{"id":"W1986024814","doi":"10.1007/s11219-013-9203-5","title":"BlackHorse: creating smart test cases from brittle recorded tests","year":2013,"lang":"en","type":"article","venue":"Software Quality Journal","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Blackberry (Canada); Western University","funders":"","keywords":"Computer science; Keyword-driven testing; Java; Test case; Test Management Approach; Manual testing; Code coverage; Regression testing; Test (biology); Software engineering; Graphical user interface testing; Reliability engineering; Test harness; Programming language; Software; Engineering; Software development; User interface; 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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001342518,0.0003102769,0.0004134294,0.0001606392,0.0006710535,0.001238209,0.001278288,0.0001576508,0.0002964768],"category_scores_gemma":[0.0196955,0.0002831947,0.0001855117,0.000444639,0.0001086075,0.001090846,0.0003502639,0.0007039171,0.0003297678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001380453,"about_ca_system_score_gemma":0.0002343179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005192721,"about_ca_topic_score_gemma":0.0000750686,"domain_scores_codex":[0.9970093,0.0003741723,0.0008410959,0.000539617,0.000624479,0.0006113457],"domain_scores_gemma":[0.989494,0.007897105,0.0005672153,0.0009827893,0.0006323367,0.0004265912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000005812683,0.0002630132,0.6208603,0.00002729759,0.0000456346,0.0002021787,0.001121599,0.000007231225,0.0003524388,0.0002091687,0.1300512,0.2468542],"study_design_scores_gemma":[0.001004533,0.0006206285,0.5185486,0.000688762,0.00003947044,0.002705282,0.0001272066,0.002721749,0.00130614,0.4674529,0.003299395,0.001485276],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3127856,0.0004740315,0.6709253,0.00156078,0.0008792313,0.0002902095,0.0000276831,0.01249899,0.0005582065],"genre_scores_gemma":[0.4497939,0.00001932442,0.5485925,0.0008274281,0.0004089778,0.00002263453,0.00000808861,0.00002995721,0.0002971634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4672438,"threshold_uncertainty_score":0.999962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04412443132399541,"score_gpt":0.314952805824067,"score_spread":0.2708283745000716,"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."}}