{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GDLMFF4RJSATG53YLXXY32ZFDP","short_pith_number":"pith:GDLMFF4R","schema_version":"1.0","canonical_sha256":"30d6c297914c813377785def8deb251bf1fd8a2eed00b78f8f0c66b95835a07b","source":{"kind":"arxiv","id":"2412.07437","version":1},"attestation_state":"computed","paper":{"title":"Impact of Sampling Techniques and Data Leakage on XGBoost Performance in Credit Card Fraud Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Siyaxolisa Kabane","submitted_at":"2024-12-10T11:54:14Z","abstract_excerpt":"Credit card fraud detection remains a critical challenge in financial security, with machine learning models like XGBoost(eXtreme gradient boosting) emerging as powerful tools for identifying fraudulent transactions. However, the inherent class imbalance in credit card transaction datasets poses significant challenges for model performance. Although sampling techniques are commonly used to address this imbalance, their implementation sometimes precedes the train-test split, potentially introducing data leakage.\n  This study presents a comparative analysis of XGBoost's performance in credit car"},"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":"2412.07437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T11:54:14Z","cross_cats_sorted":[],"title_canon_sha256":"3c9ec030bc1c90f9bc7336182f9285c9a7c53d96e2652d2316f374378cd4f1e2","abstract_canon_sha256":"d07ec39e7390d459b90901bc92864ec722f51fba0e776d01e872552897d3b537"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:09.734483Z","signature_b64":"4KyTWWyPeoAmFzSnqZy8BfsRannmvu6oaVotqTc8sqQX/xlXBVSbkONyyQBQJHesbpRldml9JqSvHimVGNxTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30d6c297914c813377785def8deb251bf1fd8a2eed00b78f8f0c66b95835a07b","last_reissued_at":"2026-07-05T09:47:09.733909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:09.733909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Impact of Sampling Techniques and Data Leakage on XGBoost Performance in Credit Card Fraud Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Siyaxolisa Kabane","submitted_at":"2024-12-10T11:54:14Z","abstract_excerpt":"Credit card fraud detection remains a critical challenge in financial security, with machine learning models like XGBoost(eXtreme gradient boosting) emerging as powerful tools for identifying fraudulent transactions. However, the inherent class imbalance in credit card transaction datasets poses significant challenges for model performance. Although sampling techniques are commonly used to address this imbalance, their implementation sometimes precedes the train-test split, potentially introducing data leakage.\n  This study presents a comparative analysis of XGBoost's performance in credit car"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07437","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.07437/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2412.07437","created_at":"2026-07-05T09:47:09.733967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07437v1","created_at":"2026-07-05T09:47:09.733967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07437","created_at":"2026-07-05T09:47:09.733967+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDLMFF4RJSAT","created_at":"2026-07-05T09:47:09.733967+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDLMFF4RJSATG53Y","created_at":"2026-07-05T09:47:09.733967+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDLMFF4R","created_at":"2026-07-05T09:47:09.733967+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/GDLMFF4RJSATG53YLXXY32ZFDP","json":"https://pith.science/pith/GDLMFF4RJSATG53YLXXY32ZFDP.json","graph_json":"https://pith.science/api/pith-number/GDLMFF4RJSATG53YLXXY32ZFDP/graph.json","events_json":"https://pith.science/api/pith-number/GDLMFF4RJSATG53YLXXY32ZFDP/events.json","paper":"https://pith.science/paper/GDLMFF4R"},"agent_actions":{"view_html":"https://pith.science/pith/GDLMFF4RJSATG53YLXXY32ZFDP","download_json":"https://pith.science/pith/GDLMFF4RJSATG53YLXXY32ZFDP.json","view_paper":"https://pith.science/paper/GDLMFF4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07437&json=true","fetch_graph":"https://pith.science/api/pith-number/GDLMFF4RJSATG53YLXXY32ZFDP/graph.json","fetch_events":"https://pith.science/api/pith-number/GDLMFF4RJSATG53YLXXY32ZFDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDLMFF4RJSATG53YLXXY32ZFDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDLMFF4RJSATG53YLXXY32ZFDP/action/storage_attestation","attest_author":"https://pith.science/pith/GDLMFF4RJSATG53YLXXY32ZFDP/action/author_attestation","sign_citation":"https://pith.science/pith/GDLMFF4RJSATG53YLXXY32ZFDP/action/citation_signature","submit_replication":"https://pith.science/pith/GDLMFF4RJSATG53YLXXY32ZFDP/action/replication_record"}},"created_at":"2026-07-05T09:47:09.733967+00:00","updated_at":"2026-07-05T09:47:09.733967+00:00"}