{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GF5BWEVORYOO6MODFBEXKR2XIE","short_pith_number":"pith:GF5BWEVO","schema_version":"1.0","canonical_sha256":"317a1b12ae8e1cef31c328497547574100b9fa47e0c16ec8d06ce1c10b67ff23","source":{"kind":"arxiv","id":"2307.01224","version":1},"attestation_state":"computed","paper":{"title":"INGB: Informed Nonlinear Granular Ball Oversampling Framework for Noisy Imbalanced Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Guoying Wang, Hao Zhou, Min Li, Qun Liu, Yabin Shao","submitted_at":"2023-07-03T01:55:20Z","abstract_excerpt":"In classification problems, the datasets are usually imbalanced, noisy or complex. Most sampling algorithms only make some improvements to the linear sampling mechanism of the synthetic minority oversampling technique (SMOTE). Nevertheless, linear oversampling has several unavoidable drawbacks. Linear oversampling is susceptible to overfitting, and the synthetic samples lack diversity and rarely account for the original distribution characteristics. An informed nonlinear oversampling framework with the granular ball (INGB) as a new direction of oversampling is proposed in this paper. It uses g"},"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":"2307.01224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-07-03T01:55:20Z","cross_cats_sorted":[],"title_canon_sha256":"636e399b8e6346f3e2279693a2162b82810f7fe29ebfb4783906221e22ddafa1","abstract_canon_sha256":"77f8d6c44b298ab7b203b77f26e8583b6ffb09662248339650c2707026eeb29a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:53.250300Z","signature_b64":"C82XMlCqcKc6e8RknRv0ZNkfca6TmiO9CrdRSJmVsRcqW3RiCRHA7Pd4tjk3J45pegHRyl7FojyLMNgTyIE8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"317a1b12ae8e1cef31c328497547574100b9fa47e0c16ec8d06ce1c10b67ff23","last_reissued_at":"2026-07-05T06:27:53.249670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:53.249670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"INGB: Informed Nonlinear Granular Ball Oversampling Framework for Noisy Imbalanced Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Guoying Wang, Hao Zhou, Min Li, Qun Liu, Yabin Shao","submitted_at":"2023-07-03T01:55:20Z","abstract_excerpt":"In classification problems, the datasets are usually imbalanced, noisy or complex. Most sampling algorithms only make some improvements to the linear sampling mechanism of the synthetic minority oversampling technique (SMOTE). Nevertheless, linear oversampling has several unavoidable drawbacks. Linear oversampling is susceptible to overfitting, and the synthetic samples lack diversity and rarely account for the original distribution characteristics. An informed nonlinear oversampling framework with the granular ball (INGB) as a new direction of oversampling is proposed in this paper. It uses g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01224","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/2307.01224/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":"2307.01224","created_at":"2026-07-05T06:27:53.249756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01224v1","created_at":"2026-07-05T06:27:53.249756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01224","created_at":"2026-07-05T06:27:53.249756+00:00"},{"alias_kind":"pith_short_12","alias_value":"GF5BWEVORYOO","created_at":"2026-07-05T06:27:53.249756+00:00"},{"alias_kind":"pith_short_16","alias_value":"GF5BWEVORYOO6MOD","created_at":"2026-07-05T06:27:53.249756+00:00"},{"alias_kind":"pith_short_8","alias_value":"GF5BWEVO","created_at":"2026-07-05T06:27:53.249756+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/GF5BWEVORYOO6MODFBEXKR2XIE","json":"https://pith.science/pith/GF5BWEVORYOO6MODFBEXKR2XIE.json","graph_json":"https://pith.science/api/pith-number/GF5BWEVORYOO6MODFBEXKR2XIE/graph.json","events_json":"https://pith.science/api/pith-number/GF5BWEVORYOO6MODFBEXKR2XIE/events.json","paper":"https://pith.science/paper/GF5BWEVO"},"agent_actions":{"view_html":"https://pith.science/pith/GF5BWEVORYOO6MODFBEXKR2XIE","download_json":"https://pith.science/pith/GF5BWEVORYOO6MODFBEXKR2XIE.json","view_paper":"https://pith.science/paper/GF5BWEVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01224&json=true","fetch_graph":"https://pith.science/api/pith-number/GF5BWEVORYOO6MODFBEXKR2XIE/graph.json","fetch_events":"https://pith.science/api/pith-number/GF5BWEVORYOO6MODFBEXKR2XIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GF5BWEVORYOO6MODFBEXKR2XIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GF5BWEVORYOO6MODFBEXKR2XIE/action/storage_attestation","attest_author":"https://pith.science/pith/GF5BWEVORYOO6MODFBEXKR2XIE/action/author_attestation","sign_citation":"https://pith.science/pith/GF5BWEVORYOO6MODFBEXKR2XIE/action/citation_signature","submit_replication":"https://pith.science/pith/GF5BWEVORYOO6MODFBEXKR2XIE/action/replication_record"}},"created_at":"2026-07-05T06:27:53.249756+00:00","updated_at":"2026-07-05T06:27:53.249756+00:00"}