMO4EMve+Ui+6hhnqjVejwTE1kmfyOcyi6SWaP/y7XXiyiy0CxIFGnJTb65+u0oeyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71eefb666a612f8ed4f5861af3d0648e7b4f67e7924fe2e69ba0a3489c680435","last_reissued_at":"2026-05-28T01:04:23.235118Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:23.235118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Mixup Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jean-Philippe Vert, Luigi Carratino, Moustapha Ciss\\'e, Rodolphe Jenatton","submitted_at":"2020-06-10T20:11:46Z","abstract_excerpt":"Mixup is a data augmentation technique that creates new examples as convex combinations of training points and labels. This simple technique has empirically shown to improve the accuracy of many state-of-the-art models in different settings and applications, but the reasons behind this empirical success remain poorly understood. In this paper we take a substantial step in explaining the theoretical foundations of Mixup, by clarifying its regularization effects. We show that Mixup can be interpreted as standard empirical risk minimization estimator subject to a combination of data transformatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06049","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.06049/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2006.06049","created_at":"2026-05-28T01:04:23.235174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06049v3","created_at":"2026-05-28T01:04:23.235174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06049","created_at":"2026-05-28T01:04:23.235174+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHXPWZTKMEXY","created_at":"2026-05-28T01:04:23.235174+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHXPWZTKMEXY5VHV","created_at":"2026-05-28T01:04:23.235174+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHXPWZTK","created_at":"2026-05-28T01:04:23.235174+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/OHXPWZTKMEXY5VHVQYNPHUDERZ","json":"https://pith.science/pith/OHXPWZTKMEXY5VHVQYNPHUDERZ.json","graph_json":"https://pith.science/api/pith-number/OHXPWZTKMEXY5VHVQYNPHUDERZ/graph.json","events_json":"https://pith.science/api/pith-number/OHXPWZTKMEXY5VHVQYNPHUDERZ/events.json","paper":"https://pith.science/paper/OHXPWZTK"},"agent_actions":{"view_html":"https://pith.science/pith/OHXPWZTKMEXY5VHVQYNPHUDERZ","download_json":"https://pith.science/pith/OHXPWZTKMEXY5VHVQYNPHUDERZ.json","view_paper":"https://pith.science/paper/OHXPWZTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06049&json=true","fetch_graph":"https://pith.science/api/pith-number/OHXPWZTKMEXY5VHVQYNPHUDERZ/graph.json","fetch_events":"https://pith.science/api/pith-number/OHXPWZTKMEXY5VHVQYNPHUDERZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHXPWZTKMEXY5VHVQYNPHUDERZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHXPWZTKMEXY5VHVQYNPHUDERZ/action/storage_attestation","attest_author":"https://pith.science/pith/OHXPWZTKMEXY5VHVQYNPHUDERZ/action/author_attestation","sign_citation":"https://pith.science/pith/OHXPWZTKMEXY5VHVQYNPHUDERZ/action/citation_signature","submit_replication":"https://pith.science/pith/OHXPWZTKMEXY5VHVQYNPHUDERZ/action/replication_record"}},"created_at":"2026-05-28T01:04:23.235174+00:00","updated_at":"2026-05-28T01:04:23.235174+00:00"}