{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6W4U7CVJBJUFBZX63KQVNRYZZW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c2ce9f52815c6545a8cbe814a9563208a4b8eb8170b6919d75953b630f871aee","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T17:50:31Z","title_canon_sha256":"b09aba06c97c6c43a428d82c5c30422d508ec40f2fe6e769b395e466c8fb95df"},"schema_version":"1.0","source":{"id":"1810.07168","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.07168","created_at":"2026-07-05T07:11:10Z"},{"alias_kind":"arxiv_version","alias_value":"1810.07168v2","created_at":"2026-07-05T07:11:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07168","created_at":"2026-07-05T07:11:10Z"},{"alias_kind":"pith_short_12","alias_value":"6W4U7CVJBJUF","created_at":"2026-07-05T07:11:10Z"},{"alias_kind":"pith_short_16","alias_value":"6W4U7CVJBJUFBZX6","created_at":"2026-07-05T07:11:10Z"},{"alias_kind":"pith_short_8","alias_value":"6W4U7CVJ","created_at":"2026-07-05T07:11:10Z"}],"graph_snapshots":[{"event_id":"sha256:a912cc05719507c3a624e542fc369324020be869ab113772ccb706ba825f5aa6","target":"graph","created_at":"2026-07-05T07:11:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1810.07168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jacques Wainer","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T17:50:31Z","title":"An empirical evaluation of imbalanced data strategies from a practitioner's point of view"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07168","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:43e081b2dc3020117833e846971bcce8be155d2fae2683b226d079be561d77ed","target":"record","created_at":"2026-07-05T07:11:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c2ce9f52815c6545a8cbe814a9563208a4b8eb8170b6919d75953b630f871aee","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-16T17:50:31Z","title_canon_sha256":"b09aba06c97c6c43a428d82c5c30422d508ec40f2fe6e769b395e466c8fb95df"},"schema_version":"1.0","source":{"id":"1810.07168","kind":"arxiv","version":2}},"canonical_sha256":"f5b94f8aa90a6850e6fedaa156c719cd8de3899ee3f7582fbf445082bcc8d03a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5b94f8aa90a6850e6fedaa156c719cd8de3899ee3f7582fbf445082bcc8d03a","first_computed_at":"2026-07-05T07:11:10.993336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:10.993336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9n81QSAAKusr/vsQNOn39a+LWd221cxXYAAbKonaqr16vIL1dvxVG4W8fb10JLm9RuIlS2BesawXGQzwOwACBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:10.993674Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.07168","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43e081b2dc3020117833e846971bcce8be155d2fae2683b226d079be561d77ed","sha256:a912cc05719507c3a624e542fc369324020be869ab113772ccb706ba825f5aa6"],"state_sha256":"0d6eb6efbc2b95452da1d36c9ceffc1e6a8ff64a9e38c0014aa2ec54ae111c3b"}