{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:H55FQ6T2N5SGKYX5WRFMYYWT6W","short_pith_number":"pith:H55FQ6T2","canonical_record":{"source":{"id":"1812.10857","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2018-12-28T01:10:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1cd7e1ce6432dfd0316d4854130776f28bc4fcf1fbf3c3f34f2ba4ede9668bf3","abstract_canon_sha256":"d76509263ee1d3ec03cc2509cdd93f9f1bbc0cffef61c51e39c238c265074e0d"},"schema_version":"1.0"},"canonical_sha256":"3f7a587a7a6f646562fdb44acc62d3f59ffdb706eeb84003e7856803fa1b1867","source":{"kind":"arxiv","id":"1812.10857","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.10857","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"arxiv_version","alias_value":"1812.10857v2","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10857","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"pith_short_12","alias_value":"H55FQ6T2N5SG","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H55FQ6T2N5SGKYX5","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H55FQ6T2","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:H55FQ6T2N5SGKYX5WRFMYYWT6W","target":"record","payload":{"canonical_record":{"source":{"id":"1812.10857","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2018-12-28T01:10:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1cd7e1ce6432dfd0316d4854130776f28bc4fcf1fbf3c3f34f2ba4ede9668bf3","abstract_canon_sha256":"d76509263ee1d3ec03cc2509cdd93f9f1bbc0cffef61c51e39c238c265074e0d"},"schema_version":"1.0"},"canonical_sha256":"3f7a587a7a6f646562fdb44acc62d3f59ffdb706eeb84003e7856803fa1b1867","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:30.509708Z","signature_b64":"hY/YXUUi7PVpjeHoXvMuAK+gSpZ3bK5jZF6jGaAPehZHcH6ZOflxxgPFI+iJoDb17prevFnLPkzEZYI4hiP1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f7a587a7a6f646562fdb44acc62d3f59ffdb706eeb84003e7856803fa1b1867","last_reissued_at":"2026-05-17T23:39:30.509153Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:30.509153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.10857","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":"2026-05-17T23:39:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cpoBnem+8tqM+0O/p6r9rZk2wQG70YC+15toKBuXaL4aQJocPnJUmPVr3gkRcRLsfRQoIJQykjCQfa6y6YPUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T13:27:02.875291Z"},"content_sha256":"a0a6df9a9483ffa340a42449b3dfa28e538d075e8d28bc9a933dba7319ea8956","schema_version":"1.0","event_id":"sha256:a0a6df9a9483ffa340a42449b3dfa28e538d075e8d28bc9a933dba7319ea8956"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:H55FQ6T2N5SGKYX5WRFMYYWT6W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Descriptive Study of Variable Discretization and Cost-Sensitive Logistic Regression on Imbalanced Credit Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.AP","authors_text":"Herman Ray, Jennifer Priestley, Lili Zhang, Soon Tan","submitted_at":"2018-12-28T01:10:13Z","abstract_excerpt":"Training classification models on imbalanced data tends to result in bias towards the majority class. In this paper, we demonstrate how variable discretization and cost-sensitive logistic regression help mitigate this bias on an imbalanced credit scoring dataset, and further show the application of the variable discretization technique on the data from other domains, demonstrating its potential as a generic technique for classifying imbalanced data beyond credit socring. The performance measurements include ROC curves, Area under ROC Curve (AUC), Type I Error, Type II Error, accuracy, and F1 s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10857","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":"2026-05-17T23:39:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nphmfx1MjG5GwoigmcqN8q5YZV6ukDsN8miONQzTgxLfl9F0SiWoMYUlvfuHx70AQWU3cqKaTzZ8sxvSttFcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T13:27:02.875706Z"},"content_sha256":"fcbad1e641173b24574642116d4d4cabdb1578ad097ded6451bddbaac29cecf7","schema_version":"1.0","event_id":"sha256:fcbad1e641173b24574642116d4d4cabdb1578ad097ded6451bddbaac29cecf7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H55FQ6T2N5SGKYX5WRFMYYWT6W/bundle.json","state_url":"https