{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:GXMDT4TAFR2LVBXHBLTNOSPZSI","short_pith_number":"pith:GXMDT4TA","schema_version":"1.0","canonical_sha256":"35d839f2602c74ba86e70ae6d749f99220f98ad5b1ab4857f58adde35cf96fea","source":{"kind":"arxiv","id":"1306.3706","version":2},"attestation_state":"computed","paper":{"title":"Local case-control sampling: Efficient subsampling in imbalanced data sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.CO","authors_text":"Trevor Hastie, William Fithian","submitted_at":"2013-06-16T21:18:12Z","abstract_excerpt":"For classification problems with significant class imbalance, subsampling can reduce computational costs at the price of inflated variance in estimating model parameters. We propose a method for subsampling efficiently for logistic regression by adjusting the class balance locally in feature space via an accept-reject scheme. Our method generalizes standard case-control sampling, using a pilot estimate to preferentially select examples whose responses are conditionally rare given their features. The biased subsampling is corrected by a post-hoc analytic adjustment to the parameters. The method"},"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":"1306.3706","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2013-06-16T21:18:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dc813c783fc41b30d5d6d617fd50022c8f540e525bad6336dfa5eecc66dc131b","abstract_canon_sha256":"80297bab62067733433fdcf321541712dbdf4d6fdfad3b8a657bca9f1e69f1af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:42:13.174886Z","signature_b64":"RmugirfAfKmQL/WgBMGtuXdzynWbdf2g1KScBxkHdjt99Uwse/nvfOVJ6KhfWnVXeX3PCGAyiAmzgIirID9DCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35d839f2602c74ba86e70ae6d749f99220f98ad5b1ab4857f58adde35cf96fea","last_reissued_at":"2026-05-18T02:42:13.174411Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:42:13.174411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local case-control sampling: Efficient subsampling in imbalanced data sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.CO","authors_text":"Trevor Hastie, William Fithian","submitted_at":"2013-06-16T21:18:12Z","abstract_excerpt":"For classification problems with significant class imbalance, subsampling can reduce computational costs at the price of inflated variance in estimating model parameters. We propose a method for subsampling efficiently for logistic regression by adjusting the class balance locally in feature space via an accept-reject scheme. Our method generalizes standard case-control sampling, using a pilot estimate to preferentially select examples whose responses are conditionally rare given their features. The biased subsampling is corrected by a post-hoc analytic adjustment to the parameters. The method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.3706","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":"1306.3706","created_at":"2026-05-18T02:42:13.174495+00:00"},{"alias_kind":"arxiv_version","alias_value":"1306.3706v2","created_at":"2026-05-18T02:42:13.174495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.3706","created_at":"2026-05-18T02:42:13.174495+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXMDT4TAFR2L","created_at":"2026-05-18T12:27:46.883200+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXMDT4TAFR2LVBXH","created_at":"2026-05-18T12:27:46.883200+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXMDT4TA","created_at":"2026-05-18T12:27:46.883200+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/GXMDT4TAFR2LVBXHBLTNOSPZSI","json":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI.json","graph_json":"https://pith.science/api/pith-number/GXMDT4TAFR2LVBXHBLTNOSPZSI/graph.json","events_json":"https://pith.science/api/pith-number/GXMDT4TAFR2LVBXHBLTNOSPZSI/events.json","paper":"https://pith.science/paper/GXMDT4TA"},"agent_actions":{"view_html":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI","download_json":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI.json","view_paper":"https://pith.science/paper/GXMDT4TA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1306.3706&json=true","fetch_graph":"https://pith.science/api/pith-number/GXMDT4TAFR2LVBXHBLTNOSPZSI/graph.json","fetch_events":"https://pith.science/api/pith-number/GXMDT4TAFR2LVBXHBLTNOSPZSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/action/storage_attestation","attest_author":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/action/author_attestation","sign_citation":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/action/citation_signature","submit_replication":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/action/replication_record"}},"created_at":"2026-05-18T02:42:13.174495+00:00","updated_at":"2026-05-18T02:42:13.174495+00:00"}