{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003253561,0.0001649356,0.0001415567,0.0002489316,0.000276333,0.0006170158,0.0005358634,0.0001371537,0.000001773476],"category_scores_gemma":[0.1098104,0.0001667789,0.00003071502,0.0004873968,0.00005770105,0.001379019,0.0002971652,0.0008484438,0.000007527915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003544893,"about_ca_system_score_gemma":0.0001264254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002940303,"about_ca_topic_score_gemma":0.000001333251,"domain_scores_codex":[0.998265,0.00007575659,0.0001946931,0.0004639478,0.0004526445,0.0005479448],"domain_scores_gemma":[0.9750965,0.02326371,0.00006966183,0.0005533652,0.000805056,0.0002117121],"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":[0.00006987929,0.0004371752,0.002131461,0.0003016058,0.00004544764,0.0001201555,0.00165258,0.0001594822,0.01245784,0.01214578,0.004088734,0.9663898],"study_design_scores_gemma":[0.005043978,0.009728331,0.02478152,0.00142634,0.0001823664,0.002733922,0.0002476064,0.2532393,0.02840833,0.05363916,0.61487,0.005699195],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08041573,0.0002475317,0.9077122,0.0008649204,0.0005174346,0.0007986516,0.00001661388,0.009175932,0.0002510459],"genre_scores_gemma":[0.347646,0.00002596864,0.651825,0.00003880442,0.0001702981,0.0002324861,0.000008763709,0.00002472194,0.00002796388],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9606907,"threshold_uncertainty_score":0.897688,"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."}}