://pith.science/pith/H55FQ6T2N5SGKYX5WRFMYYWT6W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H55FQ6T2N5SGKYX5WRFMYYWT6W/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":"2026-06-11T13:27:02Z","links":{"resolver":"https://pith.science/pith/H55FQ6T2N5SGKYX5WRFMYYWT6W","bundle":"https://pith.science/pith/H55FQ6T2N5SGKYX5WRFMYYWT6W/bundle.json","state":"https://pith.science/pith/H55FQ6T2N5SGKYX5WRFMYYWT6W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H55FQ6T2N5SGKYX5WRFMYYWT6W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:H55FQ6T2N5SGKYX5WRFMYYWT6W","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":"d76509263ee1d3ec03cc2509cdd93f9f1bbc0cffef61c51e39c238c265074e0d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2018-12-28T01:10:13Z","title_canon_sha256":"1cd7e1ce6432dfd0316d4854130776f28bc4fcf1fbf3c3f34f2ba4ede9668bf3"},"schema_version":"1.0","source":{"id":"1812.10857","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.10857","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"arxiv_version","alias_value":"1812.10857v2","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10857","created_at":"2026-05-17T23:39:30Z"},{"alias_kind":"pith_short_12","alias_value":"H55FQ6T2N5SG","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H55FQ6T2N5SGKYX5","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H55FQ6T2","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:fcbad1e641173b24574642116d4d4cabdb1578ad097ded6451bddbaac29cecf7","target":"graph","created_at":"2026-05-17T23:39:30Z","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":"Training classification models on imbalanced data tends to result in bias towards the majority class. In this paper, we demonstrate how variable discretization and cost-sensitive logistic regression help mitigate this bias on an imbalanced credit scoring dataset, and further show the application of the variable discretization technique on the data from other domains, demonstrating its potential as a generic technique for classifying imbalanced data beyond credit socring. The performance measurements include ROC curves, Area under ROC Curve (AUC), Type I Error, Type II Error, accuracy, and F1 s","authors_text":"Herman Ray, Jennifer Priestley, Lili Zhang, Soon Tan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2018-12-28T01:10:13Z","title":"A Descriptive Study of Variable Discretization and Cost-Sensitive Logistic Regression on Imbalanced Credit Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10857","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:a0a6df9a9483ffa340a42449b3dfa28e538d075e8d28bc9a933dba7319ea8956","target":"record","created_at":"2026-05-17T23:39:30Z","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":"d76509263ee1d3ec03cc2509cdd93f9f1bbc0cffef61c51e39c238c265074e0d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2018-12-28T01:10:13Z","title_canon_sha256":"1cd7e1ce6432dfd0316d4854130776f28bc4fcf1fbf3c3f34f2ba4ede9668bf3"},"schema_version":"1.0","source":{"id":"1812.10857","kind":"arxiv","version":2}},"canonical_sha256":"3f7a587a7a6f646562fdb44acc62d3f59ffdb706eeb84003e7856803fa1b1867","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f7a587a7a6f646562fdb44acc62d3f59ffdb706eeb84003e7856803fa1b1867","first_computed_at":"2026-05-17T23:39:30.509153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:30.509153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hY/YXUUi7PVpjeHoXvMuAK+gSpZ3bK5jZF6jGaAPehZHcH6ZOflxxgPFI+iJoDb17prevFnLPkzEZYI4hiP1Bg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:30.509708Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.10857","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0a6df9a9483ffa340a42449b3dfa28e538d075e8d28bc9a933dba7319ea8956","sha256:fcbad1e641173b24574642116d4d4cabdb1578ad097ded6451bddbaac29cecf7"],"state_sha256":"55e3f7beb68ae151e3d5b070dd999c6fd0a8b94bbf0624cd364a7cca9d261efd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+/DBrNsE2kEarbcMP66OJAxGOWjB4cXb3p11650arAYsOSISe/DPc4/qzycPwavdPGlMdHZ2Ay8DGGWUe0bBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T13:27:02.877808Z","bundle_sha256":"30817b5119ff8012bf0cc29589e2418a825f016b8fc62d3cab5bc5d20b9f9ef4"}}