{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6W4U7CVJBJUFBZX63KQVNRYZZW","short_pith_number":"pith:6W4U7CVJ","schema_version":"1.0","canonical_sha256":"f5b94f8aa90a6850e6fedaa156c719cd8de3899ee3f7582fbf445082bcc8d03a","source":{"kind":"arxiv","id":"1810.07168","version":2},"attestation_state":"computed","paper":{"title":"An empirical evaluation of imbalanced data strategies from a practitioner's point of view","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacques Wainer","submitted_at":"2018-10-16T17:50:31Z","abstract_excerpt":"This paper evaluates six strategies for mitigating imbalanced data: oversampling, undersampling, ensemble methods, specialized algorithms, class weight adjustments, and a no-mitigation approach referred to as the baseline. These strategies were tested on 58 real-life binary imbalanced datasets with imbalance rates ranging from 3 to 120. We conducted a comparative analysis of 10 under-sampling algorithms, 5 over-sampling algorithms, 2 ensemble methods, and 3 specialized algorithms across eight different performance metrics: accuracy, area under the ROC curve (AUC), balanced accuracy, F1-measure"},"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":"1810.07168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T17:50:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b09aba06c97c6c43a428d82c5c30422d508ec40f2fe6e769b395e466c8fb95df","abstract_canon_sha256":"c2ce9f52815c6545a8cbe814a9563208a4b8eb8170b6919d75953b630f871aee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:10.993674Z","signature_b64":"9n81QSAAKusr/vsQNOn39a+LWd221cxXYAAbKonaqr16vIL1dvxVG4W8fb10JLm9RuIlS2BesawXGQzwOwACBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5b94f8aa90a6850e6fedaa156c719cd8de3899ee3f7582fbf445082bcc8d03a","last_reissued_at":"2026-07-05T07:11:10.993336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:10.993336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An empirical evaluation of imbalanced data strategies from a practitioner's point of view","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacques Wainer","submitted_at":"2018-10-16T17:50:31Z","abstract_excerpt":"This paper evaluates six strategies for mitigating imbalanced data: oversampling, undersampling, ensemble methods, specialized algorithms, class weight adjustments, and a no-mitigation approach referred to as the baseline. These strategies were tested on 58 real-life binary imbalanced datasets with imbalance rates ranging from 3 to 120. We conducted a comparative analysis of 10 under-sampling algorithms, 5 over-sampling algorithms, 2 ensemble methods, and 3 specialized algorithms across eight different performance metrics: accuracy, area under the ROC curve (AUC), balanced accuracy, F1-measure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07168","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/1810.07168/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":"1810.07168","created_at":"2026-07-05T07:11:10.993384+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07168v2","created_at":"2026-07-05T07:11:10.993384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07168","created_at":"2026-07-05T07:11:10.993384+00:00"},{"alias_kind":"pith_short_12","alias_value":"6W4U7CVJBJUF","created_at":"2026-07-05T07:11:10.993384+00:00"},{"alias_kind":"pith_short_16","alias_value":"6W4U7CVJBJUFBZX6","created_at":"2026-07-05T07:11:10.993384+00:00"},{"alias_kind":"pith_short_8","alias_value":"6W4U7CVJ","created_at":"2026-07-05T07:11:10.993384+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/6W4U7CVJBJUFBZX63KQVNRYZZW","json":"https://pith.science/pith/6W4U7CVJBJUFBZX63KQVNRYZZW.json","graph_json":"https://pith.science/api/pith-number/6W4U7CVJBJUFBZX63KQVNRYZZW/graph.json","events_json":"https://pith.science/api/pith-number/6W4U7CVJBJUFBZX63KQVNRYZZW/events.json","paper":"https://pith.science/paper/6W4U7CVJ"},"agent_actions":{"view_html":"https://pith.science/pith/6W4U7CVJBJUFBZX63KQVNRYZZW","download_json":"https://pith.science/pith/6W4U7CVJBJUFBZX63KQVNRYZZW.json","view_paper":"https://pith.science/paper/6W4U7CVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07168&json=true","fetch_graph":"https://pith.science/api/pith-number/6W4U7CVJBJUFBZX63KQVNRYZZW/graph.json","fetch_events":"https://pith.science/api/pith-number/6W4U7CVJBJUFBZX63KQVNRYZZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6W4U7CVJBJUFBZX63KQVNRYZZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6W4U7CVJBJUFBZX63KQVNRYZZW/action/storage_attestation","attest_author":"https://pith.science/pith/6W4U7CVJBJUFBZX63KQVNRYZZW/action/author_attestation","sign_citation":"https://pith.science/pith/6W4U7CVJBJUFBZX63KQVNRYZZW/action/citation_signature","submit_replication":"https://pith.science/pith/6W4U7CVJBJUFBZX63KQVNRYZZW/action/replication_record"}},"created_at":"2026-07-05T07:11:10.993384+00:00","updated_at":"2026-07-05T07:11:10.993384+00:00"}