{"id":"W3194585484","doi":"10.1145/3468264.3468609","title":"How disabled tests manifest in test maintainability challenges?","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Technical debt; Software maintenance; Computer science; Test (biology); Maintainability; Software engineering; Code smell; Quality (philosophy); Empirical research; Reliability engineering; Risk analysis (engineering); Java; Codebase; Software quality; Software; Software development; 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":[0.01750574,0.000652355,0.0006057734,0.007103346,0.00122149,0.004394209,0.002405812,0.00221923,0.003358806],"category_scores_gemma":[0.2390302,0.0007408134,0.0006449238,0.005125513,0.003971436,0.01099903,0.002802612,0.002585562,0.0009087325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001924383,"about_ca_system_score_gemma":0.002168585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005499741,"about_ca_topic_score_gemma":0.005261938,"domain_scores_codex":[0.9744187,0.007330501,0.002114829,0.00475291,0.009688552,0.001694478],"domain_scores_gemma":[0.6520679,0.2350342,0.05829585,0.0290114,0.02071067,0.004880084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002656662,0.0001982597,0.6644576,0.0005522746,0.0001438725,0.001743757,0.01176557,0.001907255,0.002657759,0.01299108,0.007689091,0.2956278],"study_design_scores_gemma":[0.00007318792,0.0005896784,0.772875,0.00202456,0.0003582596,0.01656399,0.0205899,0.01961935,0.00799169,0.08867096,0.07039421,0.0002492064],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9004146,0.008794112,0.0484082,0.02143642,0.0003443067,0.0001481978,0.002309744,0.001651894,0.01649241],"genre_scores_gemma":[0.9877072,0.0008165753,0.007660063,0.001341994,0.0001478581,0.00006428039,0.0008670937,0.0003316755,0.001063189],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01750574,"threshold_uncertainty_score":0.09258026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02653790395737383,"score_gpt":0.266220740506306,"score_spread":0.2396828365489321,"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."}}