{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MDZGAIT7SPRHBJLBSPF5RZ2OKV","short_pith_number":"pith:MDZGAIT7","schema_version":"1.0","canonical_sha256":"60f260227f93e270a56193cbd8e74e55616a68900ab8e98c345d8306a0cb05d1","source":{"kind":"arxiv","id":"2412.07039","version":1},"attestation_state":"computed","paper":{"title":"Data Augmentation with Variational Autoencoder for Imbalanced Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arthur Charpentier, Denys Pommeret, Samuel Stocksieker","submitted_at":"2024-12-09T22:59:03Z","abstract_excerpt":"Learning from an imbalanced distribution presents a major challenge in predictive modeling, as it generally leads to a reduction in the performance of standard algorithms. Various approaches exist to address this issue, but many of them concern classification problems, with a limited focus on regression. In this paper, we introduce a novel method aimed at enhancing learning on tabular data in the Imbalanced Regression (IR) framework, which remains a significant problem. We propose to use variational autoencoders (VAE) which are known as a powerful tool for synthetic data generation, offering a"},"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":"2412.07039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T22:59:03Z","cross_cats_sorted":[],"title_canon_sha256":"9860e69412b8739a5372fdd18e867bff013d22648af8e738c7790995ef12b2c0","abstract_canon_sha256":"5c274c3de5f652f12c9e17b3698d9c3033ce69cbb16f6d5939dd2c5082d7bd2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:02.714246Z","signature_b64":"8Kl7qxxRtI+CLQeF+S8/vzcC4Gs6VL+6QjlCQLGN+GRUEB78co++b06NUKhpzhavq5ocx4H0pnimTBI/ZS4sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60f260227f93e270a56193cbd8e74e55616a68900ab8e98c345d8306a0cb05d1","last_reissued_at":"2026-07-05T09:47:02.713783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:02.713783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation with Variational Autoencoder for Imbalanced Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arthur Charpentier, Denys Pommeret, Samuel Stocksieker","submitted_at":"2024-12-09T22:59:03Z","abstract_excerpt":"Learning from an imbalanced distribution presents a major challenge in predictive modeling, as it generally leads to a reduction in the performance of standard algorithms. Various approaches exist to address this issue, but many of them concern classification problems, with a limited focus on regression. In this paper, we introduce a novel method aimed at enhancing learning on tabular data in the Imbalanced Regression (IR) framework, which remains a significant problem. We propose to use variational autoencoders (VAE) which are known as a powerful tool for synthetic data generation, offering a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07039","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/2412.07039/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":"2412.07039","created_at":"2026-07-05T09:47:02.713841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07039v1","created_at":"2026-07-05T09:47:02.713841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07039","created_at":"2026-07-05T09:47:02.713841+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDZGAIT7SPRH","created_at":"2026-07-05T09:47:02.713841+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDZGAIT7SPRHBJLB","created_at":"2026-07-05T09:47:02.713841+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDZGAIT7","created_at":"2026-07-05T09:47:02.713841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06092","citing_title":"Taming Data Challenges in ML-based Security Tasks Using Generative AI","ref_index":94,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDZGAIT7SPRHBJLBSPF5RZ2OKV","json":"https://pith.science/pith/MDZGAIT7SPRHBJLBSPF5RZ2OKV.json","graph_json":"https://pith.science/api/pith-number/MDZGAIT7SPRHBJLBSPF5RZ2OKV/graph.json","events_json":"https://pith.science/api/pith-number/MDZGAIT7SPRHBJLBSPF5RZ2OKV/events.json","paper":"https://pith.science/paper/MDZGAIT7"},"agent_actions":{"view_html":"https://pith.science/pith/MDZGAIT7SPRHBJLBSPF5RZ2OKV","download_json":"https://pith.science/pith/MDZGAIT7SPRHBJLBSPF5RZ2OKV.json","view_paper":"https://pith.science/paper/MDZGAIT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07039&json=true","fetch_graph":"https://pith.science/api/pith-number/MDZGAIT7SPRHBJLBSPF5RZ2OKV/graph.json","fetch_events":"https://pith.science/api/pith-number/MDZGAIT7SPRHBJLBSPF5RZ2OKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDZGAIT7SPRHBJLBSPF5RZ2OKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDZGAIT7SPRHBJLBSPF5RZ2OKV/action/storage_attestation","attest_author":"https://pith.science/pith/MDZGAIT7SPRHBJLBSPF5RZ2OKV/action/author_attestation","sign_citation":"https://pith.science/pith/MDZGAIT7SPRHBJLBSPF5RZ2OKV/action/citation_signature","submit_replication":"https://pith.science/pith/MDZGAIT7SPRHBJLBSPF5RZ2OKV/action/replication_record"}},"created_at":"2026-07-05T09:47:02.713841+00:00","updated_at":"2026-07-05T09:47:02.713841+00:00"}