{"id":"W1557076420","doi":"","title":"An empirical evaluation of system and regression testing","year":2002,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Software Engineering Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Regression testing; Computer science; Software quality; Empirical research; Context (archaeology); Non-regression testing; Quality (philosophy); Software reliability testing; Software engineering; Development testing; Reliability engineering; Software; Software system; Software development; Software construction; Engineering; Statistics; Programming language; Mathematics","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":[0.002802056,0.000128998,0.0002840757,0.0001683906,0.0003161711,0.00004846777,0.0007375411,0.00004613386,0.000001979044],"category_scores_gemma":[0.01516105,0.00008328082,0.00002842853,0.001598326,0.0003461391,0.0002494717,0.0003578312,0.0002034687,0.000001251907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002455525,"about_ca_system_score_gemma":0.0002201444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001634105,"about_ca_topic_score_gemma":0.000008023724,"domain_scores_codex":[0.9967819,0.00079677,0.0002786845,0.0004016689,0.001409834,0.0003311074],"domain_scores_gemma":[0.9849749,0.004114585,0.0001505437,0.0006320683,0.01004672,0.00008117803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006145116,0.001371247,0.04245434,0.004415733,0.0006278251,0.00001047519,0.0679718,0.03694949,0.09519124,0.08587239,0.005698155,0.6588228],"study_design_scores_gemma":[0.002133595,0.001578064,0.005944512,0.0028537,0.00002275471,0.000002205055,0.01641108,0.8640788,0.1038757,0.002527085,0.0003045169,0.000268013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9830762,0.003754172,0.006272607,0.002500736,0.0004735435,0.003192615,0.00005720945,0.0001054796,0.0005674602],"genre_scores_gemma":[0.9911839,0.00007311007,0.008522548,0.000002861655,0.00001982066,0.0001027862,5.642207e-7,0.000008607695,0.00008585277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8271292,"threshold_uncertainty_score":0.9931347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3136702464333212,"score_gpt":0.470684057169565,"score_spread":0.1570138107362438,"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."}}