{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01042525,0.0007243483,0.001586668,0.002265999,0.0008119541,0.001278261,0.002202198,0.001161793,0.0008964561],"category_scores_gemma":[0.02826257,0.0004997082,0.001423802,0.002188458,0.0005022414,0.001488738,0.001040814,0.001295254,0.0003243638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001260939,"about_ca_system_score_gemma":0.001969549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0154758,"about_ca_topic_score_gemma":0.0124782,"domain_scores_codex":[0.9944485,0.002892832,0.0003688221,0.000944176,0.001088425,0.0002572325],"domain_scores_gemma":[0.9829975,0.01065764,0.001536015,0.001445853,0.003095671,0.0002672069],"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":[0.0004593124,0.000254061,0.01831599,0.0002519171,0.0004112027,0.0001359462,0.000335293,0.7963141,0.001022315,0.003293098,0.001674696,0.1775321],"study_design_scores_gemma":[0.00001212396,0.00003973028,0.002286661,0.00002771627,0.00003091141,0.00002553612,0.00006559455,0.9943694,0.0008735862,0.002000502,0.0002509391,0.00001720112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1261753,0.0005826987,0.8710107,0.0002355153,0.00005483575,0.0001022983,0.0003221054,0.000576293,0.0009402742],"genre_scores_gemma":[0.6675017,0.0001783379,0.330628,0.00007456196,0.00002977884,0.0001065541,0.0007188871,0.00005433621,0.0007078679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0154758,"threshold_uncertainty_score":0.05513465,"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."}}