{"id":"W4409921902","doi":"10.1007/s10994-025-06766-5","title":"Imbalanced regression pipeline recommendation","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Pipeline (software); Regression; Computer science; Artificial intelligence; Machine learning; Regression analysis; 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":[0.0006201447,0.0001425503,0.0001513847,0.0002147005,0.0003401904,0.0001698566,0.0005004138,0.00006478665,0.00008249613],"category_scores_gemma":[0.0004841191,0.0001212864,0.00004637702,0.0005946498,0.00001588344,0.0003394889,0.0002659922,0.0004355677,0.00008482773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004623597,"about_ca_system_score_gemma":0.00003691818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007695526,"about_ca_topic_score_gemma":0.00001421572,"domain_scores_codex":[0.998705,0.0002736268,0.0002550274,0.0004181359,0.0001374362,0.0002107548],"domain_scores_gemma":[0.9991719,0.0001419046,0.0001513546,0.0004256195,0.00006111763,0.00004808444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001449947,0.00004145648,0.02564126,0.00001713133,0.000009553194,0.000001797893,0.0001172193,0.00067484,0.001773232,0.01894469,0.006149475,0.9466149],"study_design_scores_gemma":[0.0003419,0.00002416881,0.01147569,0.00004402865,0.000004910955,0.000002550885,0.000008597541,0.6163336,0.0003655026,0.0006188532,0.3706671,0.0001131045],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001625026,0.0002826856,0.9454324,0.01451314,0.0004161572,0.00009760314,0.000001502971,0.0006614194,0.03697007],"genre_scores_gemma":[0.9600199,0.00009600853,0.02457848,0.0008892648,0.00007898203,0.00001740574,0.0003249298,0.00001189085,0.01398313],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9583949,"threshold_uncertainty_score":0.4945916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01144865326301334,"score_gpt":0.2877203833240607,"score_spread":0.2762717300610474,"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."}}