{"id":"W3216603549","doi":"10.1109/icsme52107.2021.00023","title":"Mutation Analysis for Assessing End-to-End Web Tests","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Test suite; Mutation testing; Source code; Web testing; Code coverage; Test case; Web application; Programmer; Web server; Suite; Static analysis; Web page; World Wide Web; Mutation; Software engineering; The Internet; Operating system; Web application security; Programming language; Web development; Software; Machine learning; Regression analysis","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":[0.004408889,0.001449373,0.0008300039,0.007336562,0.0006163574,0.001145444,0.001698621,0.0009906736,0.001058349],"category_scores_gemma":[0.02811705,0.0003086192,0.001047288,0.001617674,0.0009798071,0.001557125,0.001153363,0.0009481957,0.0002880358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001207935,"about_ca_system_score_gemma":0.0017148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004129169,"about_ca_topic_score_gemma":0.004003296,"domain_scores_codex":[0.992758,0.002060662,0.0005575033,0.0007789456,0.003477611,0.0003671616],"domain_scores_gemma":[0.9795747,0.0107266,0.003314558,0.001481633,0.004422836,0.0004796891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007171187,0.0009042513,0.1343458,0.0006500722,0.0004760187,0.001340379,0.0009343746,0.2584907,0.1263301,0.0163811,0.002535126,0.456895],"study_design_scores_gemma":[0.00004859655,0.000671014,0.02824808,0.0001143995,0.0001582803,0.0007493494,0.0002346882,0.9107529,0.05016651,0.006324554,0.002423725,0.0001078701],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2631586,0.0005746106,0.7257511,0.0001472508,0.00003582665,0.0005402597,0.0004534443,0.007193735,0.002145138],"genre_scores_gemma":[0.6900166,0.0001244642,0.3080483,0.0000631917,0.00001313856,0.000330047,0.0005756211,0.0002608584,0.0005677407],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007336562,"threshold_uncertainty_score":0.02331668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0408933321761317,"score_gpt":0.3334186079602007,"score_spread":0.2925252757840689,"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."}}