{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:GXMDT4TAFR2LVBXHBLTNOSPZSI","short_pith_number":"pith:GXMDT4TA","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"},"canonical_sha256":"35d839f2602c74ba86e70ae6d749f99220f98ad5b1ab4857f58adde35cf96fea","source":{"kind":"arxiv","id":"1306.3706","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1306.3706","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"arxiv_version","alias_value":"1306.3706v2","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.3706","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"pith_short_12","alias_value":"GXMDT4TAFR2L","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_16","alias_value":"GXMDT4TAFR2LVBXH","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_8","alias_value":"GXMDT4TA","created_at":"2026-05-18T12:27:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:GXMDT4TAFR2LVBXHBLTNOSPZSI","target":"record","payload":{"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"},"canonical_sha256":"35d839f2602c74ba86e70ae6d749f99220f98ad5b1ab4857f58adde35cf96fea","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"},"source_kind":"arxiv","source_id":"1306.3706","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SEikUdPDiJ5QeynHUPfKnhiMRo8gUxGcJa9EJpt90fgAnet2ij3pxDum0Ad1ZCY+vWRUxtbAh+degVobM1fEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:56:42.397682Z"},"content_sha256":"194a5875ee42d76caf483d844b352c275e9d6b7fe9ddf720b64724f42124293d","schema_version":"1.0","event_id":"sha256:194a5875ee42d76caf483d844b352c275e9d6b7fe9ddf720b64724f42124293d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:GXMDT4TAFR2LVBXHBLTNOSPZSI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZvbE2hF1wrnqJ0YaSogK2phO/o9/ApRxcbUKAet04v2B/RyrRMuIYPCsvDXH8VmGZuIDWFG0L6pxMtC+qVQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:56:42.398251Z"},"content_sha256":"ebdbb82e36a4a18d25b23055c88c1d5d6e8312840797ea08a8e75fe10ab13dac","schema_version":"1.0","event_id":"sha256:ebdbb82e36a4a18d25b23055c88c1d5d6e8312840797ea08a8e75fe10ab13dac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/bundle.json","state_url":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T10:56:42Z","links":{"resolver":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI","bundle":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/bundle.json","state":"https://pith.science/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GXMDT4TAFR2LVBXHBLTNOSPZSI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:GXMDT4TAFR2LVBXHBLTNOSPZSI","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":"80297bab62067733433fdcf321541712dbdf4d6fdfad3b8a657bca9f1e69f1af","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2013-06-16T21:18:12Z","title_canon_sha256":"dc813c783fc41b30d5d6d617fd50022c8f540e525bad6336dfa5eecc66dc131b"},"schema_version":"1.0","source":{"id":"1306.3706","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1306.3706","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"arxiv_version","alias_value":"1306.3706v2","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.3706","created_at":"2026-05-18T02:42:13Z"},{"alias_kind":"pith_short_12","alias_value":"GXMDT4TAFR2L","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_16","alias_value":"GXMDT4TAFR2LVBXH","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_8","alias_value":"GXMDT4TA","created_at":"2026-05-18T12:27:46Z"}],"graph_snapshots":[{"event_id":"sha256:ebdbb82e36a4a18d25b23055c88c1d5d6e8312840797ea08a8e75fe10ab13dac","target":"graph","created_at":"2026-05-18T02:42:13Z","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"},"paper":{"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","authors_text":"Trevor Hastie, William Fithian","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2013-06-16T21:18:12Z","title":"Local case-control sampling: Efficient subsampling in imbalanced data sets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.3706","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":"sha256:194a5875ee42d76caf483d844b352c275e9d6b7fe9ddf720b64724f42124293d","target":"record","created_at":"2026-05-18T02:42:13Z","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":"80297bab62067733433fdcf321541712dbdf4d6fdfad3b8a657bca9f1e69f1af","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2013-06-16T21:18:12Z","title_canon_sha256":"dc813c783fc41b30d5d6d617fd50022c8f540e525bad6336dfa5eecc66dc131b"},"schema_version":"1.0","source":{"id":"1306.3706","kind":"arxiv","version":2}},"canonical_sha256":"35d839f2602c74ba86e70ae6d749f99220f98ad5b1ab4857f58adde35cf96fea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35d839f2602c74ba86e70ae6d749f99220f98ad5b1ab4857f58adde35cf96fea","first_computed_at":"2026-05-18T02:42:13.174411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:42:13.174411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RmugirfAfKmQL/WgBMGtuXdzynWbdf2g1KScBxkHdjt99Uwse/nvfOVJ6KhfWnVXeX3PCGAyiAmzgIirID9DCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:42:13.174886Z","signed_message":"canonical_sha256_bytes"},"source_id":"1306.3706","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:194a5875ee42d76caf483d844b352c275e9d6b7fe9ddf720b64724f42124293d","sha256:ebdbb82e36a4a18d25b23055c88c1d5d6e8312840797ea08a8e75fe10ab13dac"],"state_sha256":"fbfe91449cdb60938abe6362f991f956d73243472a551cd5c07e184fea9a8193"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ocycVVsDx0Nnoj6onTkprkYb+YuYGlH2nniqZvnbnH2Y2HkKVKUws1gv+yxB2NN1iG4G9tGJ9He0tVnHdF8uDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T10:56:42.401136Z","bundle_sha256":"e5396aa30ed8f2b4f95d011541b8b458de2ab6f85c6ce423049bb8cd393e6de0"}}