{"id":"W2479336862","doi":"10.1109/snpd.2016.7515953","title":"A comparative study on black-box testing with open source applications","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Algoma University","funders":"","keywords":"Black box; Open source software; Computer science; Open source; White-box testing; Non-regression testing; Software; Software performance testing; Software testing; Software reliability testing; Reliability engineering; Software engineering; Operating system; Software quality; Software development; Software construction; Engineering; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002670261,0.0001216481,0.0001552996,0.0000627201,0.0001674952,0.0002269048,0.001336549,0.00001749595,0.000004309687],"category_scores_gemma":[0.00009110298,0.00006506127,0.00001131402,0.0004461679,0.00006015489,0.0002409564,0.0004832247,0.00006074015,0.0001236159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003000195,"about_ca_system_score_gemma":0.00005404193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001175575,"about_ca_topic_score_gemma":0.00001265683,"domain_scores_codex":[0.9990318,0.0000580144,0.0001302899,0.0004225103,0.0001842412,0.0001731041],"domain_scores_gemma":[0.9979372,0.001027277,0.00007902962,0.0007607591,0.0001299249,0.00006579264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007882266,0.00430476,0.3028671,0.00001638192,0.0001704657,0.00003783003,0.01314708,0.0002054409,0.001100259,0.05552569,0.08237971,0.5401665],"study_design_scores_gemma":[0.01823805,0.043107,0.3474734,0.003728207,0.000202027,0.0004119148,0.003515022,0.09316362,0.04327579,0.3900113,0.04811145,0.008762201],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01027492,0.00000167096,0.9630165,0.0004505699,0.000007511883,0.0008557159,5.233118e-7,0.007227709,0.01816492],"genre_scores_gemma":[0.707178,6.034412e-8,0.2916252,0.0001821842,0.00001501788,0.0002256996,1.172852e-7,0.000006345761,0.0007673738],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.696903,"threshold_uncertainty_score":0.2653122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.094093447487158,"score_gpt":0.3420626282076523,"score_spread":0.2479691807204943,"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."}}