{"id":"W2860849205","doi":"10.1111/exsy.12311","title":"Resampling with neighbourhood bias on imbalanced domains","year":2018,"lang":"en","type":"article","venue":"Expert Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia","keywords":"Resampling; Computer science; Neighbourhood (mathematics); Machine learning; Artificial intelligence; Regression; Data mining; Variable (mathematics); Set (abstract data type); Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003420219,0.0001952984,0.0002244795,0.0001402609,0.0002283378,0.0003122027,0.001092323,0.00008198532,0.00001165928],"category_scores_gemma":[0.0000630409,0.000144598,0.0000328814,0.000427674,0.00009352358,0.0004235356,0.0001165172,0.0001161325,0.000267675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001165728,"about_ca_system_score_gemma":0.00006181445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001718193,"about_ca_topic_score_gemma":0.00001169074,"domain_scores_codex":[0.9982277,0.0001053599,0.000293354,0.000576067,0.0004415864,0.0003559648],"domain_scores_gemma":[0.9978681,0.0001085583,0.0001917322,0.001559534,0.0001655294,0.0001065281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000134367,0.0003053476,0.002247698,0.00004963045,0.00009283822,0.00005478592,0.005895461,0.00003994314,0.04791963,0.8364066,0.09250651,0.01434723],"study_design_scores_gemma":[0.003029298,0.003677019,0.01144405,0.001561021,0.000009482368,0.0003418576,0.0009779263,0.08170175,0.2519383,0.001914309,0.6410004,0.002404551],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00483651,0.0001115966,0.9754444,0.0006657348,0.0008234798,0.0004124308,0.00001032452,0.001115253,0.01658027],"genre_scores_gemma":[0.9529088,0.00001251537,0.04520624,0.0006039273,0.0005802325,0.0001531704,0.00000873511,0.00002392192,0.0005024651],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9480723,"threshold_uncertainty_score":0.5896537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04663654710554879,"score_gpt":0.2931305538328833,"score_spread":0.2464940067273345,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}