{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07680857,0.00283248,0.003634881,0.004386981,0.001854577,0.01136293,0.004437484,0.005485473,0.004725608],"category_scores_gemma":[0.2403751,0.002251046,0.003208393,0.004626294,0.007781678,0.03447983,0.008205913,0.01593322,0.004140685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002548395,"about_ca_system_score_gemma":0.008333705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007983583,"about_ca_topic_score_gemma":0.008212539,"domain_scores_codex":[0.9433401,0.04207999,0.001826238,0.00412561,0.007812378,0.0008157023],"domain_scores_gemma":[0.7297781,0.1462482,0.01282335,0.08186843,0.02531147,0.003970454],"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":[0.0002982552,0.0008558477,0.04139287,0.001237227,0.001548202,0.0001840398,0.00407631,0.07187728,0.008668546,0.2479618,0.04366786,0.5782317],"study_design_scores_gemma":[0.00007392813,0.0001787535,0.00367459,0.0005357178,0.0002189672,0.0001060814,0.001671355,0.2442313,0.005184766,0.7248739,0.01909667,0.0001539599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004207442,0.0005568468,0.9737532,0.01844678,0.0001674696,0.00005312968,0.0001172218,0.001474309,0.001223631],"genre_scores_gemma":[0.08202575,0.00106883,0.9079381,0.005238143,0.0004739096,0.0002503227,0.0004045919,0.001254008,0.001346314],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07680857,"threshold_uncertainty_score":0.4062074,"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."}}