{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BUWK6RJX7WBYPJFH6OMZHK7DT2","short_pith_number":"pith:BUWK6RJX","schema_version":"1.0","canonical_sha256":"0d2caf4537fd8387a4a7f39993abe39e9a34491a31b57b03530a877953619a87","source":{"kind":"arxiv","id":"1711.00837","version":2},"attestation_state":"computed","paper":{"title":"Oversampling for Imbalanced Learning Based on K-Means and SMOTE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Felix Last, Fernando Bacao, Georgios Douzas","submitted_at":"2017-11-02T17:43:03Z","abstract_excerpt":"Learning from class-imbalanced data continues to be a common and challenging problem in supervised learning as standard classification algorithms are designed to handle balanced class distributions. While different strategies exist to tackle this problem, methods which generate artificial data to achieve a balanced class distribution are more versatile than modifications to the classification algorithm. Such techniques, called oversamplers, modify the training data, allowing any classifier to be used with class-imbalanced datasets. Many algorithms have been proposed for this task, but most are"},"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":"1711.00837","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-02T17:43:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c886c1a7e4ad564615785d3f6974c0657b2b6af2189e35aaad3d2405cdc09ad6","abstract_canon_sha256":"a8c7eaa981a30d9dd0edc801bf2f3938685f51afd722a0606547bfd30e025b9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:45:48.926749Z","signature_b64":"lNfcK4tHnYJBGuAYzcGdJb6fSCFhySPXHeFGvBo8GkgnLzJNvPofbpp+K5Y8LDnyqNyof9fZaUqJNkq74WktCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d2caf4537fd8387a4a7f39993abe39e9a34491a31b57b03530a877953619a87","last_reissued_at":"2026-07-05T00:45:48.926371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:45:48.926371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Oversampling for Imbalanced Learning Based on K-Means and SMOTE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Felix Last, Fernando Bacao, Georgios Douzas","submitted_at":"2017-11-02T17:43:03Z","abstract_excerpt":"Learning from class-imbalanced data continues to be a common and challenging problem in supervised learning as standard classification algorithms are designed to handle balanced class distributions. While different strategies exist to tackle this problem, methods which generate artificial data to achieve a balanced class distribution are more versatile than modifications to the classification algorithm. Such techniques, called oversamplers, modify the training data, allowing any classifier to be used with class-imbalanced datasets. Many algorithms have been proposed for this task, but most are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00837","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1711.00837/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":"1711.00837","created_at":"2026-07-05T00:45:48.926437+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00837v2","created_at":"2026-07-05T00:45:48.926437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00837","created_at":"2026-07-05T00:45:48.926437+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUWK6RJX7WBY","created_at":"2026-07-05T00:45:48.926437+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUWK6RJX7WBYPJFH","created_at":"2026-07-05T00:45:48.926437+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUWK6RJX","created_at":"2026-07-05T00:45:48.926437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26053","citing_title":"When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11231","citing_title":"LiBaGS: Lightweight Boundary Gap Synthesis for Targeted Synthetic Data Selection","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11231","citing_title":"LiBaGS: Lightweight Boundary Gap Synthesis for Targeted Synthetic Data Selection","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUWK6RJX7WBYPJFH6OMZHK7DT2","json":"https://pith.science/pith/BUWK6RJX7WBYPJFH6OMZHK7DT2.json","graph_json":"https://pith.science/api/pith-number/BUWK6RJX7WBYPJFH6OMZHK7DT2/graph.json","events_json":"https://pith.science/api/pith-number/BUWK6RJX7WBYPJFH6OMZHK7DT2/events.json","paper":"https://pith.science/paper/BUWK6RJX"},"agent_actions":{"view_html":"https://pith.science/pith/BUWK6RJX7WBYPJFH6OMZHK7DT2","download_json":"https://pith.science/pith/BUWK6RJX7WBYPJFH6OMZHK7DT2.json","view_paper":"https://pith.science/paper/BUWK6RJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00837&json=true","fetch_graph":"https://pith.science/api/pith-number/BUWK6RJX7WBYPJFH6OMZHK7DT2/graph.json","fetch_events":"https://pith.science/api/pith-number/BUWK6RJX7WBYPJFH6OMZHK7DT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUWK6RJX7WBYPJFH6OMZHK7DT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUWK6RJX7WBYPJFH6OMZHK7DT2/action/storage_attestation","attest_author":"https://pith.science/pith/BUWK6RJX7WBYPJFH6OMZHK7DT2/action/author_attestation","sign_citation":"https://pith.science/pith/BUWK6RJX7WBYPJFH6OMZHK7DT2/action/citation_signature","submit_replication":"https://pith.science/pith/BUWK6RJX7WBYPJFH6OMZHK7DT2/action/replication_record"}},"created_at":"2026-07-05T00:45:48.926437+00:00","updated_at":"2026-07-05T00:45:48.926437+00:00"}