{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2JACWPGFRVP3SIUD2SFEUVXHMW","short_pith_number":"pith:2JACWPGF","schema_version":"1.0","canonical_sha256":"d2402b3cc58d5fb92283d48a4a56e765960cbddd2a164844341b2fcacaf93a2b","source":{"kind":"arxiv","id":"2201.08528","version":3},"attestation_state":"computed","paper":{"title":"To SMOTE, or not to SMOTE?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hadar Averbuch-Elor, Yotam Elor","submitted_at":"2022-01-21T03:37:39Z","abstract_excerpt":"Balancing the data before training a classifier is a popular technique to address the challenges of imbalanced binary classification in tabular data. Balancing is commonly achieved by duplication of minority samples or by generation of synthetic minority samples. While it is well known that balancing affects each classifier differently, most prior empirical studies did not include strong state-of-the-art (SOTA) classifiers as baselines. In this work, we are interested in understanding whether balancing is beneficial, particularly in the context of SOTA classifiers. Thus, we conduct extensive e"},"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":"2201.08528","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-21T03:37:39Z","cross_cats_sorted":[],"title_canon_sha256":"83cc93a9452e7ccb0993d3a09b73df8f0eb8bad81d7743c398bde8ab01d4c6fb","abstract_canon_sha256":"832722a85491a1ec7f0aaf22e95dd038dd909d5d8059b16e3a7e4b7cb908d21e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:19.242620Z","signature_b64":"H3kRRj26mjH/B5IOFAjIb1A1qKY440u4P5YT70fYCvtouQ8JvEsPNUug+bC5yDKJkt/EZp9PX1T7nDvsWx8MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2402b3cc58d5fb92283d48a4a56e765960cbddd2a164844341b2fcacaf93a2b","last_reissued_at":"2026-07-05T04:22:19.242071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:19.242071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"To SMOTE, or not to SMOTE?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hadar Averbuch-Elor, Yotam Elor","submitted_at":"2022-01-21T03:37:39Z","abstract_excerpt":"Balancing the data before training a classifier is a popular technique to address the challenges of imbalanced binary classification in tabular data. Balancing is commonly achieved by duplication of minority samples or by generation of synthetic minority samples. While it is well known that balancing affects each classifier differently, most prior empirical studies did not include strong state-of-the-art (SOTA) classifiers as baselines. In this work, we are interested in understanding whether balancing is beneficial, particularly in the context of SOTA classifiers. Thus, we conduct extensive e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08528","kind":"arxiv","version":3},"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/2201.08528/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":"2201.08528","created_at":"2026-07-05T04:22:19.242141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08528v3","created_at":"2026-07-05T04:22:19.242141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08528","created_at":"2026-07-05T04:22:19.242141+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JACWPGFRVP3","created_at":"2026-07-05T04:22:19.242141+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JACWPGFRVP3SIUD","created_at":"2026-07-05T04:22:19.242141+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JACWPGF","created_at":"2026-07-05T04:22:19.242141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.01557","citing_title":"An Experimental Study on the Rashomon Effect of Balancing Methods in Imbalanced Classification","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2407.11089","citing_title":"Explainable bank failure prediction models: Counterfactual explanations to reduce the failure risk","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW","json":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW.json","graph_json":"https://pith.science/api/pith-number/2JACWPGFRVP3SIUD2SFEUVXHMW/graph.json","events_json":"https://pith.science/api/pith-number/2JACWPGFRVP3SIUD2SFEUVXHMW/events.json","paper":"https://pith.science/paper/2JACWPGF"},"agent_actions":{"view_html":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW","download_json":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW.json","view_paper":"https://pith.science/paper/2JACWPGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08528&json=true","fetch_graph":"https://pith.science/api/pith-number/2JACWPGFRVP3SIUD2SFEUVXHMW/graph.json","fetch_events":"https://pith.science/api/pith-number/2JACWPGFRVP3SIUD2SFEUVXHMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/action/storage_attestation","attest_author":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/action/author_attestation","sign_citation":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/action/citation_signature","submit_replication":"https://pith.science/pith/2JACWPGFRVP3SIUD2SFEUVXHMW/action/replication_record"}},"created_at":"2026-07-05T04:22:19.242141+00:00","updated_at":"2026-07-05T04:22:19.242141+00:00"}