{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:23HISIN332YEBQAEQLEUX5XEXX","short_pith_number":"pith:23HISIN3","schema_version":"1.0","canonical_sha256":"d6ce8921bbdeb040c00482c94bf6e4bdd90c5c0b9facefbc11b5e87be7ee7741","source":{"kind":"arxiv","id":"2302.09288","version":1},"attestation_state":"computed","paper":{"title":"Data Augmentation for Imbalanced Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Arthur Charpentier, Denys Pommeret, Samuel Stocksieker","submitted_at":"2023-02-18T11:23:34Z","abstract_excerpt":"In this work, we consider the problem of imbalanced data in a regression framework when the imbalanced phenomenon concerns continuous or discrete covariates. Such a situation can lead to biases in the estimates. In this case, we propose a data augmentation algorithm that combines a weighted resampling (WR) and a data augmentation (DA) procedure. In a first step, the DA procedure permits exploring a wider support than the initial one. In a second step, the WR method drives the exogenous distribution to a target one. We discuss the choice of the DA procedure through a numerical study that illust"},"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":"2302.09288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-02-18T11:23:34Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"6e169fd9c8112196cccdf4d2c2a8f54a46cd8b417cf719d1f4cd63dcc2fdf889","abstract_canon_sha256":"ba77508c729673c1cd93235fea3ca78e28db339641a23366d8f0ce94ff1fe9aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:23.652943Z","signature_b64":"frRZgjXyg0Pmr7KfJd4Lb3a6qkrVa2THVdDc8Qh4R2xU3FIV0rnZbifzs5Cz6hRiNT/F6ztTTV7EqaWt3uSICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6ce8921bbdeb040c00482c94bf6e4bdd90c5c0b9facefbc11b5e87be7ee7741","last_reissued_at":"2026-07-05T05:43:23.652572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:23.652572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation for Imbalanced Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Arthur Charpentier, Denys Pommeret, Samuel Stocksieker","submitted_at":"2023-02-18T11:23:34Z","abstract_excerpt":"In this work, we consider the problem of imbalanced data in a regression framework when the imbalanced phenomenon concerns continuous or discrete covariates. Such a situation can lead to biases in the estimates. In this case, we propose a data augmentation algorithm that combines a weighted resampling (WR) and a data augmentation (DA) procedure. In a first step, the DA procedure permits exploring a wider support than the initial one. In a second step, the WR method drives the exogenous distribution to a target one. We discuss the choice of the DA procedure through a numerical study that illust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09288","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/2302.09288/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":"2302.09288","created_at":"2026-07-05T05:43:23.652641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.09288v1","created_at":"2026-07-05T05:43:23.652641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09288","created_at":"2026-07-05T05:43:23.652641+00:00"},{"alias_kind":"pith_short_12","alias_value":"23HISIN332YE","created_at":"2026-07-05T05:43:23.652641+00:00"},{"alias_kind":"pith_short_16","alias_value":"23HISIN332YEBQAE","created_at":"2026-07-05T05:43:23.652641+00:00"},{"alias_kind":"pith_short_8","alias_value":"23HISIN3","created_at":"2026-07-05T05:43:23.652641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12327","citing_title":"Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced Regression","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23HISIN332YEBQAEQLEUX5XEXX","json":"https://pith.science/pith/23HISIN332YEBQAEQLEUX5XEXX.json","graph_json":"https://pith.science/api/pith-number/23HISIN332YEBQAEQLEUX5XEXX/graph.json","events_json":"https://pith.science/api/pith-number/23HISIN332YEBQAEQLEUX5XEXX/events.json","paper":"https://pith.science/paper/23HISIN3"},"agent_actions":{"view_html":"https://pith.science/pith/23HISIN332YEBQAEQLEUX5XEXX","download_json":"https://pith.science/pith/23HISIN332YEBQAEQLEUX5XEXX.json","view_paper":"https://pith.science/paper/23HISIN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.09288&json=true","fetch_graph":"https://pith.science/api/pith-number/23HISIN332YEBQAEQLEUX5XEXX/graph.json","fetch_events":"https://pith.science/api/pith-number/23HISIN332YEBQAEQLEUX5XEXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23HISIN332YEBQAEQLEUX5XEXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23HISIN332YEBQAEQLEUX5XEXX/action/storage_attestation","attest_author":"https://pith.science/pith/23HISIN332YEBQAEQLEUX5XEXX/action/author_attestation","sign_citation":"https://pith.science/pith/23HISIN332YEBQAEQLEUX5XEXX/action/citation_signature","submit_replication":"https://pith.science/pith/23HISIN332YEBQAEQLEUX5XEXX/action/replication_record"}},"created_at":"2026-07-05T05:43:23.652641+00:00","updated_at":"2026-07-05T05:43:23.652641+00:00"}