{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:BQWAJPUXVEHVXKPMQAWILIBL3I","short_pith_number":"pith:BQWAJPUX","schema_version":"1.0","canonical_sha256":"0c2c04be97a90f5ba9ec802c85a02bda099035754fddba6b66adca9456ea5cd9","source":{"kind":"arxiv","id":"1403.3378","version":2},"attestation_state":"computed","paper":{"title":"Box Drawings for Learning with Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Cynthia Rudin, Siong Thye Goh","submitted_at":"2014-03-13T19:28:48Z","abstract_excerpt":"The vast majority of real world classification problems are imbalanced, meaning there are far fewer data from the class of interest (the positive class) than from other classes. We propose two machine learning algorithms to handle highly imbalanced classification problems. The classifiers constructed by both methods are created as unions of parallel axis rectangles around the positive examples, and thus have the benefit of being interpretable. The first algorithm uses mixed integer programming to optimize a weighted balance between positive and negative class accuracies. Regularization is intr"},"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":"1403.3378","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-03-13T19:28:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"84bbd8bc79ae78225ea7f68ec90a991e7458d8a53893218e2c45fb3f6f89a7e8","abstract_canon_sha256":"1b6840a27f5d5b35ea994086bffb915851b3e35ac3619112fe55baae3766a571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:50:12.732937Z","signature_b64":"DEvmrzVxipzZoSg9wOZ0IAfJgaWyU0ijceJNHxFEI7gZUAXoX2l2+T9MHeU95/GuVW6UrtwnXs2m7ZTjXA2+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c2c04be97a90f5ba9ec802c85a02bda099035754fddba6b66adca9456ea5cd9","last_reissued_at":"2026-05-18T02:50:12.732300Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:50:12.732300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Box Drawings for Learning with Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Cynthia Rudin, Siong Thye Goh","submitted_at":"2014-03-13T19:28:48Z","abstract_excerpt":"The vast majority of real world classification problems are imbalanced, meaning there are far fewer data from the class of interest (the positive class) than from other classes. We propose two machine learning algorithms to handle highly imbalanced classification problems. The classifiers constructed by both methods are created as unions of parallel axis rectangles around the positive examples, and thus have the benefit of being interpretable. The first algorithm uses mixed integer programming to optimize a weighted balance between positive and negative class accuracies. Regularization is intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.3378","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":""},"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":"1403.3378","created_at":"2026-05-18T02:50:12.732396+00:00"},{"alias_kind":"arxiv_version","alias_value":"1403.3378v2","created_at":"2026-05-18T02:50:12.732396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.3378","created_at":"2026-05-18T02:50:12.732396+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQWAJPUXVEHV","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQWAJPUXVEHVXKPM","created_at":"2026-05-18T12:28:22.404517+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQWAJPUX","created_at":"2026-05-18T12:28:22.404517+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/BQWAJPUXVEHVXKPMQAWILIBL3I","json":"https://pith.science/pith/BQWAJPUXVEHVXKPMQAWILIBL3I.json","graph_json":"https://pith.science/api/pith-number/BQWAJPUXVEHVXKPMQAWILIBL3I/graph.json","events_json":"https://pith.science/api/pith-number/BQWAJPUXVEHVXKPMQAWILIBL3I/events.json","paper":"https://pith.science/paper/BQWAJPUX"},"agent_actions":{"view_html":"https://pith.science/pith/BQWAJPUXVEHVXKPMQAWILIBL3I","download_json":"https://pith.science/pith/BQWAJPUXVEHVXKPMQAWILIBL3I.json","view_paper":"https://pith.science/paper/BQWAJPUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1403.3378&json=true","fetch_graph":"https://pith.science/api/pith-number/BQWAJPUXVEHVXKPMQAWILIBL3I/graph.json","fetch_events":"https://pith.science/api/pith-number/BQWAJPUXVEHVXKPMQAWILIBL3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQWAJPUXVEHVXKPMQAWILIBL3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQWAJPUXVEHVXKPMQAWILIBL3I/action/storage_attestation","attest_author":"https://pith.science/pith/BQWAJPUXVEHVXKPMQAWILIBL3I/action/author_attestation","sign_citation":"https://pith.science/pith/BQWAJPUXVEHVXKPMQAWILIBL3I/action/citation_signature","submit_replication":"https://pith.science/pith/BQWAJPUXVEHVXKPMQAWILIBL3I/action/replication_record"}},"created_at":"2026-05-18T02:50:12.732396+00:00","updated_at":"2026-05-18T02:50:12.732396+00:00"}