{"id":"W2604385322","doi":"10.1145/3036290.3036323","title":"Investigating the Accuracy of Test Code Size Prediction using Use Case Metrics and Machine Learning Algorithms","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Machine learning; Regression testing; Software quality; Software metric; Artificial intelligence; Naive Bayes classifier; Algorithm; Test case; Data mining; Software; Software regression; Code coverage; Regression analysis; Software system; Software development; Support vector machine; Software construction; 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":[0.0008035758,0.00008687376,0.0001008796,0.00008377784,0.0006078334,0.000580071,0.0005087897,0.0000380209,0.000002551547],"category_scores_gemma":[0.06263201,0.00006255361,0.00002013627,0.00027528,0.0001183533,0.0009132299,0.0006416868,0.0002783471,7.046746e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002843056,"about_ca_system_score_gemma":0.00004536496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001662321,"about_ca_topic_score_gemma":0.00002402939,"domain_scores_codex":[0.9991145,0.00004842943,0.0001647999,0.000209265,0.0002815603,0.0001814456],"domain_scores_gemma":[0.9904044,0.00865494,0.0001432592,0.0005861941,0.0001268172,0.00008439089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[6.679964e-7,0.00002218498,0.9472895,0.00004298081,0.00002151963,0.0001194447,0.000771637,0.005553479,0.003974902,0.0002656409,0.00003441916,0.04190367],"study_design_scores_gemma":[0.000146107,0.00003768425,0.07536726,0.00002320021,0.000005153721,0.0004141245,0.00002047524,0.9213283,0.002487631,0.00004345947,0.00006450513,0.00006212212],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6368393,0.00006750166,0.3626024,0.0001531893,0.00009279157,0.0001045383,0.000006115767,0.0001176779,0.00001652109],"genre_scores_gemma":[0.8462566,0.0000142786,0.1535991,0.0000139883,0.00003184687,0.000002248548,3.246662e-7,0.000008250438,0.0000734607],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9157748,"threshold_uncertainty_score":0.9452639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0977008421245475,"score_gpt":0.3237995397512882,"score_spread":0.2260986976267407,"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."}}