{"id":"W48642625","doi":"","title":"Validation Against Actual Behavior: Still a Challenge for Testing Tools.","year":2010,"lang":"en","type":"article","venue":"Software Engineering Research and Practice","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University; Carleton University","funders":"","keywords":"Computer science; Traceability; Software engineering; Acceptance testing; Model-based testing; Quality (philosophy); Code (set theory); Test (biology); Test case; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05596434,0.001837937,0.001791521,0.002305927,0.001307106,0.00675483,0.0058455,0.004344017,0.001663219],"category_scores_gemma":[0.2392383,0.000960637,0.001230997,0.001631183,0.006379229,0.0125241,0.004512497,0.005194858,0.001224063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001736008,"about_ca_system_score_gemma":0.005224718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001387312,"about_ca_topic_score_gemma":0.0009476159,"domain_scores_codex":[0.9169723,0.03439575,0.005470107,0.004881979,0.03698991,0.001289923],"domain_scores_gemma":[0.6356137,0.2336781,0.018872,0.08119463,0.02875392,0.001887629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002635188,0.0008125468,0.029661,0.003823219,0.0005329485,0.001042592,0.008017714,0.03456453,0.03855792,0.2165572,0.01014068,0.6560261],"study_design_scores_gemma":[0.0003389642,0.003069059,0.01648856,0.008726912,0.0007117849,0.007146618,0.006065268,0.2500557,0.09539402,0.4776897,0.1335786,0.0007347598],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0386834,0.002023727,0.9424039,0.005399222,0.0002620788,0.0003712489,0.0001756282,0.00441554,0.006265408],"genre_scores_gemma":[0.3696134,0.002189497,0.6204802,0.00243132,0.0002179754,0.0007764375,0.0007661884,0.001574009,0.001950996],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05596434,"threshold_uncertainty_score":0.2959712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1350736130410877,"score_gpt":0.3782731407054294,"score_spread":0.2431995276643417,"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."}}