{"id":"W3010658448","doi":"10.1002/smr.2260","title":"Fuzzy case‐based‐reasoning‐based imputation for incomplete data in software engineering repositories","year":2020,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Missing data; Imputation (statistics); Categorical variable; Data mining; Computer science; Software; Fuzzy logic; Reuse; Machine learning; Artificial intelligence; Engineering","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007499888,0.0001777462,0.0002833153,0.0002944286,0.0001194275,0.00019943,0.0007547856,0.00009299794,0.000001159152],"category_scores_gemma":[0.008818156,0.0001747975,0.00005566065,0.0007517937,0.00002976224,0.001149275,0.0001512587,0.0003369423,7.383809e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001299517,"about_ca_system_score_gemma":0.0004774438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001630301,"about_ca_topic_score_gemma":0.000004710185,"domain_scores_codex":[0.9983445,0.00004095913,0.0005069824,0.0003576501,0.000456927,0.0002929743],"domain_scores_gemma":[0.997396,0.001270777,0.0002603959,0.000306205,0.0005323319,0.0002342723],"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":[0.0005469712,0.0002461138,0.4652444,0.004942846,0.0001428685,0.002323949,0.003341804,0.4948526,0.0002560054,0.001017804,0.002500552,0.0245841],"study_design_scores_gemma":[0.00243263,0.0006604292,0.03019372,0.0005677248,0.00003308114,0.001364201,0.0001020464,0.9620911,0.0004158906,0.0006225922,0.001040607,0.0004759808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04877603,0.0009123537,0.9489642,0.0005996618,0.0003567087,0.0001913511,0.0000264524,0.0001726436,6.040372e-7],"genre_scores_gemma":[0.6913205,0.000002969842,0.3083109,0.00008842979,0.0002378405,0.00001021938,0.00001038263,0.00001763829,0.000001172695],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6425444,"threshold_uncertainty_score":0.999531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03250375646217073,"score_gpt":0.2970636970608757,"score_spread":0.2645599405987049,"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."}}