{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M7WZFPFXPTN7PFJZ5C5UGLZR7R","short_pith_number":"pith:M7WZFPFX","schema_version":"1.0","canonical_sha256":"67ed92bcb77cdbf79539e8bb432f31fc771f5371fa58e5024e57a1dfbdd3359a","source":{"kind":"arxiv","id":"2210.16413","version":1},"attestation_state":"computed","paper":{"title":"When does mixup promote local linearity in learned representations?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Krishna Menon, Andreas Veit, Arslan Chaudhry, Sadeep Jayasumana, Sanjiv Kumar, Srikumar Ramalingam","submitted_at":"2022-10-28T21:27:33Z","abstract_excerpt":"Mixup is a regularization technique that artificially produces new samples using convex combinations of original training points. This simple technique has shown strong empirical performance, and has been heavily used as part of semi-supervised learning techniques such as mixmatch~\\citep{berthelot2019mixmatch} and interpolation consistent training (ICT)~\\citep{verma2019interpolation}. In this paper, we look at Mixup through a \\emph{representation learning} lens in a semi-supervised learning setup. In particular, we study the role of Mixup in promoting linearity in the learned network represent"},"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":"2210.16413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-28T21:27:33Z","cross_cats_sorted":[],"title_canon_sha256":"24eafe1130c7e2215e4da51a8e983e168ad9fded14c853ed8025dc2ac34d5530","abstract_canon_sha256":"291c9fc07e2c297ce2d1712bdc45026a144351fe7dfad7cd753aad53600b3718"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:46.021974Z","signature_b64":"cLaMUcOCJwHcHfVwNEd3WIeUPuD1k3rsynziv1FMlWZqYj5HcBJi93tEFJtDIAlWf+V/g96w2HWkFw+PgjNXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67ed92bcb77cdbf79539e8bb432f31fc771f5371fa58e5024e57a1dfbdd3359a","last_reissued_at":"2026-07-05T05:11:46.021570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:46.021570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When does mixup promote local linearity in learned representations?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Krishna Menon, Andreas Veit, Arslan Chaudhry, Sadeep Jayasumana, Sanjiv Kumar, Srikumar Ramalingam","submitted_at":"2022-10-28T21:27:33Z","abstract_excerpt":"Mixup is a regularization technique that artificially produces new samples using convex combinations of original training points. This simple technique has shown strong empirical performance, and has been heavily used as part of semi-supervised learning techniques such as mixmatch~\\citep{berthelot2019mixmatch} and interpolation consistent training (ICT)~\\citep{verma2019interpolation}. In this paper, we look at Mixup through a \\emph{representation learning} lens in a semi-supervised learning setup. In particular, we study the role of Mixup in promoting linearity in the learned network represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16413","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.16413/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":"2210.16413","created_at":"2026-07-05T05:11:46.021627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16413v1","created_at":"2026-07-05T05:11:46.021627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16413","created_at":"2026-07-05T05:11:46.021627+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7WZFPFXPTN7","created_at":"2026-07-05T05:11:46.021627+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7WZFPFXPTN7PFJZ","created_at":"2026-07-05T05:11:46.021627+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7WZFPFX","created_at":"2026-07-05T05:11:46.021627+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/M7WZFPFXPTN7PFJZ5C5UGLZR7R","json":"https://pith.science/pith/M7WZFPFXPTN7PFJZ5C5UGLZR7R.json","graph_json":"https://pith.science/api/pith-number/M7WZFPFXPTN7PFJZ5C5UGLZR7R/graph.json","events_json":"https://pith.science/api/pith-number/M7WZFPFXPTN7PFJZ5C5UGLZR7R/events.json","paper":"https://pith.science/paper/M7WZFPFX"},"agent_actions":{"view_html":"https://pith.science/pith/M7WZFPFXPTN7PFJZ5C5UGLZR7R","download_json":"https://pith.science/pith/M7WZFPFXPTN7PFJZ5C5UGLZR7R.json","view_paper":"https://pith.science/paper/M7WZFPFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16413&json=true","fetch_graph":"https://pith.science/api/pith-number/M7WZFPFXPTN7PFJZ5C5UGLZR7R/graph.json","fetch_events":"https://pith.science/api/pith-number/M7WZFPFXPTN7PFJZ5C5UGLZR7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7WZFPFXPTN7PFJZ5C5UGLZR7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7WZFPFXPTN7PFJZ5C5UGLZR7R/action/storage_attestation","attest_author":"https://pith.science/pith/M7WZFPFXPTN7PFJZ5C5UGLZR7R/action/author_attestation","sign_citation":"https://pith.science/pith/M7WZFPFXPTN7PFJZ5C5UGLZR7R/action/citation_signature","submit_replication":"https://pith.science/pith/M7WZFPFXPTN7PFJZ5C5UGLZR7R/action/replication_record"}},"created_at":"2026-07-05T05:11:46.021627+00:00","updated_at":"2026-07-05T05:11:46.021627+00:00"}