{"id":"W3180512116","doi":"10.1007/s10664-021-09969-1","title":"The secret life of test smells - an empirical study on test smell evolution and maintenance","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Code smell; Test (biology); Code refactoring; Empirical research; Computer science; Reliability engineering; Engineering; Software; Software quality; Software development; Statistics","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":[0.0007439303,0.0003070963,0.0003543804,0.0001374913,0.0001919713,0.0002143717,0.0008595215,0.0001266604,0.000006963271],"category_scores_gemma":[0.02348369,0.0002458217,0.00008453949,0.001156752,0.0000771983,0.0002917286,0.0005323696,0.000611037,0.00002041191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001721793,"about_ca_system_score_gemma":0.0002202873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001333732,"about_ca_topic_score_gemma":0.000005976503,"domain_scores_codex":[0.9972984,0.0001002831,0.0004525641,0.0007274876,0.0007651084,0.0006561994],"domain_scores_gemma":[0.9882281,0.009930656,0.00006783718,0.001090883,0.0002593066,0.0004231556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006398259,0.0005139294,0.9906872,0.00004391444,0.00003260735,0.00009662886,0.0005274643,0.005564144,0.0004581022,0.00009962605,0.0009708207,0.0009991917],"study_design_scores_gemma":[0.0004531701,0.0007076183,0.9622715,0.0000629811,0.000008862659,0.00003390578,0.00009096917,0.03372103,0.0005573257,0.00008404954,0.0017034,0.0003052421],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6378664,0.0004441466,0.3598767,0.0006144298,0.0003190266,0.0002777534,0.00001033773,0.0005785886,0.00001268352],"genre_scores_gemma":[0.9905614,0.00001959529,0.008975967,0.0001133567,0.0001412023,0.00003971172,0.000003131909,0.00004449208,0.0001011021],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3526951,"threshold_uncertainty_score":0.9999994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02457635823879043,"score_gpt":0.294351377688388,"score_spread":0.2697750194495976,"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."}}