{"id":"W1481457981","doi":"10.1002/spe.2147","title":"Methods for selecting and improving software clustering algorithms","year":2012,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Software Engineering Research","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Computer science; Software; Data mining; Algorithm; Strengths and weaknesses; Process (computing); Machine learning; Programming language","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":[0.02230652,0.002513677,0.001828675,0.008544557,0.001720472,0.004795381,0.005069713,0.002687038,0.003770576],"category_scores_gemma":[0.06101659,0.001619721,0.002738483,0.00614393,0.002141443,0.005383783,0.003884763,0.002948295,0.002093293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002567425,"about_ca_system_score_gemma":0.003789353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001817247,"about_ca_topic_score_gemma":0.002892653,"domain_scores_codex":[0.9700382,0.01100933,0.0033584,0.004021549,0.01071293,0.0008596409],"domain_scores_gemma":[0.9565911,0.021275,0.004247791,0.005446069,0.0119809,0.0004591588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000141938,0.0001821083,0.003091728,0.001725686,0.000194653,0.0002184802,0.001569007,0.0390721,0.0125204,0.1087542,0.00633127,0.8261985],"study_design_scores_gemma":[0.000300747,0.0004081168,0.002685449,0.001169912,0.0004629981,0.001645559,0.001358853,0.6210263,0.06079876,0.1736883,0.1360964,0.0003586295],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009170644,0.0001706676,0.9975216,0.00009036778,0.00002110173,0.0001419344,0.00002068798,0.0004548875,0.0006617529],"genre_scores_gemma":[0.01013466,0.0001865419,0.9886047,0.0000381177,0.00002372723,0.000276452,0.00008709307,0.0001424608,0.0005063146],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02230652,"threshold_uncertainty_score":0.1179696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03515311790681467,"score_gpt":0.3848034187302256,"score_spread":0.3496503008234109,"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."}}