{"id":"W2066687630","doi":"10.1007/s10664-013-9292-6","title":"Towards improving statistical modeling of software engineering data: think locally, act globally!","year":2014,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Cluster analysis; Multivariate adaptive regression splines; Data mining; Machine learning; Software; Statistical model; Parametric statistics; Data modeling; Artificial intelligence; Data science; Regression analysis; Nonparametric regression; Mathematics; Statistics; Software 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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016381,0.0006694493,0.0008349661,0.0004124803,0.000124505,0.0003376013,0.004319607,0.0003456689,0.00002600497],"category_scores_gemma":[0.02623099,0.0006862371,0.0001695381,0.001170493,0.00005613797,0.00120254,0.002985732,0.001048136,0.00004525076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003223441,"about_ca_system_score_gemma":0.0003243718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001286241,"about_ca_topic_score_gemma":0.000003246519,"domain_scores_codex":[0.9946133,0.00007837607,0.0009592032,0.001375649,0.001584694,0.001388743],"domain_scores_gemma":[0.9931766,0.003165867,0.0001223745,0.002581164,0.0002928786,0.000661063],"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":[0.00001610107,0.0001172588,0.01965073,0.0007580407,0.0001319538,0.00006823659,0.0002876942,0.9438688,0.0002455895,0.00158402,0.0006822437,0.03258938],"study_design_scores_gemma":[0.0004624903,0.000119649,0.01367269,0.0001877216,0.00002463917,0.00005007787,0.000004224997,0.9827684,0.0002506896,0.0001416125,0.001590871,0.0007268979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02669663,0.0003577343,0.9688433,0.0001255161,0.0008839309,0.0002935095,0.00006042791,0.002726006,0.00001289407],"genre_scores_gemma":[0.4842553,0.000009064082,0.5152208,0.00006663864,0.0002713797,0.00001861134,0.00005105316,0.00009743574,0.000009656332],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4575587,"threshold_uncertainty_score":0.9995589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03219726578772242,"score_gpt":0.2902385702837676,"score_spread":0.2580413044960452,"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."}}