{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M4FBYJ6WQE3XF6HI5RGYJWFROF","short_pith_number":"pith:M4FBYJ6W","schema_version":"1.0","canonical_sha256":"670a1c27d6813772f8e8ec4d84d8b1717580c6d8cd4d4a6a3cf656f3f817fae1","source":{"kind":"arxiv","id":"2104.02240","version":1},"attestation_state":"computed","paper":{"title":"Survey of Imbalanced Data Methodologies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Lian Yu, Nengfeng Zhou","submitted_at":"2021-04-06T02:10:22Z","abstract_excerpt":"Imbalanced data set is a problem often found and well-studied in financial industry. In this paper, we reviewed and compared some popular methodologies handling data imbalance. We then applied the under-sampling/over-sampling methodologies to several modeling algorithms on UCI and Keel data sets. The performance was analyzed for class-imbalance methods, modeling algorithms and grid search criteria comparison."},"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":"2104.02240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-04-06T02:10:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"78a827d53fca96598292a2e10a07698a3952a5f48e721b0bf8a54e1b67a21796","abstract_canon_sha256":"12589e25175915285694c1232106bc2ab54e858ffc7d3bbb314a4a9e67c541e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:16.102722Z","signature_b64":"tcqzk94kgkCuo3bDt/UkJ0jYrpDXtBYcjGDubeu1rhICCS0864jORBiTmNDmcyuw6yq8LDghD9yhpOFuyyTdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"670a1c27d6813772f8e8ec4d84d8b1717580c6d8cd4d4a6a3cf656f3f817fae1","last_reissued_at":"2026-07-05T02:29:16.102321Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:16.102321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Survey of Imbalanced Data Methodologies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Lian Yu, Nengfeng Zhou","submitted_at":"2021-04-06T02:10:22Z","abstract_excerpt":"Imbalanced data set is a problem often found and well-studied in financial industry. In this paper, we reviewed and compared some popular methodologies handling data imbalance. We then applied the under-sampling/over-sampling methodologies to several modeling algorithms on UCI and Keel data sets. The performance was analyzed for class-imbalance methods, modeling algorithms and grid search criteria comparison."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02240","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/2104.02240/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":"2104.02240","created_at":"2026-07-05T02:29:16.102381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02240v1","created_at":"2026-07-05T02:29:16.102381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02240","created_at":"2026-07-05T02:29:16.102381+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4FBYJ6WQE3X","created_at":"2026-07-05T02:29:16.102381+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4FBYJ6WQE3XF6HI","created_at":"2026-07-05T02:29:16.102381+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4FBYJ6W","created_at":"2026-07-05T02:29:16.102381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03392","citing_title":"Absolute Evaluation Measures for Machine Learning: A Survey","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4FBYJ6WQE3XF6HI5RGYJWFROF","json":"https://pith.science/pith/M4FBYJ6WQE3XF6HI5RGYJWFROF.json","graph_json":"https://pith.science/api/pith-number/M4FBYJ6WQE3XF6HI5RGYJWFROF/graph.json","events_json":"https://pith.science/api/pith-number/M4FBYJ6WQE3XF6HI5RGYJWFROF/events.json","paper":"https://pith.science/paper/M4FBYJ6W"},"agent_actions":{"view_html":"https://pith.science/pith/M4FBYJ6WQE3XF6HI5RGYJWFROF","download_json":"https://pith.science/pith/M4FBYJ6WQE3XF6HI5RGYJWFROF.json","view_paper":"https://pith.science/paper/M4FBYJ6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02240&json=true","fetch_graph":"https://pith.science/api/pith-number/M4FBYJ6WQE3XF6HI5RGYJWFROF/graph.json","fetch_events":"https://pith.science/api/pith-number/M4FBYJ6WQE3XF6HI5RGYJWFROF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4FBYJ6WQE3XF6HI5RGYJWFROF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4FBYJ6WQE3XF6HI5RGYJWFROF/action/storage_attestation","attest_author":"https://pith.science/pith/M4FBYJ6WQE3XF6HI5RGYJWFROF/action/author_attestation","sign_citation":"https://pith.science/pith/M4FBYJ6WQE3XF6HI5RGYJWFROF/action/citation_signature","submit_replication":"https://pith.science/pith/M4FBYJ6WQE3XF6HI5RGYJWFROF/action/replication_record"}},"created_at":"2026-07-05T02:29:16.102381+00:00","updated_at":"2026-07-05T02:29:16.102381+00:00"}