{"id":"W2099441126","doi":"10.1109/tse.2003.1214327","title":"General test result checking with log file analysis","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Random testing; Formalism (music); Programming language; Unit testing; Operating system; Software; Test case","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":[0.005819703,0.00161318,0.001298364,0.003277684,0.0007152322,0.003221233,0.004041425,0.00168409,0.005121144],"category_scores_gemma":[0.0368065,0.0008092988,0.001706109,0.00183454,0.003313489,0.006775377,0.003306326,0.00195161,0.001431096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001318562,"about_ca_system_score_gemma":0.002989001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002180503,"about_ca_topic_score_gemma":0.001605702,"domain_scores_codex":[0.9863593,0.004570359,0.001313333,0.001529735,0.005437585,0.0007896477],"domain_scores_gemma":[0.9638414,0.01705532,0.003144664,0.01255218,0.003080451,0.0003258988],"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":[0.001872118,0.0009540087,0.01767866,0.00185562,0.0003008865,0.001802247,0.001051244,0.1117063,0.0617876,0.1840515,0.01417102,0.6027688],"study_design_scores_gemma":[0.0002562022,0.0006021031,0.002331463,0.0003287669,0.0001928569,0.002089937,0.0001342801,0.7014862,0.1226012,0.1508023,0.0189905,0.0001841779],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007896787,0.00007660389,0.9808736,0.00009210307,0.00001678504,0.0001476252,0.0001269231,0.00981705,0.000952517],"genre_scores_gemma":[0.3169245,0.000163728,0.6777416,0.0002509195,0.00008238597,0.0006486533,0.0009724647,0.001433479,0.001782355],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005819703,"threshold_uncertainty_score":0.03077793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01114718760434826,"score_gpt":0.215001202784079,"score_spread":0.2038540151797307,"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."}}