{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6FSYTI456QJ42PE232BR3JN5JG","short_pith_number":"pith:6FSYTI45","schema_version":"1.0","canonical_sha256":"f16589a39df413cd3c9ade831da5bd499257a158434c9912350b9896053d4458","source":{"kind":"arxiv","id":"2108.12296","version":2},"attestation_state":"computed","paper":{"title":"Contrastive Mixup: Self- and Semi-Supervised learning for Tabular Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Pazoki, Majid Sarrafzadeh, Sajad Darabi, Shayan Fazeli, Sriram Sankararaman","submitted_at":"2021-08-27T14:09:13Z","abstract_excerpt":"Recent literature in self-supervised has demonstrated significant progress in closing the gap between supervised and unsupervised methods in the image and text domains. These methods rely on domain-specific augmentations that are not directly amenable to the tabular domain. Instead, we introduce Contrastive Mixup, a semi-supervised learning framework for tabular data and demonstrate its effectiveness in limited annotated data settings. Our proposed method leverages Mixup-based augmentation under the manifold assumption by mapping samples to a low dimensional latent space and encourage interpol"},"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":"2108.12296","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-27T14:09:13Z","cross_cats_sorted":[],"title_canon_sha256":"b4b5928e97ba42116cdba03102c613eadfe9c9b42b5452965031ec6be08ad07c","abstract_canon_sha256":"fa33dfcd90abfcecf330eb27cd11622070002f48631b0ba601403bed15d2d77a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:10:41.920004Z","signature_b64":"AaFDz0qIrZv5FgxiXmSHaEsr3kP8/wgfJ5zkYPZL5xqbTEkcqTH/FDruIrzsDSO+kbofw53QpbXarRBLW+dDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f16589a39df413cd3c9ade831da5bd499257a158434c9912350b9896053d4458","last_reissued_at":"2026-07-05T03:10:41.919675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:10:41.919675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Mixup: Self- and Semi-Supervised learning for Tabular Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Pazoki, Majid Sarrafzadeh, Sajad Darabi, Shayan Fazeli, Sriram Sankararaman","submitted_at":"2021-08-27T14:09:13Z","abstract_excerpt":"Recent literature in self-supervised has demonstrated significant progress in closing the gap between supervised and unsupervised methods in the image and text domains. These methods rely on domain-specific augmentations that are not directly amenable to the tabular domain. Instead, we introduce Contrastive Mixup, a semi-supervised learning framework for tabular data and demonstrate its effectiveness in limited annotated data settings. Our proposed method leverages Mixup-based augmentation under the manifold assumption by mapping samples to a low dimensional latent space and encourage interpol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.12296","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.12296/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":"2108.12296","created_at":"2026-07-05T03:10:41.919728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.12296v2","created_at":"2026-07-05T03:10:41.919728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.12296","created_at":"2026-07-05T03:10:41.919728+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FSYTI456QJ4","created_at":"2026-07-05T03:10:41.919728+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FSYTI456QJ42PE2","created_at":"2026-07-05T03:10:41.919728+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FSYTI45","created_at":"2026-07-05T03:10:41.919728+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/6FSYTI456QJ42PE232BR3JN5JG","json":"https://pith.science/pith/6FSYTI456QJ42PE232BR3JN5JG.json","graph_json":"https://pith.science/api/pith-number/6FSYTI456QJ42PE232BR3JN5JG/graph.json","events_json":"https://pith.science/api/pith-number/6FSYTI456QJ42PE232BR3JN5JG/events.json","paper":"https://pith.science/paper/6FSYTI45"},"agent_actions":{"view_html":"https://pith.science/pith/6FSYTI456QJ42PE232BR3JN5JG","download_json":"https://pith.science/pith/6FSYTI456QJ42PE232BR3JN5JG.json","view_paper":"https://pith.science/paper/6FSYTI45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.12296&json=true","fetch_graph":"https://pith.science/api/pith-number/6FSYTI456QJ42PE232BR3JN5JG/graph.json","fetch_events":"https://pith.science/api/pith-number/6FSYTI456QJ42PE232BR3JN5JG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FSYTI456QJ42PE232BR3JN5JG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FSYTI456QJ42PE232BR3JN5JG/action/storage_attestation","attest_author":"https://pith.science/pith/6FSYTI456QJ42PE232BR3JN5JG/action/author_attestation","sign_citation":"https://pith.science/pith/6FSYTI456QJ42PE232BR3JN5JG/action/citation_signature","submit_replication":"https://pith.science/pith/6FSYTI456QJ42PE232BR3JN5JG/action/replication_record"}},"created_at":"2026-07-05T03:10:41.919728+00:00","updated_at":"2026-07-05T03:10:41.919728+00:00"}