{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000505646,0.0001099358,0.0001325796,0.0002444291,0.0000523869,0.00006505012,0.0004291651,0.00006080382,0.000003780743],"category_scores_gemma":[0.001269187,0.0001309176,0.00002744467,0.000881852,0.00002829217,0.0004042713,0.0002623889,0.0001419777,0.00001759261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001048935,"about_ca_system_score_gemma":0.00009692125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002715807,"about_ca_topic_score_gemma":0.00001581177,"domain_scores_codex":[0.9989378,0.00004240126,0.00008439436,0.0005271324,0.00006524879,0.0003429761],"domain_scores_gemma":[0.9975166,0.001834751,0.00002064879,0.0003393292,0.0001137578,0.0001749586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002302768,0.0002816866,0.1187236,0.000309864,0.0001131794,0.0008522923,0.00157618,0.175859,0.006726237,0.6812621,0.001419656,0.01264592],"study_design_scores_gemma":[0.0006983177,0.0002925757,0.03726151,0.00005543654,0.000008529402,0.00001851204,0.00003664331,0.9512455,0.003890819,0.002336452,0.003754649,0.0004010797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1164495,0.00000514956,0.8829353,0.0001228912,0.00007904018,0.0002270277,0.000001876692,0.000163641,0.00001554516],"genre_scores_gemma":[0.5907083,0.000001355596,0.4091263,0.0000346918,0.00003269579,0.000002836731,2.483762e-7,0.000008236687,0.00008533701],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7753865,"threshold_uncertainty_score":0.5338663,"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."}}