{"id":"W4401908463","doi":"10.1109/icst60714.2024.00039","title":"Are We Testing or Being Tested? Exploring the Practical Applications of Large Language Models in Software Testing","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Software testing; Software reliability testing; Software performance testing; Software engineering; System integration testing; Test strategy; Software; Programming language; Software construction; Software system","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":[0.03921922,0.0004341284,0.0003630767,0.001764682,0.001886877,0.006786299,0.00174509,0.00193012,0.002871617],"category_scores_gemma":[0.1148032,0.0005807722,0.0004332014,0.001669448,0.009812624,0.01747055,0.003601049,0.002660038,0.0003818817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004539677,"about_ca_system_score_gemma":0.004462334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004138658,"about_ca_topic_score_gemma":0.007442435,"domain_scores_codex":[0.9574346,0.03708815,0.0006911018,0.001105489,0.002851672,0.0008290556],"domain_scores_gemma":[0.7704642,0.2118857,0.006146253,0.005176239,0.004878673,0.001448786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001816826,0.0005392377,0.06797178,0.0006355312,0.00004646634,0.001652199,0.51824,0.003050733,0.004053007,0.2424938,0.003071123,0.1580645],"study_design_scores_gemma":[0.00009640924,0.0005486718,0.02781302,0.001729726,0.00008588344,0.001770793,0.5723134,0.04344361,0.00331643,0.2852946,0.06342122,0.0001661869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7502638,0.001385571,0.1756472,0.03809923,0.00006770314,0.0004436807,0.000157886,0.0001976165,0.03373725],"genre_scores_gemma":[0.9672369,0.0003361544,0.0305844,0.0008959253,0.00001295824,0.0002560761,0.00004292013,0.00004432405,0.0005903819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03921922,"threshold_uncertainty_score":0.2074135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1581902158217574,"score_gpt":0.3575882324472093,"score_spread":0.199398016625452,"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."}}