{"id":"W4310506204","doi":"10.1145/3563767.3568132","title":"Evaluating the Quality of Student-Written Software Tests with Curated Mutation Analysis","year":2022,"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; Correctness; Programming language; Assertion; Software engineering; Software quality; Code coverage; Software; Software testing; Test (biology); Invocation; Test case; Software development; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.002098082,0.00008864528,0.0001751162,0.0001403769,0.0003270589,0.00007075416,0.0008335816,0.00001326153,0.00003077406],"category_scores_gemma":[0.0004604084,0.00005657975,0.00006742023,0.002255778,0.00003740829,0.0001294737,0.0003826028,0.0001267872,0.000001005583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004533876,"about_ca_system_score_gemma":0.00008205744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000581404,"about_ca_topic_score_gemma":0.00003609985,"domain_scores_codex":[0.9980295,0.0004579076,0.0002937067,0.0002786515,0.0008038813,0.0001364067],"domain_scores_gemma":[0.9976642,0.001146333,0.0002652584,0.0006565875,0.0002428128,0.00002477002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004193151,0.0004126136,0.8497679,0.00002596191,0.0005942915,0.00001747078,0.004572778,0.05782744,0.0003289038,0.004016595,0.001630608,0.0807635],"study_design_scores_gemma":[0.0003942759,0.001235009,0.7024266,0.0000129118,0.0002039923,0.00002022957,0.0002458377,0.280607,0.0002698611,0.01428186,0.00001165419,0.0002908115],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4414661,0.00002270009,0.5549685,0.0003436392,0.00002780751,0.0001495614,0.000002904345,0.002922576,0.00009622864],"genre_scores_gemma":[0.7683159,1.620138e-7,0.2313391,0.0002076847,0.00000486931,0.00005645324,0.000005685375,0.000004118041,0.00006603695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3268498,"threshold_uncertainty_score":0.2515506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1151691530031579,"score_gpt":0.427437826411757,"score_spread":0.3122686734085992,"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."}}