{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RLBFF3GYIEYFQJ5XRVSMSHOOJM","short_pith_number":"pith:RLBFF3GY","schema_version":"1.0","canonical_sha256":"8ac252ecd841305827b78d64c91dce4b378e932d423944ad9adb452a2c6e0cc8","source":{"kind":"arxiv","id":"2111.03516","version":1},"attestation_state":"computed","paper":{"title":"Solving the Class Imbalance Problem Using a Counterfactual Method for Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mark T. Keane, Mohammed Temraz","submitted_at":"2021-11-05T14:14:06Z","abstract_excerpt":"Learning from class imbalanced datasets poses challenges for many machine learning algorithms. Many real-world domains are, by definition, class imbalanced by virtue of having a majority class that naturally has many more instances than its minority class (e.g. genuine bank transactions occur much more often than fraudulent ones). Many methods have been proposed to solve the class imbalance problem, among the most popular being oversampling techniques (such as SMOTE). These methods generate synthetic instances in the minority class, to balance the dataset, performing data augmentations that im"},"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":"2111.03516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-05T14:14:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1842558f8b10225be901796e4607eb238cb022e209087c21364ffcb0573f3a8f","abstract_canon_sha256":"b8865f37e38bde052787e3e65538e419f7d86c637fb4e2d4c0d860738ef1615f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:25.277348Z","signature_b64":"efTL6RWb/VA1LpkhJ+PH7vyngjORvylcXHdxTjUpA08gLBjgMdUcuYCRLCfARi10qHvAOfQSlAi+ewvBv2W7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ac252ecd841305827b78d64c91dce4b378e932d423944ad9adb452a2c6e0cc8","last_reissued_at":"2026-07-05T03:29:25.276926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:25.276926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving the Class Imbalance Problem Using a Counterfactual Method for Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mark T. Keane, Mohammed Temraz","submitted_at":"2021-11-05T14:14:06Z","abstract_excerpt":"Learning from class imbalanced datasets poses challenges for many machine learning algorithms. Many real-world domains are, by definition, class imbalanced by virtue of having a majority class that naturally has many more instances than its minority class (e.g. genuine bank transactions occur much more often than fraudulent ones). Many methods have been proposed to solve the class imbalance problem, among the most popular being oversampling techniques (such as SMOTE). These methods generate synthetic instances in the minority class, to balance the dataset, performing data augmentations that im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03516","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/2111.03516/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":"2111.03516","created_at":"2026-07-05T03:29:25.277004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.03516v1","created_at":"2026-07-05T03:29:25.277004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03516","created_at":"2026-07-05T03:29:25.277004+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLBFF3GYIEYF","created_at":"2026-07-05T03:29:25.277004+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLBFF3GYIEYFQJ5X","created_at":"2026-07-05T03:29:25.277004+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLBFF3GY","created_at":"2026-07-05T03:29:25.277004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18933","citing_title":"VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLBFF3GYIEYFQJ5XRVSMSHOOJM","json":"https://pith.science/pith/RLBFF3GYIEYFQJ5XRVSMSHOOJM.json","graph_json":"https://pith.science/api/pith-number/RLBFF3GYIEYFQJ5XRVSMSHOOJM/graph.json","events_json":"https://pith.science/api/pith-number/RLBFF3GYIEYFQJ5XRVSMSHOOJM/events.json","paper":"https://pith.science/paper/RLBFF3GY"},"agent_actions":{"view_html":"https://pith.science/pith/RLBFF3GYIEYFQJ5XRVSMSHOOJM","download_json":"https://pith.science/pith/RLBFF3GYIEYFQJ5XRVSMSHOOJM.json","view_paper":"https://pith.science/paper/RLBFF3GY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.03516&json=true","fetch_graph":"https://pith.science/api/pith-number/RLBFF3GYIEYFQJ5XRVSMSHOOJM/graph.json","fetch_events":"https://pith.science/api/pith-number/RLBFF3GYIEYFQJ5XRVSMSHOOJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLBFF3GYIEYFQJ5XRVSMSHOOJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLBFF3GYIEYFQJ5XRVSMSHOOJM/action/storage_attestation","attest_author":"https://pith.science/pith/RLBFF3GYIEYFQJ5XRVSMSHOOJM/action/author_attestation","sign_citation":"https://pith.science/pith/RLBFF3GYIEYFQJ5XRVSMSHOOJM/action/citation_signature","submit_replication":"https://pith.science/pith/RLBFF3GYIEYFQJ5XRVSMSHOOJM/action/replication_record"}},"created_at":"2026-07-05T03:29:25.277004+00:00","updated_at":"2026-07-05T03:29:25.277004+00:00"}