{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1005628,0.0007942682,0.0006634504,0.004562589,0.001011721,0.00259981,0.00226576,0.001937193,0.004837502],"category_scores_gemma":[0.5158507,0.0004097821,0.000699081,0.003976475,0.003858352,0.005844179,0.002404916,0.001867341,0.001032287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002183749,"about_ca_system_score_gemma":0.001227999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002263281,"about_ca_topic_score_gemma":0.001815227,"domain_scores_codex":[0.8056425,0.1618789,0.007028989,0.004835552,0.01910903,0.001504995],"domain_scores_gemma":[0.1514138,0.7671471,0.03246001,0.02225365,0.0240069,0.002718438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.008122681,0.006736598,0.743463,0.001309372,0.001085113,0.0006044123,0.005080531,0.01701611,0.00122099,0.01704777,0.005758299,0.1925551],"study_design_scores_gemma":[0.002000903,0.02965834,0.7206479,0.0009213187,0.0008809093,0.002702165,0.00705072,0.1975503,0.004741454,0.011909,0.02167602,0.0002609487],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9561801,0.00206476,0.02018106,0.00150493,0.0001285214,0.0008422612,0.0009391722,0.0002632449,0.01789587],"genre_scores_gemma":[0.9908231,0.000241427,0.006899624,0.0002021385,0.00009566137,0.0004337757,0.0005995997,0.00005610726,0.0006483967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1005628,"threshold_uncertainty_score":0.5318335,"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."}}