{"id":"W4233113820","doi":"10.22215/etd/2009-10188","title":"Using machine learning to refine black-box test specifications and test suites","year":2009,"lang":"en","type":"dissertation","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Test (biology); Computer science; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002896789,0.00032206,0.0003051627,0.0004130662,0.0002983795,0.0004037537,0.0006241849,0.0001715559,0.00001551737],"category_scores_gemma":[0.006355444,0.0003091205,0.00005257342,0.0006998986,0.00002609993,0.0001825776,0.000103054,0.0003967501,0.00003773504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006210349,"about_ca_system_score_gemma":0.00008639494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004893346,"about_ca_topic_score_gemma":0.0002613509,"domain_scores_codex":[0.998347,0.00003252632,0.0003572618,0.0006848829,0.0002739094,0.0003044204],"domain_scores_gemma":[0.9964139,0.002397361,0.0001965317,0.0006117787,0.0002265416,0.0001538757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003606634,0.001421181,0.3664109,0.0005799072,0.00008826744,0.0001556879,0.009539388,0.0003419891,0.04353846,0.01735015,0.07688973,0.4836482],"study_design_scores_gemma":[0.001223079,0.003517419,0.5395616,0.004416458,0.0003048792,0.0004639642,0.0003520901,0.3093292,0.04392457,0.04587372,0.04367398,0.007359033],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2891725,0.005076027,0.4932008,0.007495804,0.001570574,0.003763985,0.0001116491,0.1290025,0.07060614],"genre_scores_gemma":[0.187122,0.00008873272,0.7964563,0.0003434542,0.0001582248,0.00001774097,0.000214576,0.0000527122,0.01554632],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4762892,"threshold_uncertainty_score":0.9999361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05609987584792415,"score_gpt":0.3105859834633714,"score_spread":0.2544861076154473,"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."}}