{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AEBHLUQQINJQDDBTFRR2JRWQ2D","short_pith_number":"pith:AEBHLUQQ","schema_version":"1.0","canonical_sha256":"010275d2104353018c332c63a4c6d0d0eb8e32cf60bd42e7230f23394f85f2db","source":{"kind":"arxiv","id":"1806.05236","version":7},"attestation_state":"computed","paper":{"title":"Manifold Mixup: Better Representations by Interpolating Hidden States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Aaron Courville, Alex Lamb, Amir Najafi, Christopher Beckham, David Lopez-Paz, Ioannis Mitliagkas, Vikas Verma, Yoshua Bengio","submitted_at":"2018-06-13T19:32:59Z","abstract_excerpt":"Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples. This includes distribution shifts, outliers, and adversarial examples. To address these issues, we propose Manifold Mixup, a simple regularizer that encourages neural networks to predict less confidently on interpolations of hidden representations. Manifold Mixup leverages semantic interpolations as additional training signal, obtaining neural networks with smoother decision boundaries at multiple levels of representation. As a resu"},"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":"1806.05236","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-13T19:32:59Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"183c073c2ae63ff60616346b8dcc42c83c3dde3f32a3410c936632765f30cdc7","abstract_canon_sha256":"cfa6dc94d8251733446b8c86303e178e42c1df86d7a9c90143a2ee70698e18a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:30.376878Z","signature_b64":"6g14wS6+2w9nhihJrDWg0yAXBMn+OxfWeod3HYf3v/uU3P2dWTJAhwS9nYED+7UAO7nBMPYT1BgEE7azE0QqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"010275d2104353018c332c63a4c6d0d0eb8e32cf60bd42e7230f23394f85f2db","last_reissued_at":"2026-05-17T23:46:30.376158Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:30.376158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Manifold Mixup: Better Representations by Interpolating Hidden States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Aaron Courville, Alex Lamb, Amir Najafi, Christopher Beckham, David Lopez-Paz, Ioannis Mitliagkas, Vikas Verma, Yoshua Bengio","submitted_at":"2018-06-13T19:32:59Z","abstract_excerpt":"Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples. This includes distribution shifts, outliers, and adversarial examples. To address these issues, we propose Manifold Mixup, a simple regularizer that encourages neural networks to predict less confidently on interpolations of hidden representations. Manifold Mixup leverages semantic interpolations as additional training signal, obtaining neural networks with smoother decision boundaries at multiple levels of representation. As a resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05236","kind":"arxiv","version":7},"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":"1806.05236","created_at":"2026-05-17T23:46:30.376273+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05236v7","created_at":"2026-05-17T23:46:30.376273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05236","created_at":"2026-05-17T23:46:30.376273+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEBHLUQQINJQ","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEBHLUQQINJQDDBT","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEBHLUQQ","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.08412","citing_title":"Data Interpolating Prediction: Alternative Interpretation of Mixup","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11172","citing_title":"Learning Data Augmentation Strategies for Object Detection","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06800","citing_title":"Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20248","citing_title":"Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEBHLUQQINJQDDBTFRR2JRWQ2D","json":"https://pith.science/pith/AEBHLUQQINJQDDBTFRR2JRWQ2D.json","graph_json":"https://pith.science/api/pith-number/AEBHLUQQINJQDDBTFRR2JRWQ2D/graph.json","events_json":"https://pith.science/api/pith-number/AEBHLUQQINJQDDBTFRR2JRWQ2D/events.json","paper":"https://pith.science/paper/AEBHLUQQ"},"agent_actions":{"view_html":"https://pith.science/pith/AEBHLUQQINJQDDBTFRR2JRWQ2D","download_json":"https://pith.science/pith/AEBHLUQQINJQDDBTFRR2JRWQ2D.json","view_paper":"https://pith.science/paper/AEBHLUQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05236&json=true","fetch_graph":"https://pith.science/api/pith-number/AEBHLUQQINJQDDBTFRR2JRWQ2D/graph.json","fetch_events":"https://pith.science/api/pith-number/AEBHLUQQINJQDDBTFRR2JRWQ2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEBHLUQQINJQDDBTFRR2JRWQ2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEBHLUQQINJQDDBTFRR2JRWQ2D/action/storage_attestation","attest_author":"https://pith.science/pith/AEBHLUQQINJQDDBTFRR2JRWQ2D/action/author_attestation","sign_citation":"https://pith.science/pith/AEBHLUQQINJQDDBTFRR2JRWQ2D/action/citation_signature","submit_replication":"https://pith.science/pith/AEBHLUQQINJQDDBTFRR2JRWQ2D/action/replication_record"}},"created_at":"2026-05-17T23:46:30.376273+00:00","updated_at":"2026-05-17T23:46:30.376273+00:00"}