{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:GX57CDO7RINCBMZ6CPVONNJNZE","short_pith_number":"pith:GX57CDO7","schema_version":"1.0","canonical_sha256":"35fbf10ddf8a1a20b33e13eae6b52dc91222cf08d5d162bfc6ee94e97c71f064","source":{"kind":"arxiv","id":"1106.1813","version":1},"attestation_state":"computed","paper":{"title":"SMOTE: Synthetic Minority Over-sampling Technique","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"K. W. Bowyer, L. O. Hall, N. V. Chawla, W. P. Kegelmeyer","submitted_at":"2011-06-09T13:53:42Z","abstract_excerpt":"An approach to the construction of classifiers from    imbalanced datasets is described. A dataset is imbalanced if the    classification categories are not approximately equally    represented. Often real-world data sets are predominately composed of    \"normal\" examples with only a small percentage of \"abnormal\" or    \"interesting\" examples. It is also the case that the cost of    misclassifying an abnormal (interesting) example as a normal example    is often much higher than the cost of the reverse    error. Under-sampling of the majority (normal) class has been proposed    as a good means"},"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":"1106.1813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-06-09T13:53:42Z","cross_cats_sorted":[],"title_canon_sha256":"30adfb45e45003d13b8483c15a2f113a3dcf49fbf77656df625e325142ce68a5","abstract_canon_sha256":"1198c67378b992bbd1ac01fb27e70050a8a791e963e5733ab3a578606e74a78c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:07:43.348836Z","signature_b64":"rnlv84/6a/+KpwP5TR8EUvnSb/w8A29l5pEBtqYME1H1THnIZERxH4PG8HlB+kHkHpGP7OPF5JJkyFMGsQqoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35fbf10ddf8a1a20b33e13eae6b52dc91222cf08d5d162bfc6ee94e97c71f064","last_reissued_at":"2026-05-18T04:07:43.348234Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:07:43.348234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMOTE: Synthetic Minority Over-sampling Technique","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"K. W. Bowyer, L. O. Hall, N. V. Chawla, W. P. Kegelmeyer","submitted_at":"2011-06-09T13:53:42Z","abstract_excerpt":"An approach to the construction of classifiers from    imbalanced datasets is described. A dataset is imbalanced if the    classification categories are not approximately equally    represented. Often real-world data sets are predominately composed of    \"normal\" examples with only a small percentage of \"abnormal\" or    \"interesting\" examples. It is also the case that the cost of    misclassifying an abnormal (interesting) example as a normal example    is often much higher than the cost of the reverse    error. Under-sampling of the majority (normal) class has been proposed    as a good means"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.1813","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":""},"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":"1106.1813","created_at":"2026-05-18T04:07:43.348340+00:00"},{"alias_kind":"arxiv_version","alias_value":"1106.1813v1","created_at":"2026-05-18T04:07:43.348340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.1813","created_at":"2026-05-18T04:07:43.348340+00:00"},{"alias_kind":"pith_short_12","alias_value":"GX57CDO7RINC","created_at":"2026-05-18T12:26:30.835961+00:00"},{"alias_kind":"pith_short_16","alias_value":"GX57CDO7RINCBMZ6","created_at":"2026-05-18T12:26:30.835961+00:00"},{"alias_kind":"pith_short_8","alias_value":"GX57CDO7","created_at":"2026-05-18T12:26:30.835961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.08966","citing_title":"Class Imbalance Corrections Failed to Enhance Discrimination, Model Calibration, and Prediction Stability: An Empirical Simulation Study Based on Clinical Dataset","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2409.01962","citing_title":"Attentive Dilated Convolution for Automatic Sleep Staging using Force-directed Layout","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21507","citing_title":"Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2509.24954","citing_title":"Stellar flare detection in XMM-Newton with gradient boosted trees","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09280","citing_title":"AMO-ENE: Attention-based Multi-Omics Fusion Model for Outcome Prediction in Extra Nodal Extension and HPV-associated Oropharyngeal Cancer","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18759","citing_title":"Model-Agnostic Meta Learning for Class Imbalance Adaptation","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GX57CDO7RINCBMZ6CPVONNJNZE","json":"https://pith.science/pith/GX57CDO7RINCBMZ6CPVONNJNZE.json","graph_json":"https://pith.science/api/pith-number/GX57CDO7RINCBMZ6CPVONNJNZE/graph.json","events_json":"https://pith.science/api/pith-number/GX57CDO7RINCBMZ6CPVONNJNZE/events.json","paper":"https://pith.science/paper/GX57CDO7"},"agent_actions":{"view_html":"https://pith.science/pith/GX57CDO7RINCBMZ6CPVONNJNZE","download_json":"https://pith.science/pith/GX57CDO7RINCBMZ6CPVONNJNZE.json","view_paper":"https://pith.science/paper/GX57CDO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1106.1813&json=true","fetch_graph":"https://pith.science/api/pith-number/GX57CDO7RINCBMZ6CPVONNJNZE/graph.json","fetch_events":"https://pith.science/api/pith-number/GX57CDO7RINCBMZ6CPVONNJNZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GX57CDO7RINCBMZ6CPVONNJNZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GX57CDO7RINCBMZ6CPVONNJNZE/action/storage_attestation","attest_author":"https://pith.science/pith/GX57CDO7RINCBMZ6CPVONNJNZE/action/author_attestation","sign_citation":"https://pith.science/pith/GX57CDO7RINCBMZ6CPVONNJNZE/action/citation_signature","submit_replication":"https://pith.science/pith/GX57CDO7RINCBMZ6CPVONNJNZE/action/replication_record"}},"created_at":"2026-05-18T04:07:43.348340+00:00","updated_at":"2026-05-18T04:07:43.348340+00:00"}