{"id":"W4313578599","doi":"10.1002/smr.2529","title":"Optimized fuzzy clustering‐based k‐nearest neighbors imputation for mixed missing data in software development effort estimation","year":2023,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Data mining; Computer science; Categorical variable; Imputation (statistics); Missing data; Cluster analysis; Fuzzy logic; Software; Artificial intelligence; Machine learning","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":[0.001822574,0.0001738381,0.0002759474,0.0007310559,0.0001890628,0.0002196617,0.0007635269,0.0001059133,0.000001883257],"category_scores_gemma":[0.003939856,0.0001669886,0.0000433264,0.001031486,0.00003291059,0.001257891,0.0002101912,0.0002277598,0.000003769125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001820536,"about_ca_system_score_gemma":0.0007958845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006499111,"about_ca_topic_score_gemma":0.000009710396,"domain_scores_codex":[0.9980487,0.000044376,0.0006240063,0.0003421655,0.0005865114,0.0003542769],"domain_scores_gemma":[0.9977699,0.001012387,0.0003028282,0.0003033156,0.0004515231,0.0001600509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000232489,0.0001017907,0.03629029,0.001247691,0.00004728712,0.00004346841,0.001208735,0.7555903,0.00002864424,0.00004205935,0.0008617931,0.2043055],"study_design_scores_gemma":[0.001954143,0.0001053834,0.1224688,0.0004530789,0.00001051308,0.00004775526,0.00004685029,0.8732276,0.0001314517,0.001067971,0.0002612555,0.0002251788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04423043,0.0002524372,0.95417,0.0003469726,0.0004709738,0.0002839483,0.000008428671,0.0002357743,0.000001020223],"genre_scores_gemma":[0.389717,0.00000978976,0.6100687,0.00002865433,0.0000619315,0.00002339059,0.00005867962,0.0000206648,0.00001126173],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3454866,"threshold_uncertainty_score":0.6809598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03699946842914301,"score_gpt":0.3226420344798559,"score_spread":0.2856425660507129,"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."}}