{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:32MR4KAYNX7NCVFWUSYC4QDM3Y","short_pith_number":"pith:32MR4KAY","schema_version":"1.0","canonical_sha256":"de991e28186dfed154b6a4b02e406cde2e663146e434ffd9395447a1f8c4a755","source":{"kind":"arxiv","id":"1811.00972","version":2},"attestation_state":"computed","paper":{"title":"Clustering and Learning from Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Dhall, Naman D. Singh","submitted_at":"2018-11-02T16:37:09Z","abstract_excerpt":"A learning classifier must outperform a trivial solution, in case of imbalanced data, this condition usually does not hold true. To overcome this problem, we propose a novel data level resampling method - Clustering Based Oversampling for improved learning from class imbalanced datasets. The essential idea behind the proposed method is to use the distance between a minority class sample and its respective cluster centroid to infer the number of new sample points to be generated for that minority class sample. The proposed algorithm has very less dependence on the technique used for finding clu"},"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":"1811.00972","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-02T16:37:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"70a64bee06dd87001808a9dd60a9eb70424ff91e518f4c89385fcf0e2a223a4e","abstract_canon_sha256":"4bb300406e38e9816147567c2de8cc84e5ae4c171fc32a70685f5c1741dfa01b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:06.534253Z","signature_b64":"hYNb7qp39KTzOj79e+76FnDKxyIF9IJamja8D8h20av6/J4IlipEa3nOIhkFSepAlhie3ZqzdaO6hdvyilO+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de991e28186dfed154b6a4b02e406cde2e663146e434ffd9395447a1f8c4a755","last_reissued_at":"2026-05-18T00:01:06.533674Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:06.533674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustering and Learning from Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhinav Dhall, Naman D. Singh","submitted_at":"2018-11-02T16:37:09Z","abstract_excerpt":"A learning classifier must outperform a trivial solution, in case of imbalanced data, this condition usually does not hold true. To overcome this problem, we propose a novel data level resampling method - Clustering Based Oversampling for improved learning from class imbalanced datasets. The essential idea behind the proposed method is to use the distance between a minority class sample and its respective cluster centroid to infer the number of new sample points to be generated for that minority class sample. The proposed algorithm has very less dependence on the technique used for finding clu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00972","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1811.00972","created_at":"2026-05-18T00:01:06.533769+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00972v2","created_at":"2026-05-18T00:01:06.533769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00972","created_at":"2026-05-18T00:01:06.533769+00:00"},{"alias_kind":"pith_short_12","alias_value":"32MR4KAYNX7N","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"32MR4KAYNX7NCVFW","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"32MR4KAY","created_at":"2026-05-18T12:32:02.567920+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/32MR4KAYNX7NCVFWUSYC4QDM3Y","json":"https://pith.science/pith/32MR4KAYNX7NCVFWUSYC4QDM3Y.json","graph_json":"https://pith.science/api/pith-number/32MR4KAYNX7NCVFWUSYC4QDM3Y/graph.json","events_json":"https://pith.science/api/pith-number/32MR4KAYNX7NCVFWUSYC4QDM3Y/events.json","paper":"https://pith.science/paper/32MR4KAY"},"agent_actions":{"view_html":"https://pith.science/pith/32MR4KAYNX7NCVFWUSYC4QDM3Y","download_json":"https://pith.science/pith/32MR4KAYNX7NCVFWUSYC4QDM3Y.json","view_paper":"https://pith.science/paper/32MR4KAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00972&json=true","fetch_graph":"https://pith.science/api/pith-number/32MR4KAYNX7NCVFWUSYC4QDM3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/32MR4KAYNX7NCVFWUSYC4QDM3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32MR4KAYNX7NCVFWUSYC4QDM3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32MR4KAYNX7NCVFWUSYC4QDM3Y/action/storage_attestation","attest_author":"https://pith.science/pith/32MR4KAYNX7NCVFWUSYC4QDM3Y/action/author_attestation","sign_citation":"https://pith.science/pith/32MR4KAYNX7NCVFWUSYC4QDM3Y/action/citation_signature","submit_replication":"https://pith.science/pith/32MR4KAYNX7NCVFWUSYC4QDM3Y/action/replication_record"}},"created_at":"2026-05-18T00:01:06.533769+00:00","updated_at":"2026-05-18T00:01:06.533769+00:00"}