{"id":"W3119800663","doi":"10.1109/tse.2020.3048991","title":"A Method to Assess and Argue for Practical Significance in Software Engineering","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Software Engineering Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Marcus och Amalia Wallenbergs minnesfond","keywords":"Computer science; Bayesian probability; Statistical hypothesis testing; Software; Context (archaeology); Machine learning; Data mining; Empirical research; Statistical model; Data science; Artificial intelligence; Statistics; Mathematics; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1356315,0.002753619,0.003176307,0.01384357,0.004561783,0.01261797,0.005968321,0.007779303,0.015741],"category_scores_gemma":[0.3357936,0.002015035,0.005247502,0.008715441,0.0248618,0.0184912,0.01347958,0.0169919,0.003224778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005072116,"about_ca_system_score_gemma":0.00871367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002359495,"about_ca_topic_score_gemma":0.001794265,"domain_scores_codex":[0.8577698,0.1105935,0.004692245,0.008690436,0.01718508,0.001069059],"domain_scores_gemma":[0.5430692,0.3994173,0.01422201,0.02799955,0.0128867,0.00240517],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005452417,0.00007700809,0.001239416,0.0002996074,0.0001401768,0.0001404871,0.001497492,0.002814829,0.0003754208,0.959627,0.002781473,0.03095255],"study_design_scores_gemma":[0.00004128825,0.00006874065,0.0003512652,0.0002279535,0.00004323474,0.0001121029,0.0002234605,0.01549414,0.0003328493,0.972562,0.0104998,0.00004314244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001389583,0.0002096766,0.9900419,0.002706288,0.0001565635,0.0002503706,0.0001185771,0.0002631521,0.004863819],"genre_scores_gemma":[0.07728317,0.0003595064,0.9164883,0.001353772,0.0004296626,0.002320572,0.0001654882,0.0002347127,0.001364865],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8643685,"threshold_uncertainty_score":0.7172964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1236003765638669,"score_gpt":0.27344290841785,"score_spread":0.1498425318539831,"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."}}