{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001859247,0.0002235154,0.0002133193,0.0001230194,0.0004735022,0.0004300238,0.0004285979,0.0001038028,0.000003085086],"category_scores_gemma":[0.02294915,0.0002223795,0.00003774373,0.0003828134,0.00008059035,0.004000981,0.0007167278,0.0002868484,0.000003241902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006088681,"about_ca_system_score_gemma":0.00006025462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000754854,"about_ca_topic_score_gemma":9.233037e-7,"domain_scores_codex":[0.998033,0.0001314706,0.0002412425,0.0005549305,0.0002443036,0.0007949909],"domain_scores_gemma":[0.9910553,0.007893129,0.0001188784,0.0004189729,0.0001936616,0.0003200843],"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":[0.00001905884,0.00004148304,0.01167144,0.0001513541,0.00002201928,0.000003659602,0.01908786,0.00001793715,0.001643884,0.0002612328,0.00003342736,0.9670466],"study_design_scores_gemma":[0.007542259,0.003091757,0.06429813,0.0009407534,0.0003753434,0.0100669,0.03659786,0.4165165,0.09903242,0.003202572,0.3484212,0.00991421],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01375862,0.003943625,0.9807007,0.0001794402,0.0005443953,0.0003059804,0.000001262114,0.0005557178,0.00001021678],"genre_scores_gemma":[0.08289396,0.00007934457,0.9163092,0.0002591846,0.0001792482,0.0002010251,9.702245e-7,0.00002905446,0.00004794447],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9571325,"threshold_uncertainty_score":0.9852809,"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."}}