{"id":"W2155803905","doi":"10.5555/2663608.2663627","title":"BlackHorse: creating smart test cases from brittle recorded tests","year":2012,"lang":"en","type":"article","venue":"Automation of Software Test","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Blackberry (Canada); Western University","funders":"","keywords":"Computer science; Keyword-driven testing; Java; Test case; Test Management Approach; Graphical user interface testing; Test (biology); Code coverage; Manual testing; Software engineering; Test harness; Programming language; Reliability engineering; Software; Software development; User interface; Engineering; Software construction; 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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005097098,0.0002469934,0.0003122175,0.0001802799,0.0002003184,0.0001226153,0.0006689989,0.0001332105,0.0000792377],"category_scores_gemma":[0.01945576,0.0002512479,0.00008757023,0.000593097,0.0000902402,0.0009848125,0.0002547714,0.0001625617,0.000182539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000076181,"about_ca_system_score_gemma":0.00007952058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009794144,"about_ca_topic_score_gemma":0.00001797662,"domain_scores_codex":[0.9981877,0.0000653782,0.0005478497,0.0003702813,0.0004012309,0.0004275854],"domain_scores_gemma":[0.9885282,0.009738054,0.0004309326,0.0008525564,0.0002782403,0.0001720026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001392828,0.0003432801,0.9159905,0.00003911203,0.0000121815,0.000009207142,0.0007060122,0.00000572774,0.0005812125,0.0002140782,0.02220058,0.05989666],"study_design_scores_gemma":[0.0004588318,0.0003843787,0.9590498,0.0005348371,0.00004288073,0.0001672919,0.00002239102,0.01256697,0.01088926,0.01373396,0.001429803,0.0007195591],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3622459,0.0007243641,0.5887453,0.0004505986,0.0008362776,0.0005738725,0.000127334,0.0446465,0.001649868],"genre_scores_gemma":[0.6062533,0.000004959054,0.3933446,0.0001240726,0.000108395,0.00002376831,0.00002847751,0.00001875272,0.00009367598],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2440073,"threshold_uncertainty_score":0.999994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02530140677214751,"score_gpt":0.2744781825957093,"score_spread":0.2491767758235618,"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."}}